—————————————————–

9
 A
Project report on
“Crop Growth optimization and Disease
Detection ”

Submitted By:
Akshada Gaikwad [B190582013]
Darshana Jadhav [B190582023]
Akshada Kute [B190582033]
B.E. [AI & DS Engineering]

2023-24
Guided By:
Mr. M. T. Dhande

Department of Artificial Intelligence and Data Science

Engineering
Matoshri College of Engineering and Research
Centre, Odhagaon Nashik-422105

Savitribai Phule Pune University

 Matoshri College of Engineering and
Research Centre, Nashik

This is to certify that Project stage I report entitled

“Crop Growth optimization and Disease Detection ”
Gaikwad Akshada Jadhav Darshana
Kute Akshada
Is a record of bonafide work carried out by us, under our guidance,
in partial fulfillment of the requirement for the award of Degree of
Bachelor of Engineering (Artificial Intelligence and Data Science) at
Matoshri College of Engineering and Research Centre, Nashik under
the Savitribai Phule Pune University, Pune.

Date: / / 2023

........................... ..............................
Mr. M.T. Dhande Mr. M.T. Dhande
Project Guide Project Coordinator

........................... ..............................
Dr. J.J.Chopade Dr. G. K. Kharate
Head of Department Principal

EXAMINATION

........................ ..........................
Sign of External 1 Sign of External 2
 Acknowledgement

It is a privilege for us to have been associated with Mr. M. T. Dhande,

my guide, during this project work. I have been greatly benefited by his valuable
suggestions and ideas. It is with great pleasure that I express our deep sense of grat-
itude for his valuable guidance, constant encouragement and patience throughout
this work.

I express our gratitude to Dr. J. J. Chopade, Head,Department of Computer

Engineering well as to Mr. M. T. Dhande [Project Co-ordinator] for his con-
stant encouragement, co-operation, and support.

I take this opportunity to thank all our classmates for their company during the
course work and for useful discussion I had with them.

I would be failing in our duties if I do not make a mention of our family members
including our parents for providing moral support, without which this work would
not have been completed.

Akshada Gaikwad [B190582013]

Darshana Jadhav [B190582023]
Akshada Kute [B190582033]
 Abstract

The system uses advanced computer programs to predict how much crops will
grow and recommend the best fertilizer to use. It is an innovative solution designed
to enhance agricultural practices and increase crop productivity. This system lever-
ages a combination of machine learning techniques, including both traditional sta-
tistical models and advanced deep learning algorithms, to accurately forecast crop
yields. By analyzing historical data, environmental factors, and crop-specific infor-
mation, the system predicts future yields, helping farmers make informed decisions
about planting, harvesting, and resource allocation. Furthermore, the system in-
corporates a fertilizer recommendation component, which suggests the optimal type
and quantity of fertilizers based on soil nutrient analysis and crop requirements,
promoting efficient resource management and sustainability. This hybrid approach
offers a comprehensive and data-driven solution for precision agriculture, improving
crop yield while minimizing the environmental impact of excessive fertilizer use.

Keywords: Crop yield prediction, Support Vector Machine, Disease Prediction,

Fertilizer recommendation
Contents

List of Figures iv

1 Introduction 1
1.1 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.3 Project scope . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.4 Hypothesis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.5 Strategy Plan to solve problem . . . . . . . . . . . . . . . . . . . . . 5

2 Literature Survey 6
2.1 Table of related paper refereed . . . . . . . . . . . . . . . . . . . . . . 6
2.1.1 Transforming Information-Based Agricultural Portal to Knowledge-
Based Agricultural Hub . . . . . . . . . . . . . . . . . . . . . 7
2.1.2 Crop Yield Prediction and Fertilizer Recommendation System
Using Hybrid Machine Learning Algorithms . . . . . . . . . . 7
2.1.3 Crop Disease Prediction by Using Machine Learning . . . . . . 7
2.1.4 An E-farming Web Portal . . . . . . . . . . . . . . . . . . . . 7
2.2 Existing System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.3 Drawbacks of Existing System . . . . . . . . . . . . . . . . . . . . . . 9
2.4 Future work in Existing System in all scenario . . . . . . . . . . . . . 10

3 Requirement Analysis 11
3.1 Requirement Feature of System . . . . . . . . . . . . . . . . . . . . . 11
3.2 Hardware Requirements . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.3 Software Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . 12
3.4 Nonfunctional Requirements . . . . . . . . . . . . . . . . . . . . . . . 13
3.4.1 Performance Requirements . . . . . . . . . . . . . . . . . . . . 13
3.4.2 Safety Requirements . . . . . . . . . . . . . . . . . . . . . . . 13

4 System Architecture 14
4.1 Proposed System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
4.2 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
4.3 Modules . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17

i
CONTENTS CONTENTS

4.3.1 Goverment Scheme Information . . . . . . . . . . . . . . . . . 17

4.3.2 Crop Prediction . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.3.3 Disease Prediction . . . . . . . . . . . . . . . . . . . . . . . . 17
4.3.4 Fertilizer Recommandation . . . . . . . . . . . . . . . . . . . . 17

5 System Design 18
5.1 DFD level 0 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
5.2 DFD level 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
5.3 DFD level 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
5.4 CFD . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
5.5 E-R Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
5.6 UML Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
5.6.1 Use Case Diagram . . . . . . . . . . . . . . . . . . . . . . . . 23
5.6.2 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . 25
5.6.3 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
5.6.4 Sequence Diagram . . . . . . . . . . . . . . . . . . . . . . . . 27
5.6.5 Component Diagram . . . . . . . . . . . . . . . . . . . . . . . 28

6 System implementation 29
6.1 Technical Specification . . . . . . . . . . . . . . . . . . . . . . . . . . 29
6.1.1 Platform . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
6.1.2 Programming Language . . . . . . . . . . . . . . . . . . . . . 31
6.1.3 Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
6.1.4 Development Tools . . . . . . . . . . . . . . . . . . . . . . . . 33
6.1.5 Database . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
6.2 Software Development Life Cycle . . . . . . . . . . . . . . . . . . . . 35
6.3 Project Plan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
6.3.1 Gantt chart . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
6.4 Software Development Life Cycle . . . . . . . . . . . . . . . . . . . . 38
6.4.1 Risk management . . . . . . . . . . . . . . . . . . . . . . . . . 38

7 Software Testing 40
7.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
7.2 Types of Testing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
7.2.1 Manual Testing . . . . . . . . . . . . . . . . . . . . . . . . . . 41
7.2.2 Automated Testing . . . . . . . . . . . . . . . . . . . . . . . . 41
7.2.3 Unit Testing . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
7.2.4 Integration Testing . . . . . . . . . . . . . . . . . . . . . . . . 41
7.2.5 Regression Testing . . . . . . . . . . . . . . . . . . . . . . . . 42
7.2.6 Test cases for Registration . . . . . . . . . . . . . . . . . . . . 44
7.2.7 Test cases for Log In . . . . . . . . . . . . . . . . . . . . . . . 46
7.2.8 Cases For Crop Recommendation . . . . . . . . . . . . . . . . 47
7.2.9 Test Cases for Image Uploading . . . . . . . . . . . . . . . . . 48

ii
CONTENTS CONTENTS

8 Results 49
8.1 Final Snapshots . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49
8.2 Result Discussions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59
8.2.1 Comparison with existing system . . . . . . . . . . . . . . . . 59

9 Advantages and Disadvantages 60

9.1 Advantages . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60
9.2 Disadvantage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61

10 Applications 62

11 Conclusion 64
11.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64
11.2 Future Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65

Appendix 69

iii
List of Figures

4.1 Architecture Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

5.1 DFD 0 Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

5.2 DFD 1 Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
5.3 DFD 2 Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
5.4 CFD Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
5.5 ER Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
5.6 Usecase Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
5.7 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
5.8 Class diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
5.9 Sequence Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
5.10 Component Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . 28

6.1 VS Code programming language . . . . . . . . . . . . . . . . . . . . . 31

6.2 Python software programming language . . . . . . . . . . . . . . . . . 33
6.3 SQLite Database . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
6.4 SDLC Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
6.5 Gantt chart . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

8.1 Homepage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49
8.2 Registration page . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50
8.3 Login page . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
8.4 Dashboard page . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52
8.5 Crop Recommendation page . . . . . . . . . . . . . . . . . . . . . . . 53
8.6 Predicted Crop . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54
8.7 Fertilizer Recommendation page . . . . . . . . . . . . . . . . . . . . . 55
8.8 Crop Disease detection page . . . . . . . . . . . . . . . . . . . . . . . 56
8.9 detected Disease . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57
8.10 Government Yojna page . . . . . . . . . . . . . . . . . . . . . . . . . 58

iv
List of Tables

2.1 Table of related paper refereed . . . . . . . . . . . . . . . . . . . . . . 6

6.1 Project plan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

7.1 Test Case for successful registration . . . . . . . . . . . . . . . . . . . 44

7.2 Test case for blank field . . . . . . . . . . . . . . . . . . . . . . . . . 44
7.3 Test case for invalid phone number . . . . . . . . . . . . . . . . . . . 45
7.4 Test case for incorrect phone number . . . . . . . . . . . . . . . . . . 45
7.5 Test cases for password . . . . . . . . . . . . . . . . . . . . . . . . . . 46
7.6 Test cases for successful login . . . . . . . . . . . . . . . . . . . . . . 46
7.7 Test cases for crop recommendation . . . . . . . . . . . . . . . . . . . 47
7.8 Test cases for successful image upload . . . . . . . . . . . . . . . . . . 48
7.9 Test cases for invalid image format . . . . . . . . . . . . . . . . . . . 48

v
Chapter 1

Introduction

1.1 Problem Definition

The creation of the farmer portal described in the provided information is undeni-
ably relevant in today’s agricultural landscape. With the global population on the
rise and climate change impacting traditional farming practices, technology-driven
solutions are critical to ensuring food security and the livelihoods of farmers. The
portal’s compilation of government schemes information is particularly pertinent, as
it can empower farmers with knowledge of available support programs and subsi-
dies, enabling them to make informed decisions and access vital resources to improve
their agricultural practices. Furthermore, the integration of cutting-edge machine
learning for crop prediction and image-based disease detection directly addresses the
challenges of uncertain weather patterns and crop diseases, which can significantly
impact crop yields.

Furthermore, the proactive approach to data-driven decision-making fostered by

this portal aligns perfectly with the evolving demands of modern agriculture. It po-
sitions farmers as proactive managers of their farms rather than passive recipients
of agricultural support. This shift empowers them to adapt to changing conditions,
make informed choices, and optimize their farming practices.

1
 Crop Growth optimization and Disease Detection

1.2 Objective
• To Enhance Access to Government

• To Empower Informed Decision-Making.

• Apply Disease Detection and Mitigation

• Optimize Nutrient Management

• To Provide Linguistic Inclusivity

• Improve Accessibility for Rural Areas

• TO Enhance User Education and Training

• Facilitate Seamless Government Interaction

• Encourage Sustainable Farming Practices

• To Establish Feedback Mechanisms

• Foster Community Engagement

• Ensure Data Privacy and Security

MCOERC, Nashik, Department of AI & DS Engineering 2

 Crop Growth optimization and Disease Detection

1.3 Project scope

The scope behind embarking on the development of the comprehensive farmer por-
tal is deeply rooted in a profound understanding of the challenges faced by farmers
and a commitment to transforming these challenges into opportunities. Agricul-
ture, as the cornerstone of our societies, not only feeds us but sustains livelihoods
and economies. Yet, it grapples with the uncertainties of climate change, the com-
plexity of government policies, and the ever-present threat of crop diseases. These
challenges can seem insurmountable, but they also present a call to action, an oppor-
tunity to innovate, and a chance to empower those who till the land. At the heart
of this project is a driving desire to bridge the information gap and provide farmers
with the knowledge they need to make informed decisions. The portal’s provision of
government schemes information aims to ensure that no farmer is left behind, that
every farmer has access to the support and resources they are entitled to. The in-
corporation of cutting-edge technology, such as machine learning for crop prediction
and image-based disease detection, is a testament to our belief that technology can
be harnessed to mitigate the impacts of climate change and crop diseases.
It represents a commitment to increasing agricultural productivity while reducing
environmental impact. Moreover, the dedication to linguistic inclusivity through the
Marathi language system reflects an understanding that solutions must be accessi-
ble to all, regardless of linguistic background. In Maharashtra, this feature has the
potential to empower millions of Marathi-speaking farmers who have unique needs
and challenges. This project’s motivation is deeply rooted in the belief that through
innovation, information, and inclusivity, we can usher in a new era of agriculture,
one where farmers have the tools and support they need to thrive, ensuring food
security and prosperity for generations to come.

MCOERC, Nashik, Department of AI & DS Engineering 3

 Crop Growth optimization and Disease Detection

1.4 Hypothesis
The hypothesis for a System to predict how much crops will grow and suggest what
fertilizers to use. Hybrid Machine Learning Algorithms can be described in the fol-
lowing way:

1. Hypothesis for Crop Prediction: Traditional machine learning models (e.g., lin-
ear regression) can accurately predict crop yields based on historical data and
environmental variables. Hybrid machine learning algorithms, which combine
traditional statistical models and deep learning techniques, will yield more ac-
curate crop yield predictions compared to traditional models. The hypothesis
for crop yield prediction aims to determine whether the hybrid approach offers
a statistically significant improvement in predictive accuracy over traditional
machine learning models.

2. Hypothesis for Fertilizer Recommendation: A fertilizer recommendation sys-

tem based on soil nutrient analysis and crop requirements does not significantly
impact crop yield improvement when compared to a non-recommendation
approach. Implementing a fertilizer recommendation system that optimizes
the type and quantity of fertilizers based on data-driven analysis will re-
sult in a statistically significant improvement in crop yields compared to a
non-recommendation approach.The hypothesis for fertilizer recommendation
focuses on evaluating the effectiveness of the recommendation system in im-
proving crop yield outcomes.

To test these hypothesis, a dataset containing historical crop yield data, environ-
mental variables, and fertilizer application records can be used. The hybrid machine
learning algorithm can be compared to traditional machine learning models in terms
of their predictive accuracy, and the impact of the fertilizer recommendation system
on crop yields can be assessed through statistical analysis and comparison of yield
outcomes.

MCOERC, Nashik, Department of AI & DS Engineering 4

 Crop Growth optimization and Disease Detection

1.5 Strategy Plan to solve problem

Solving the problem of manual Crop Yield Prediction and Fertilizer Recommen-
dation with an automated system requires a well-defined strategy plan. Here is a
step-by-step plan to develop and implement an automated solution:

1. Problem Definition and Goal Setting: Clearly define the problem and set spe-
cific goals for automating crop yield prediction and fertilizer recommendation.
Identify the key objectives, such as improving yield, optimizing resource use,
and reducing manual labor.

2. Data Collection and Integration: Gather historical crop yield data, environ-
mental variables, soil nutrient data, and other relevant information. Develop
data integration pipelines to clean, preprocess, and harmonize the data from
multiple sources.

3. Machine Learning Model Development: Employ hybrid machine learning al-

gorithms that combine traditional statistical models with deep learning tech-
niques. Develop and train predictive models to forecast crop yields based on
historical and real-time data.

4. Fertilizer Recommendation System: Implement a recommendation system that

considers soil nutrient analysis, crop requirements, and historical performance.
Use ML models to optimize the type and quantity of fertilizers required for
each crop.

5. User Interface and Accessibility: Design a user-friendly interface accessible to

farmers, agricultural workers, or advisors. Make sure the system works on
different devices like phones and tablets.

6. Integration with Agricultural Equipment: If applicable, integrate the system

with agricultural machinery for automated and precise application of recom-
mended fertilizers.

MCOERC, Nashik, Department of AI & DS Engineering 5

Chapter 2

Literature Survey

2.1 Table of related paper refereed

Table 2.1: Table of related paper refereed

Sr. Paper Name Year of Publisher

No. Publish
1 An E-farming Web Portal 2022 Pallavi Sain-
dane, Swasth
Phasal
2 Transforming Information- 2021 Faudziah Ah-
Based Agricultural Portal mad; Nur
to Knowledge-Based Agri- Haryani Zakaria
cultural Hub
3 Crop Yield Prediction and 2022 3. K P K Devan;
Fertilizer Recommendation B Swetha
System Using Hybrid Ma-
chine Learning Algorithms
4 Crop Disease Prediction by 2023 Anuja Nanda;
Using Machine Learning Sangam Nayak

6
 Crop Growth optimization and Disease Detection

2.1.1 Transforming Information-Based Agricultural Portal

to Knowledge-Based Agricultural Hub
The research is about Agribazaar, a website that gives information about farming.
The Department of Agriculture, part of the Ministry of Agriculture and Agricultural
Industries. Give it a go, Malaysia. Basically, the website has been created to provide
an online platform Business system for people who buy and sell farm products.

2.1.2 Crop Yield Prediction and Fertilizer Recommenda-

tion System Using Hybrid Machine Learning Algo-
rithms
advancements in how we can use computers to help us grow crops. Ways to make
agricultural predictions better. In studying how much crops grow, machines are
used. Learning is a very big topic that many people are studying. Estimating how
much crop will be harvested is really important. Farming Machine learning (ML) is
a way to predict things using computers. Finding connections between the things
you put in and the results you get.

2.1.3 Crop Disease Prediction by Using Machine Learning

There are more people now, so we need to produce more. They grew food to feed
themselves. In the meantime, we have a lot of problems to deal with. Thinking
about what a lot of people need. Many crops are destroyed. This affects how much
food we can grow and can lead to not having enough food. ”We understand” Plants
often get sick. Some of the fac- mean to express concerns or worries about something
that could happen. Farmers use fertilizers and pesticides, and also take care of the
environment and surroundings. Conditions and so on.

2.1.4 An E-farming Web Portal

Farming has been the main job in India for a long time. In Indian tradition, it is
believed that. In the future, we will need 345 million more edible grains. In the next
ten years, the importance of manufacturing in India’s economy has gone down. text
was pretty complicated, could you break it down into simpler terms. Sure The text
was difficult to understand. Can you explain it in simpler words. Many farmers are
very poor and that makes their situation very sad. They need to borrow money to
pay for things, and it’s hard for them to pay it back sometimes. the money borrowed
from a bank or lender. Our website wants to give farmers crop seeds and fertilizers
at low prices.

MCOERC, Nashik, Department of AI & DS Engineering 7

 Crop Growth optimization and Disease Detection

2.2 Existing System

A process that helps predict how much crops will grow and tells you what kind of
fertilizer to use. depends on the knowledge and skills of farm experts, local advi-
sors, and farmers To make good choices about how to take care of crops. In this
approach, historical crop yield data, environmental factors, and soil conditions are
considered alongside expert knowledge to make predictions and recommendations.
Agronomists analyze past yield data and assess the impact of various environmen-
tal variables, such as weather conditions and soil quality, on crop growth. Based on
this analysis, they predict future crop yields, helping farmers plan their planting and
harvesting schedules. Additionally, soil nutrient analysis plays a vital role in deter-
mining fertilizer recommendations. Agronomists and experts analyze soil samples
to identify nutrient deficiencies and pH levels, and they recommend specific types
and quantities of fertilizers to address these deficiencies and optimize crop growth.
While this manual method lacks the automation of machine learning algorithms, it
remains a valuable approach, particularly in areas with limited access to advanced
technology. It requires ongoing collaboration, expert knowledge, and continuous
monitoring to adapt to changing conditions and optimize agricultural outcomes.

MCOERC, Nashik, Department of AI & DS Engineering 8

 Crop Growth optimization and Disease Detection

2.3 Drawbacks of Existing System

The manual method of Crop Yield Prediction and Fertilizer Recommendation Sys-
tem, while valuable in many agricultural settings, has some notable drawbacks. One
of the primary limitations is its reliance on human expertise and historical data anal-
ysis.
Manual methods are labor-intensive and can be challenging to scale to larger agri-
cultural operations or regions. The need for expert agronomists and advisors for
every farm can be impractical in areas with a high number of farms. The accu-
racy of predictions and recommendations heavily depends on the expertise of the
agronomists and advisors. Different experts may provide varying recommendations,
leading to inconsistencies and potential errors. Manual data collection, analysis,
and decision-making can be time-consuming. Farmers may experience delays in re-
ceiving recommendations, which can impact planting and harvest schedules. The
availability of historical data and soil nutrient analysis may be limited, especially
in remote or resource-constrained regions. Incomplete or outdated data can hinder
the accuracy of predictions and recommendations. Manual methods often require
frequent site visits by agronomists and advisors, which can be resource-intensive, es-
pecially in terms of travel costs and time. Manual systems may struggle to provide
real-time adjustments based on rapidly changing weather conditions or unforeseen
events, such as pest outbreaks. The expertise and knowledge of agronomists can
vary, leading to differences in the quality of recommendations and predictions. In-
experienced or poorly trained advisors may provide sub-optimal guidance.

MCOERC, Nashik, Department of AI & DS Engineering 9

 Crop Growth optimization and Disease Detection

2.4 Future work in Existing System in all scenario

In the future, there is significant potential to enhance and refine manual meth-
ods of Crop Yield Prediction and Fertilizer Recommendation Systems. Combining
manual expertise with digital tools, such as mobile applications and sensor-based
data collection, can streamline data gathering and analysis. This integration can
provide real-time updates and enable more accurate predictions and recommenda-
tions. Efforts should be directed towards improving data accessibility in remote and
resource-constrained areas. This includes initiatives to gather and digitize historical
data, expand soil testing services, and establish data-sharing networks among farm-
ers and advisors. Training programs for farmers and advisors can help them learn
more and do things the same way. Sharing information and ideas on platforms and
networks helps people learn from each other’s experiences and find new ways to do
things better.

MCOERC, Nashik, Department of AI & DS Engineering 10

Chapter 3

Requirement Analysis

3.1 Requirement Feature of System

The requirements and features of a Crop Yield Prediction and Fertilizer Recommen-
dation System can be divided into various categories to ensure its effectiveness and
usability. Here’s an overview of the essential requirements and features:

• Implement machine learning algorithms for crop yield prediction, considering

historical data and environmental factors. Ensure accurate and reliable yield
predictions with a defined margin of error. Allow for the customization of
prediction models for different crop types and regions.

• Allow users to create profiles and input their farm-specific data for personalized
recommendations.

• Offer training materials and resources to educate farmers and advisors on using
the system effectively.

• Maintain a library of educational content on crop management and sustainable

agriculture practices.

• The foundation of a comprehensive Crop Yield Prediction and Fertilizer Rec-

ommendation System that benefits farmers, agricultural advisors, and the agri-
culture industry as a whole.

3.2 Hardware Requirements

• AMD/Intel i3 Processor or above Processor

• 3GB RAM for application development

11
 Crop Growth optimization and Disease Detection

• 250 GB or above Hard Disk

3.3 Software Requirements

• Windows 7 or above

• Vscode, Xamp

• Python

MCOERC, Nashik, Department of AI & DS Engineering 12

 Crop Growth optimization and Disease Detection

3.4 Nonfunctional Requirements

Nonfunctional requirements in the context of image steganography are the attributes
that describe how the system should perform, rather than specific features or func-
tionalities. These nonfunctional requirements help define the overall quality, perfor-
mance, and behavior of the steganography system.

3.4.1 Performance Requirements

The system should respond quickly when users interact with it, with very little
waiting time. When you look at predictions and suggestions. It needs to be able
to deal with more and more. Amount of people using and amount of information
without much change in speed.

3.4.2 Safety Requirements

The system must employ robust data security measures to protect sensitive user
data, including farm-specific information and soil analysis results. Data should be
encrypted during transmission and storage to prevent unauthorized access or data
breaches.: The system must comply with data privacy regulations to safeguard the
privacy and confidentiality of user data.This means making sure that someone gives
permission after they understand all the information. We collect data and make
sure it’s only used for what it’s supposed to be used for. The system should support
farming in a way that takes care of the environment and can continue into the future.
This includes recommending eco-friendly fertilizers, minimizing excessive fertilizer
use to prevent soil and water pollution, and promoting organic farming practices
where appropriate.

MCOERC, Nashik, Department of AI & DS Engineering 13

Chapter 4

System Architecture

4.1 Proposed System

The portal’s Government schemes information section serves as a repository of vital
resources, offering farmers access to essential information about various agricultural
policies, subsidies, and support programs.
Leveraging machine learning algorithms, the platform provides best crop predictions
by analyzing historical data, weather patterns, and soil conditions. This predictive
capability empowers farmers to optimize their crop selection, planting, and harvest-
ing strategies, ultimately increasing productivity and profitability.
The image-based disease prediction feature employs advanced computer vision tech-
niques to identify and diagnose crop diseases from images uploaded by farmers. This
rapid and accurate disease detection aids in early intervention and mitigation, re-
ducing crop losses and ensuring food security.
Additionally, the fertilizer recommendation system utilizes data-driven insights to
suggest personalized fertilizer blends based on soil analysis and crop type, promoting
efficient nutrient management practices.
To further bridge the digital divide, the inclusion of a Marathi language system
ensures accessibility and usability for local farmers.

4.2 System Architecture

The new system is a innovative approach Crop Growth Optimization and Disease
Detection is a multifaceted agricultural system that combines cutting-edge technol-
ogy and data-driven approaches to enhance crop production and mitigate disease
risks. At its core, this system relies on a network of sensors and data collection
devices installed in the field to continuously monitor various environmental param-
eters such as soil moisture, temperature, humidity, and light conditions. These data

14
 Crop Growth optimization and Disease Detection

points are then transmitted to a centralized platform where advanced algorithms

and machine learning models analyze the information in real-time. By leveraging
this data, the system can provide precise recommendations for crop management,
including optimal irrigation schedules, fertilization plans, and pest control measures.
Simultaneously, the system employs image recognition technology to detect signs of
disease, pests, or nutrient deficiencies in plants. This enables early detection and
targeted intervention, minimizing crop damage and loss. By seamlessly integrating
data analytics, sensor technology, and artificial intelligence, Crop Growth Optimiza-
tion and Disease Detection offers a comprehensive solution to optimize agricultural
practices and ensure healthier, more productive crops while reducing resource waste.

MCOERC, Nashik, Department of AI & DS Engineering 15

 Crop Growth optimization and Disease Detection

Figure 4.1: Architecture Diagram

MCOERC, Nashik, Department of AI & DS Engineering 16

 Crop Growth optimization and Disease Detection

4.3 Modules

4.3.1 Goverment Scheme Information

Government scheme information refers to the various agricultural policies and pro-
grams implemented by the government to support farmers and improve agricultural
practices. These schemes can provide valuable data and resources that can be in-
tegrated into the prediction and detection system. By incorporating government
scheme information, the system can have a more comprehensive understanding of
the agricultural landscape and make more accurate predictions and detections.

4.3.2 Crop Prediction

Crop prediction refers to the process of estimating or forecasting the potential yield
of crops in a given area. This is done by analyzing various factors such as historical
data, weather patterns, soil conditions, and other relevant parameters. By using
machine learning algorithms and statistical models, the system can make predic-
tions about the expected crop yield, which can help farmers plan their agricultural
activities, make informed decisions, and optimize their crop production.

4.3.3 Disease Prediction

Disease detection means finding and diagnosing diseases that can harm plants. This
is done with different methods like changing pictures, teaching machines, and looking
at data. The system looks at pictures or information from the plants to find any
signs of sickness, like changed colors, spots, or strange shapes. By finding diseases
early, farmers can quickly stop them from spreading and reduce the harm to their
crops.

4.3.4 Fertilizer Recommandation

Fertilizer recommendation refers to providing guidance on the appropriate type and
amount of fertilizer to be applied to crops based on their specific needs. This rec-
ommendation is typically made by analyzing various factors such as soil nutrient
levels, crop type, growth stage, and environmental conditions. By considering these
factors, the system can suggest the optimal fertilizer composition and application
rate to maximize crop health and yield.

MCOERC, Nashik, Department of AI & DS Engineering 17

Chapter 5

System Design

5.1 DFD level 0

A data flow diagram (DFD) is a graphical or visual representation using a stan-
dardized set of symbols and notations to describe a business’s operations through
data movement.
DFD 0, also called context diagram of the result management system. As the
bubbles are decomposed into less and less abstract bubbles, the corresponding data
flow may also be needed to be decomposed.

Figure 5.1: DFD 0 Diagram

18
 Crop Growth optimization and Disease Detection

5.2 DFD level 1

DFD 1, a context diagram is divided into many bubbles or processes. In this At this
level, we focus on the main goals of the system and explain the important details.
Changing the first level data flow diagram into smaller processes.

Figure 5.2: DFD 1 Diagram

MCOERC, Nashik, Department of AI & DS Engineering 19

 Crop Growth optimization and Disease Detection

5.3 DFD level 2

DFD 2 goes further into breaking down the parts of DFD 1. It can be used to show
something. Write down or save the important information about how the system
works.

Figure 5.3: DFD 2 Diagram

MCOERC, Nashik, Department of AI & DS Engineering 20

 Crop Growth optimization and Disease Detection

5.4 CFD
A Cumulative Flow Diagram (CFD) is a chart that shows the progress of work
items over time. It helps to see how tasks are moving forward or getting stuck.
Move through various steps of a process as time goes by.
move through different steps of a process as time goes by. CFDs are often used
in Agile and Kanban methodologies to provide insights into work item flow, bottle-
necks, and overall process efficiency. Cumulative Flow Diagrams provide a valuable
visual tool for understanding and managing workflow in various domains, such as
software development, manufacturing, and project management.

Figure 5.4: CFD Diagram

MCOERC, Nashik, Department of AI & DS Engineering 21

 Crop Growth optimization and Disease Detection

5.5 E-R Diagram

An ERD, or entity relationship diagram, shows how things are connected in a system.
It’s also called an entity relationship model. A diagram that shows how people,
things, and places are connected. Ideas or things in a computer system. Depending
on how big the change is, it can be dangerous to directly change the way a database
is set up. A database management system. In order to prevent causing damage to
the information in a working database, it is essential to carefully think through and
organize all the steps. Examine the changes closely. ERD is a helpful tool. Using
ER diagrams to see In coming up with ideas for how to organize a database, you get
to find and fix any errors or problems in the design. To fix mistakes before making
changes in the database.

Figure 5.5: ER Diagram

MCOERC, Nashik, Department of AI & DS Engineering 22

 Crop Growth optimization and Disease Detection

5.6 UML Diagram

5.6.1 Use Case Diagram

The use case diagram is made up of four modeling parts.

• Actors: Actors are a kind of users, and users are people who use the system.
In this situation, students, teachers, and developers are the people who use
the framework and application.

• Use cases:A use case tells us how a system behaves. Each task is named with
a phrase that shows what the system is supposed to do. The name can be
inside or outside the oval shape.

• Associations: An association is a connection between a person or thing and

a specific action or purpose. The connection between an actor and a use case
is shown by a line.

• The include relationship: It’s like when objects talk to each other. One sit-
uation needs a certain action that is completely described in another situation.
.

MCOERC, Nashik, Department of AI & DS Engineering 23

 Crop Growth optimization and Disease Detection

Figure 5.6: Usecase Diagram

MCOERC, Nashik, Department of AI & DS Engineering 24

 Crop Growth optimization and Disease Detection

5.6.2 Activity Diagram

Use cases describe the tasks or actions that your system needs to perform. ”Activity
diagrams let you define and show the steps and flow of an activity or process. ”
Please explain how your system will achieve its goals. Activity diagrams illustrate
the main steps or actions in a process. Linked together to show how something
happens in your system. An activity diagram is a visual representation of the flow
of activities in a process or system. It’s like a picture that shows how one activity
leads to the next. Not like a train. An activity diagram is like a flowchart, but it
also shows when things are happening at the same time and when there are different
paths to follow. Activity diagrams show how a system moves and changes over time.

Figure 5.7: Activity Diagram

MCOERC, Nashik, Department of AI & DS Engineering 25

 Crop Growth optimization and Disease Detection

5.6.3 Class Diagram

The class diagram explains the basic elements of a system that uses objects. Class
- a group or category of things or people with similar characteristics or qualities.
A picture shows a still picture of the model, explaining what it looks like. The
text talks about the qualities and actions it has instead of explaining how to do
it. Performing tasks or activities. Class diagrams are very helpful for showing how
things are connected to each other. Classes and interfaces are different types of
blueprints for creating objects in programming. Classes define the structure and
behavior of an object, while interfaces define the contract that a class must follow.
Generalizations, aggregations, and connections are important and useful. Able to
show how things work and connect with each other.

Figure 5.8: Class diagram

The figure shows how classes are related to each other. The matchstick show
whether or not ObjectExplorer is dependent on ThumbNail. Aggregation shows
that the ObjectExplorer class used ThumbNail, but it’s not clear if ObjectExplorer
depends on ThumbNail. do not always have it in there. The powerful, combined
groups by the ”Other connectors show who owns or contains the source classes. ”
Rewrite this text: target. In a video player class, information like settings will be
stored in a table. Tents, which are shelters made of fabric stretched over a frame,
are used for camping and outdoor activities.

MCOERC, Nashik, Department of AI & DS Engineering 26

 Crop Growth optimization and Disease Detection

5.6.4 Sequence Diagram

The sequence diagram is mostly used to display how objects interact with each
other. in the order that those interactions happen one after the other. ”Developers
usually think in order. ” Diagrams were only for them. However, the people who
work for a company. You might find sequence diagrams helpful for showing how
the business works right now. Sequence diagrams display how different business
items communicate. ”Talk to each other and do things together. ” arranged in a
particular order. Objects can send and get messages from each other. The sequence
diagram is used to show how different parts of a system interact with each other in
a specific order. The purpose is to explain the order of events between the different
parts of the system that are involved in a specific task. Interaction is when two or
more things or people work together or affect each other.

Figure 5.9: Sequence Diagram

MCOERC, Nashik, Department of AI & DS Engineering 27

 Crop Growth optimization and Disease Detection

5.6.5 Component Diagram

A component diagram shows how different parts of a system are organized
and how they depend on each other. Parts of something. A component diagram
shows how things are put together in a system. Explanation of a system’s view. This
means creating a model of the things that are on a node. Things like programs, data,
lists, and files.
A component diagram is a group of points and lines. Component diagrams
show the organization and dependencies of the software components in a system.
usually have

• Components

• Interfaces

• Dependency, generalization, association and realization relationships.

Figure 5.10: Component Diagram

MCOERC, Nashik, Department of AI & DS Engineering 28

Chapter 6

System implementation

6.1 Technical Specification

1. User Interface with the application.

2. Database management.

3. Dataset creation.

4. Data values Processing.

5. Display result.

6. The information is shown on a website using a flask and works on a powerful

computer. teaching computer programs and technologies in a way that is easy
for people to use. Rewrite this text for people who use the product.

7. The training data we obtained will help us predict market prices and demand.
So, the plan helps farmers fix their problems and make more money.

8. Predicting how much crops will grow with the right information, predicting
how much fertilizer to use and predicting how much rain will fall.

9. This project shows how we use computer programs and different methods to
help farmers with their crops.

10. This app can help to predict things like spotting diseases in leaves and fruits.
and other ideas that can be used on this platform to make the project bigger.

29
 Crop Growth optimization and Disease Detection

6.1.1 Platform
A web app is a type of software that you can use on the internet. It can do different
things like help you write documents or play games. A program that you can use
on a web browser. It is made to do certain things specifically. The internet allows
people to do things and communicate with each other using a website. A browser
can be used on different types of gadgets like computers, smartphones, and tablets.
A web application Applications are often used to provide services and features to
users through the internet. The World Wide Web is a system of information that
is connected by the internet. It allows people to access and share information from
all over the world.
Here are some key characteristics and components of web applications:

1. Client-Server Architecture: Web applications usually work by having a client,

like a computer or phone, talk to a server, which is a big computer that holds
all the information and responds to requests from the client.

2. Web applications work by a device, like a computer or phone, talking to a big

computer called a server. The server holds all the information and responds
to requests from the device. The client is the person using the web browser,
and the server stores the program and information.

3. Interactivity: Web applications can be highly interactive, allowing users to

perform tasks like submitting forms, searching for information, making online
purchases, and more. JavaScript is a crucial technology for adding interactivity
to web applications.

4. Data Storage and Databases: Most web applications require data storage.
Databases, both relational (e.g., MySQL, PostgreSQL) and NoSQL (e.g., Mon-
goDB), are used to store and manage data.

5. Cross-Platform Access: Web applications are accessible on various devices and

operating systems as long as there is a compatible web browser. This makes
them platform-independent.

6. Updates and Maintenance: Web applications can be updated and maintained

centrally on the server, which is a significant advantage over traditional desktop
applications that may require manual updates on each user’s machine.

7. Cloud Hosting: Many web applications are hosted in the cloud, which offers
scalability, reliability, and accessibility from anywhere with an internet con-
nection.

Web applications are used for a wide range of purposes, from social networking
platforms and e-commerce websites to productivity tools and content management
systems. They have become an integral part of modern life, enabling users to perform
various tasks and access information over the internet.

MCOERC, Nashik, Department of AI & DS Engineering 30

 Crop Growth optimization and Disease Detection

6.1.2 Programming Language

Visual Studio Code is a code editor made by Microsoft that is free to use and can
be modified by anyone. It is important to rewrite the text in simple words. is a
favorite for developers because it can do many things and has a lot of features.

Figure 6.1: VS Code programming language

Here are some key aspects of Visual Studio Code (VS Code):
1. VS Code available on different operating systems such as Windows, macOS,
and Linux. This means you can use it on various types of computers. it can
be used by developers on different types of devices.
2. Lightweight: It’s a lightweight code editor that’s faster and uses fewer sys-
tem resources compared to full-fledged integrated development environments
(IDEs).
3. Simple: VS Code can be used for many different programming languages and
has a lot of extra features you can add on. You can add extra features to the
editor to make it work better for you.
4. Intelligent Code Editing: It has tools like highlighting important parts of the
code, suggesting code improvements, and finding mistakes. The tool provides
checking, fixing, and cleaning for different coding languages.
5. Debugging: It provides integrated debugging tools for various languages and
platforms.
6. Customizable Themes and Styles: VS Code allows you to choose from a variety
of themes and customize the editor’s appearance to your liking.
VS Code has become very popular among many different groups of people who
create and build things. changing from creating websites to working with data and
can change it to work with different coding methods .

MCOERC, Nashik, Department of AI & DS Engineering 31

 Crop Growth optimization and Disease Detection

6.1.3 Framework
Django is a powerful web development tool that helps you create websites quickly
using Python. Simple and practical design. It uses the Model-View-Controller
(MVC) system for organizing. The pattern is made to help developers create web
apps more easily. fast and effectively.
Django has many features and tools, such as:

1. A system that helps manage databases by mapping objects to tables.

2. A pre-installed control panel for organizing the app’s information.

3. A URL routing system.

4. A template system for creating dynamic web pages.

5. Authentication and authorization mechanisms.

6. Security features help to keep web applications safe from common vulnerabil-
ities.

7. Internationalization and localization support.

8. Extensibility through reusable apps and plugins.

9. Community helps and lots of other packages made by different companies.

Django is commonly used for developing all sorts of web applications, from small
personal projects to large, complex websites. It is known for its robustness, scala-
bility, and the ”batteries-included” philosophy, which means that it comes with a
lot of built-in functionality to help you get started quickly.

MCOERC, Nashik, Department of AI & DS Engineering 32

 Crop Growth optimization and Disease Detection

6.1.4 Development Tools

Figure 6.2: Python software programming language

Python is a type of computer language that can be used in different ways for
programming. Object-oriented programming is a type of computer programming
where we create objects that have their own data and behavior. We can use these
objects to build more complex programs. Ming and structured programming are
well supported, and they have many features. Features help with functional pro-
gramming and aspect-oriented programming (including). Metaprogramming is a
type of programming that uses metaobjects. Python is a type of computer language
that is easy to use and can do many things. It is not too hard to understand for
beginners. Dynamic semantics is a study of how words and sentences are used in
real-life conversations and situations. It’s made with advanced data structures and
can change while running. ”Using typing and dynamic binding will make your Rapid
Application Development process even faster and more flexible. Try it out to see
the amazing results. ” This language can be used for software development, and
also for connecting different programs. Put the parts together. Python is easy to
learn and its syntax is simple to read. This lowers the amount of money needed to
maintain the program. Python can use modules. Programs are broken down into
smaller parts and can be used again in different programs.

MCOERC, Nashik, Department of AI & DS Engineering 33

 Crop Growth optimization and Disease Detection

6.1.5 Database

Figure 6.3: SQLite Database

SQLite is a small database system that doesn’t need a server to work. It manages
data in a structured way. It is important to use easy words. Simple words: is a free
library that works in your computer’s memory without needing any special setup or
configuration. any setup or arrangement. it’s very convenient because it’s smaller
than 500 kilobytes. much smaller than other database systems. SQLite has the
following characteristics:

• SQLite is a tool that makes software for things like TVs and phones. phones,
cameras, and other devices.

• It can handle not too many website visitors at once.

• SQLite can make files smaller and contain less information about them.

• SQLite is used as a place to store and work with data in an app.

• SQLite is a free software that anyone can use. You don’t need a license to
use the software once you install it. SQLite doesn’t need a separate server to
work.

• SQLite lets you work on more than one database at the same time, which
makes it flexible.

MCOERC, Nashik, Department of AI & DS Engineering 34

 Crop Growth optimization and Disease Detection

6.2 Software Development Life Cycle

Figure 6.4: SDLC Model

1. Requirement Analysis and Definition:

At this point, we figure out the system’s characteristics, limitations, and goals.
by talking to people who use the system. All of this will be explained in detail.
The requirements and duties of a system. Here’s how to do it: gather the
information. Meet all the requirements and then study and figure out what
needs to be done. The program needs to meet certain requirements. This
stage has to be completed entirely so that we can continue. create a precise
plan .
2. System and Software Design:
In the System and Software Design Phase, a system architecture will be formed
based on established requirements. in addition, identification and depiction of
the basic abstraction of the software system and its relationships are carried
out. The design is done after the complete requirements are collected in full.
3. Implementation and Unit Testing:
During the System and Software Design Phase, a plan for how the system will
be organized and built will be created. according to the rules that are already
set. Moreover, finding and showing. The main idea of the software system and
how it is connected to other things is shown. ”Get out” The design is finished
once all the requirements are gathered.

4. Integration and System Testing:

During Integration and System Testing, each part of the program will be

MCOERC, Nashik, Department of AI & DS Engineering 35

 Crop Growth optimization and Disease Detection

tested. We made sure that all the parts work together by testing the entire
system. The system meets the needs that already exist.

5. Operation and Maintenance:

During the Operation and Maintenance stage, the system is set up and started.
”Try to reword this text using easier language. ” It also fixes mistakes that
weren’t caught during production. In this situation The development process
also includes adding new features to the system. characteristics and opera-
tions.

MCOERC, Nashik, Department of AI & DS Engineering 36

 Crop Growth optimization and Disease Detection

6.3 Project Plan

Task Title Start Date End Date Group Members

Topic Finalization 18/08/2023 20/08/2023 Team
Requirement specification 22/08/2023 31/08/2023 Team
Technology Familiarization 01/09/2023 08/09/2023 Team
System Set up 09/09/2023 22/09/2023 Team
Concept Review Study 23/09/2023 03/10/2023 Team
Study of technologies used in the project 04/10/2023 17/10/2023 Team
Addition of extra module 18/10/2023 30/10/2023 Team
Design of user interface 31/10/2023 20/11/2023 Team
Moules Implementation 15/12/2023 25/01/2024 Team
Creation of database files and rules 27/01/2024 28/02/2024 Team
Designing the Architectural layout 01/03/2024 08/03/2024 Team
Testing 09/03/2024 14/03/2024 Team
Documentation Preparation 15/03/2024 24/04/2024 Team
Maintenance 25/04/2024 28/04/2024 Team

Table 6.1: Project plan

6.3.1 Gantt chart

Figure 6.5: Gantt chart

MCOERC, Nashik, Department of AI & DS Engineering 37

 Crop Growth optimization and Disease Detection

6.4 Software Development Life Cycle

The system will be developed using the following software development life cycle
(SDLC):
1. Gathering information: We will collect the needs of the system from the people
involved.
2. System design: The system will be created using the information gathered in
Step 1.
3. Putting the system into place will be done according to the design made in
Step 2.
4. Testing: The system will be checked to make sure it does what it’s supposed
to and doesn’t have any problems.
5. Deployment: The system will be put into use in a real working environment.

6.4.1 Risk management

Risk management in the context of Crop Growth Optimization and Disease Detec-
tion is essential to ensure the system’s effectiveness, sustainability, and the well-
being of the agricultural operations it serves. Here are some key considerations for
managing risks in this domain:
• Data Security and Privacy: The system collects and stores sensitive data about
crop health and environmental conditions. Protecting this data from breaches
and unauthorized access is critical. Implement robust encryption, access con-
trols, and data backup procedures.
• Data Accuracy and Reliability: Inaccurate or unreliable data can lead to incor-
rect recommendations, impacting crop health and yield. Regularly calibrate
and maintain sensors, and implement data validation and quality control mea-
sures to ensure data accuracy.
• Technical Failures: Hardware and software failures can disrupt the system’s
operation. Implement redundancy and failover mechanisms to minimize down-
time. Regular maintenance and system health checks are essential.
• Model Inaccuracy: The algorithms and machine learning models used for anal-
ysis and recommendations may not always be accurate. Continuously validate
and improve these models to reduce the risk of incorrect guidance.
• Pesticide Resistance and Environmental Impact: Over-reliance on pesticides
can lead to resistance in pests and harm the environment. Implement inte-
grated pest management (IPM) strategies to reduce pesticide use and mitigate
environmental risks.

MCOERC, Nashik, Department of AI & DS Engineering 38

 Crop Growth optimization and Disease Detection

• Following rules and regulations: Make sure to follow the rules for farming set
by the local and national government. Not doing it can cause problems with
the law and money. Stay informed about changing farming laws.

• Cybersecurity: The system is vulnerable to cyberattacks that can disrupt op-

erations or compromise data integrity. Employ strong cybersecurity measures,
conduct regular security audits, and keep software and firmware up to date.

• Market Volatility: Agricultural markets can be unpredictable, impacting the

economic viability of farming. Diversify crops and have contingency plans for
market fluctuations.

MCOERC, Nashik, Department of AI & DS Engineering 39

Chapter 7

Software Testing

7.1 Introduction
Software testing is when we check to see if a program or app works well. Check-
ing if a program or system does what it’s supposed to do. It is greater than Simply
using a program to find mistakes. Every task is different every time. various mea-
sures Not all situations are the same, so one rule may not work for everything.
text needs to be simplified. is a special and important area with very different
issues. Essential for Software quality is very good and used by a lot of programs
and testers. Testing software coding. Software is still considered an art because we
don’t fully understand how it works. The problem The problem comes from the
software being complicated. Software testing is done to make sure the quality of the
software. Assurance, verification, and validation mean checking to make sure that
something works properly. Reliability estimation is figuring out how likely some-
thing is to work well. Software testing is a process to check if computer programs
work correctly. Balancing how much money, time and quality are spent. This chap-
ter explains important testing strategies used to test the system. The text is talking
about experiments and trials.

7.2 Types of Testing

The plan for testing the system is as follows,
1. Manual Testing
2. Automated Testing
3. Unit Testing
4. Integration Testing
5. Regression Testing

40
 Crop Growth optimization and Disease Detection

7.2.1 Manual Testing

There are two types of software testing: manual and automated testing. We are
doing work by hand. We are doing a test to check our system without using any
automated tool or script. Simply put, the text is extremely difficult to understand.
This type of tester acts like a regular person using the software and checks to find
any problems. Unusual actions or problem in a program. In manual testing, there
are different steps to go through, like unit testing. Trying out, putting together,
checking how things work as a whole, and seeing if users like it or not. Testers use A
plan to test the software, including the specific tests that will be done to make sure it
is complete. The process of testing. Manual testing also involves exploratory testing
where testers explore the software without using automated tools. A program that
finds mistakes.

7.2.2 Automated Testing

”Automation testing, also called Test Automation, is when the tester writes a
program to test the software instead of doing it manually. ” Scripts are written
programs that are used to check and test other software. This process is about
making things work automatically. a process done by hand. Automation testing is
when computer programs are used to re-do the same test situations. Done by hand,
fast and many times.

7.2.3 Unit Testing

In unit testing, we test each part of the software one by one. This can be the
different elements or sections of the software. Each part of the software is checked on
its own without the need for other parts to be involved in the testing. Rewrite this
text in simple words: the system. In unit testing, each small part of the software is
tested to make sure it works. purpose of unit testing is to check and make sure that
each small part of the code works correctly. The software system is checked to see
if it works well and how well it performs. Then it is compared with something else.
Software specification refers to a detailed description of what a software application
is supposed to do and the features it should have. The important control routes are
checked and confirmed to find mistakes. The edge of the module and the design of
the component at the same level.

7.2.4 Integration Testing

Integration testing is a type of testing that is used to check how different parts
of the software work together. It helps to make sure that the software architecture
is built properly. by discovering the mistakes related to connecting different things

MCOERC, Nashik, Department of AI & DS Engineering 41

 Crop Growth optimization and Disease Detection

together. After the unit testing is done and everything works well, the different parts
of the software will be put together. Put together to create the complete software
system as it is described. Explain what high level design means. Understanding
Facial Expressions Using a Computer Program Integration testing is a good way to
check that the software is put together correctly. checking the order in which the
software system runs when conducting tests. Find mistakes related to connecting
different things together.

7.2.5 Regression Testing

Whenever the software is changed during development, to double check and
make sure the changes they make to the code are correct. The new software is just
as good as the old one. on checking if the changes work properly. on how well
the software works and when it might not work as expected. be influenced by the
changes. Test Cases: A way to test if the thing works or not. Test cases are a group
of steps or rules that show how to check if a software system or app is working right.
They are made to check different parts of the software to make sure it works as it
should. Test cases give certain inputs, what we expect to get as outputs, and the
steps to follow when we test something. They list the situations to test, including
common and unusual cases, and explain what to do and what results to expect. The
main goal of test cases is to make sure that the software works as it should and does
what it’s supposed to do in different situations. They find problems in the software
and let us know how good and reliable it is.

1. A well-designed test case typically includes the following elements:

2. Test Case ID: A unique identifier or number assigned to the test case for easy
reference and tracking.
3. Test Case Description: A brief description of the objective or purpose of the test
case.
4. Test Steps: A series of detailed steps to follow during the test execution, including
the input data or actions to be performed.
5. Expected Results: The expected outcome or behavior of the software system when
the test steps are executed correctly.
6. Actual Results: The actual outcome observed during the test execution, which is
compared against the expected results.
7. Pass/Fail Criteria: Criteria or conditions to determine whether the test case has
passed or failed.

MCOERC, Nashik, Department of AI & DS Engineering 42

 Crop Growth optimization and Disease Detection

• It helps in assessing the software’s compliance with the desired functionality. Test
cases can be designed and documented using various formats, such as spreadsheets,
test management tools, or specialized testing frameworks. They should be com-
prehensive, covering different aspects and scenarios of the software, and should be
traceable back to the specific requirements or user stories.
• Effective test case design involves considering both positive and negative scenarios,
bound- conditions, error handling, and performance considerations. It is important
to create test cases that are clear, concise, and unambiguous, allowing testers to
execute them accurately and consistently.
• By executing well-designed test cases, software testers can systematically validate
the software’s functionality, uncover defects or inconsistencies, and provide valuable
feedback to improve its quality. Test cases serve as a roadmap for testing activities
and play a crucial role in ensuring the reliability and effectiveness of the software
system.

MCOERC, Nashik, Department of AI & DS Engineering 43

 Crop Growth optimization and Disease Detection

7.2.6 Test cases for Registration

No Behaviour Description Property

1 Unique Test case ID TC001
2 Test Case Name Successful Registration
3 Prerequisites Constant Internet Connection
4 Test Case Description Enter Data in the field
First Name, Last Name,
5 Input
Phone number, Password
6 Expected Result User should get registered to the system
7 Actual Result Registered Successfully!
8 Pass/Fail Pass

Table 7.1: Test Case for successful registration

No Behaviour Description Property

1 Unique Test case ID TC002
2 Test Case Name Blank required fields
3 Prerequisites Constant Internet Connection
4 Test Case Description Do not enter any data in the field
5 Input Blank Field
6 Expected Result Shows error symbol on the right side of the field.
7 Actual Result Required
8 Pass/Fail Pass

Table 7.2: Test case for blank field

MCOERC, Nashik, Department of AI & DS Engineering 44

 Crop Growth optimization and Disease Detection

No Behaviour Description Property

1 Unique Test case ID TC003
2 Test Case Name Phone Number is not in the correct format
3 Prerequisites Constant Internet Connection
4 Test Case Description Enter invalid phone number
5 Input Invalid Phone Number
6 Expected Result Shows error symbol on the right side of the field.
7 Actual Result Invalid Phone Number
8 Pass/Fail Pass

Table 7.3: Test case for invalid phone number

No Behaviour Description Property

1 Unique Test case ID TC004
2 Test Case Name Input the phone no with more than 10 numbers
3 Prerequisites Constant Internet Connection
4 Test Case Description Enter invalid phone no.
5 Input phone no with more than 10 numbers
6 Expected Result Error message” Phone no exceeds the limit”
7 Actual Result Phone no exceeds the limit
8 Pass/Fail Pass

Table 7.4: Test case for incorrect phone number

MCOERC, Nashik, Department of AI & DS Engineering 45

 Crop Growth optimization and Disease Detection

7.2.7 Test cases for Log In

No Behavior Description Property

1 Unique Test case ID TC005
2 Test Case Name Blank Contact and password fields
3 Prerequisites Constant Internet Connection
4 Test Case Description Do not enter any information in the field
5 Input Blank field
6 Expected Result Shows error symbol on the right side of the field
7 Actual Result Required
8 Pass/Fail Pass

Table 7.5: Test cases for password

No Behavior Description Property

1 Unique Test case ID TC006
2 Test Case Name Valid Contact and password combination
3 Prerequisites Constant Internet Connection
4 Test Case Description Enter valid contact and password
5 Input Valid Contact and password combination
6 Expected Result Login is successfully
7 Actual Result Redirects to the Dashboard
8 Pass/Fail Pass

Table 7.6: Test cases for successful login

MCOERC, Nashik, Department of AI & DS Engineering 46

 Crop Growth optimization and Disease Detection

7.2.8 Cases For Crop Recommendation

No Behavior Description Property

1 Unique Test case ID TC009
2 Test Case Name Enter all required fields from soil report
3 Prerequisites Constant Internet Connection
4 Test Case Description Enter soil report details
5 Input Incomplete details
6 Expected Result Error Message “Enter complete details”
7 Actual Result Enter required details
8 Pass/Fail Pass

Table 7.7: Test cases for crop recommendation

MCOERC, Nashik, Department of AI & DS Engineering 47

 Crop Growth optimization and Disease Detection

7.2.9 Test Cases for Image Uploading

No Behavior Description Property

1 Unique Test case ID TC007
2 Test Case Name Successful image upload
3 Prerequisites Constant Internet Connection
4 Test Case Description Upload the relevant image
5 Input Relevant Pomegranate Disease image
6 Expected Result Image will get successfully uploaded
7 Actual Result Image is successfully uploaded
8 Pass/Fail Pass

Table 7.8: Test cases for successful image upload

No Behavior Description Property

1 Unique Test case ID TC008
2 Test Case Name Invalid image format
3 Prerequisites Constant Internet Connection
4 Test Case Description Upload Image with invalid format
5 Input Image with invalid format
6 Expected Result Image will not get uploaded
7 Actual Result Image will not get uploaded
8 Pass/Fail Pass

Table 7.9: Test cases for invalid image format

MCOERC, Nashik, Department of AI & DS Engineering 48

Chapter 8

Results

8.1 Final Snapshots

Figure 8.1: Homepage

Description:
This is the first activity of the project from here users can log in or register them-
selves.

49
 Crop Growth optimization and Disease Detection

Figure 8.2: Registration page

Description:
If the user clicks on the registration tab then the registration form will appear for
the registering user has to enter a credential.

MCOERC, Nashik, Department of AI & DS Engineering 50

 Crop Growth optimization and Disease Detection

Figure 8.3: Login page

Description:
If the user clicks on the Login tab then they just have to log in by using their
username and password.

MCOERC, Nashik, Department of AI & DS Engineering 51

 Crop Growth optimization and Disease Detection

Figure 8.4: Dashboard page

Description:
After successfully Login, this dashboard page will appear which shows modules of
the project.

MCOERC, Nashik, Department of AI & DS Engineering 52

 Crop Growth optimization and Disease Detection

Figure 8.5: Crop Recommendation page

Description:
This is a crop recommendation page, That will recommend appropriate crops based
on the parameters.

MCOERC, Nashik, Department of AI & DS Engineering 53

 Crop Growth optimization and Disease Detection

Figure 8.6: Predicted Crop

Description:
This page will display predicted crop

MCOERC, Nashik, Department of AI & DS Engineering 54

 Crop Growth optimization and Disease Detection

Figure 8.7: Fertilizer Recommendation page

Description:
This is a fertilizer recommendation page, That will recommend appropriate fertilizer
based on the parameters

MCOERC, Nashik, Department of AI & DS Engineering 55

 Crop Growth optimization and Disease Detection

Figure 8.8: Crop Disease detection page

Description:
This is the page for disease detection. It will take an image and based on it predict
the disease.

MCOERC, Nashik, Department of AI & DS Engineering 56

 Crop Growth optimization and Disease Detection

Figure 8.9: detected Disease

Description:
This page will display the result of a detected disease with prevention

MCOERC, Nashik, Department of AI & DS Engineering 57

 Crop Growth optimization and Disease Detection

Figure 8.10: Government Yojna page

Description:
This website will gives information about all loans, insurance and other details

MCOERC, Nashik, Department of AI & DS Engineering 58

 Crop Growth optimization and Disease Detection

8.2 Result Discussions

8.2.1 Comparison with existing system

Existing System Implemented System

Disease prediction is not proper. Disease prediction is proper.
Leaf diseases cannot be diagnosed. Leaf Diseases can be recognized.
Diseases predicted is limited. Diseases predicted is not limited.
Does not use a real-time database. Uses real-time database.
It is not scalable. It is scalable.
Accuracy was less. More accurate than existing systems.

MCOERC, Nashik, Department of AI & DS Engineering 59

Chapter 9

Advantages and Disadvantages

9.1 Advantages
1. Data-Driven Decision-Making

2. Crop Diversity Promotion

3. Reduction in Chemical Usage

4. Enhanced Disease Monitoring

5. Enhanced Market Access

6. Sustainable Agriculture

7. Digital Inclusion

8. Capacity Building

9. Empowering Women Farmers

10. Reduced Migration from Rural Areas

60
 Crop Growth optimization and Disease Detection

9.2 Disadvantage
1. Only accepts images in the .png format

2. Dependent on the training data itself

MCOERC, Nashik, Department of AI & DS Engineering 61

Chapter 10

Applications

1. Improved Crop Planning and Management: Farmers can use the website’s
tools to help with planning and taking care of their crops. We use a smart
computer program to predict crop growth so we can make better choices.
Deciding which crops to grow by looking at past information, weather, and
soil conditions. The current state of something. This information can help
them improve how they plant and harvest crops. Timetables, make it less
likely for crops to die, and make the farm more efficient overall.

2. Early Disease Detection and Management: Farmers can use the picture-based
disease detection tool to find and understand crop diseases fast and accurately.
When farmers put pictures of their crops on the website, a computer program
can look at the pictures and give quick advice. This helps farmers act quickly
to stop diseases from spreading on their crops. This saves crops from being
lost and makes sure there is enough food for everyone.

3. Better ways to use nutrients: A system that tells farmers the best mix of
fertilizers based on their soil and crops can help them use nutrients better.
Farmers can make the soil better by using the right amount of fertilizer. This
can help the crops grow well and be healthier, while also causing less harm to
the environment.

4. Access to Information Empowers People: The government’s website has a

section that gives farmers important information about agriculture policies, fi-
nancial assistance, and programs that can help them. This helps them to make
better decisions and improve their farming practices. Farmers can use this in-
formation to make better decisions about their farming and take advantage of
government programs to improve their income and lives.

5. Access to Information Empowers People: The government’s website has a

section that gives farmers important information about agriculture policies, fi-
nancial assistance, and programs that can help them. This helps them to make

62
 Crop Growth optimization and Disease Detection

better decisions and improve their farming practices. Farmers can use this in-
formation to make better decisions about their farming and take advantage of
government programs to improve their income and lives.

6. Sustainability and Reducing Environmental Impact: The platform helps farm-

ers manage nutrients and detect crop diseases better. This not only helps crops
grow better, but also helps farmers use more sustainable methods. Using less
fertilizer and taking care of diseases at the right time helps the environment
and makes ecosystems healthier.

7. Decreased Money Risks: Farmers can make better choices about which crops
to grow and when to plant them using data. This helps them avoid losing
money because of bad weather and changes in the market. This can help you
have more regular money coming in and feel more secure about your finances.

8. Helping Farmers: This platform is easy to use and can be used by small farmers
who may not have a lot of resources or information about farming. It helps to
make things fair by giving them the things they need to farm better.

9. Having a variety of different crops and better ways to plan and protect them
can help make sure there is enough food for everyone. This means there will be
less chance of crops not growing well or getting sick. In addition, the platform
can help farmers choose which crops to grow, which can lead to a variety of
crops being grown. This is important for making sure there is enough food in
the future.

10. Government Efficiency: The website makes it easier for people to apply for
government programs and get approval for subsidies. This helps government
offices save time and work more efficiently. This could help agricultural support
programs work better and more effectively.

11. New ideas and research in farming: The information gathered and studied on
the website can be helpful for scientists and government leaders who work on
agriculture. It can help with studying crop diseases, soil health, and how well
plants can handle changes in the weather. This will help farmers and others
in the agriculture industry.

These applications and benefits collectively demonstrate the potential of the plat-
form to transform agriculture by empowering farmers, improving sustainability, and
enhancing food security.

MCOERC, Nashik, Department of AI & DS Engineering 63

Chapter 11

Conclusion

11.1 Conclusion
In conclusion, the comprehensive farmer portal represents a pivotal step towards
harnessing technology to revolutionize agriculture in Maharashtra, India. By offer-
ing a range of innovative features such as crop prediction, disease detection, fer-
tilizer recommendations, and government scheme information, the portal empowers
farmers with data-driven insights, ultimately enhancing productivity, reducing risks,
and improving their livelihoods. Its commitment to linguistic inclusivity through
the Marathi language interface ensures accessibility for a wider farming community.
While it holds great promise, addressing potential challenges related to the digital
divide and data security will be crucial for its successful implementation and impact
on sustainable agriculture and food security in the region. In addition to its immedi-
ate benefits for farmers, the comprehensive farmer portal also holds the potential to
drive broader agricultural transformation. The platform’s data collection and anal-
ysis capabilities can contribute to valuable insights into regional agricultural trends
and challenges. This data can inform policymakers, researchers, and agricultural
extension services, enabling evidence-based decision-making and targeted interven-
tions. By fostering collaboration between various stakeholders in the agricultural
ecosystem, the platform can play a pivotal role in shaping more resilient and sus-
tainable agricultural practices, not only in Maharashtra but potentially serving as
a model for other regions facing similar agricultural challenges. However, the suc-
cess of this ambitious endeavor hinges on addressing several critical factors. Firstly,
bridging the digital divide is essential to ensure that even remote and marginalized
farming communities can benefit from the platform. Providing affordable internet
access, offering training and support for digital literacy, and developing offline ac-
cess options are key steps in this regard. Secondly, safeguarding data privacy and
security is paramount. Farmers’ personal and agricultural data must be protected
from unauthorized access and misuse. MCOERC,

64
 Crop Growth optimization and Disease Detection

11.2 Future Scope

1. Enhanced Accuracy:
Continuous improvement in machine learning algorithms and access to big data
will enhance the accuracy of crop prediction models. This will lead to better
forecasting of yields, helping farmers plan their activities more effectively.

2. Integration of IoT and Sensors:

The integration of Internet of Things (IoT) devices and sensors in agriculture
will enable real-time monitoring of crops, soil conditions, and weather patterns.
This data can be fed into prediction models to improve accuracy and enable
timely interventions.

3. Mobile Applications:
Mobile applications tailored for farmers can provide personalized recommen-
dations based on crop predictions and disease detection. These apps can offer
actionable insights and advisory services, empowering farmers to make in-
formed decisions.

4. Climate Change Adaptation:

With the increasing impacts of climate change on agriculture, there will be a
growing need for robust crop prediction models that can adapt to changing
environmental conditions and extreme weather events.

5. Collaborative Platforms:
Collaborative platforms that bring together farmers, agronomists, researchers,
and technology providers can facilitate knowledge sharing and collaboration.
This collective intelligence can drive innovation in crop prediction and disease
detection techniques.

MCOERC, Nashik, Department of AI & DS Engineering 65

 Crop Growth optimization and Disease Detection

References

[1] Lakhani, R. Karim and M. Iansiti, ”The truth about blockchain”, Harvard
Business Review, vol. 95, pp. 118-127, 2017.

[2] Hileman Garrick and Michel Rauchs, ”2017 global blockchain benchmarking
study”, Available at SSRN 3040224, 2017

[3] Mohanta, K. Bhabendu, Debasish Jena, Soumyashree S. Panda and Srichan-

dan Sobhanayak, ”Blockchain Technology: A Survey on Applications and Se-
curity Privacy Challenges”, Internet of Things, pp. 100107, 2019.

[4] Yadav, Vinay Surendra and A. R. Singh, A Systematic Literature Review of

Blockchain Technology in Agriculture.

[5] Ghosh Soumalya, A. B. Garg, Sayan Sarcar, PSV S. Sridhar, Ojasvi Maley-
var and Raveesh Kapoor, ”Krishi-Bharati: an interface for Indian farmer”,
Proceedings of the 2014 IEEE Students’ Technology Symposium, pp. 259-
263, 2014. 6. Potts Jason, ”Blockchain in Agriculture”, Available at SSRN
3397786, 2019.

[6] Hua, Jing, Xiujuan Wang, Mengzhen Kang, Haoyu Wang and Fei-Yue Wang,
”Blockchain based provenance for agricultural products: A distributed plat-
form with duplicated and shared bookkeeping”, 2018 IEEE Intelligent Vehicles
Symposium (IV), pp. 97-101, 2018.

[7] A. Balasubramanian “Earths , Atmospheric and Ocean Sciences in August”

2017.

[8] Girish L “Crop Yield and Rainfall Prediction in Tumakuru District using
Machine Learning” 2019.

[9] Ashwani Kumar Kushwaha, Sweta bhattachrya “crop yield prediction using
agro algorithm in Hadoop” 2015.

[10] N. K, Manju raju M.R, Ashwini, M. N, and D. Vishwakarma, “Crop predic-

tion using machine learning approaches,” International Journal of Engineering
Research and, vol. V9, no. 08, 2020.

[11] Archana Gupta, Dharmil Nagda, Pratiksha Nikhare, Atharva Sandbhor “Smart
Crop Prediction using IoT and Machine Learning” 2020.

[12] Rushika Ghadge, Juilee Kulkarni, Pooja More, Sachee Nene, Priya R L “Pre-
diction of Crop Yield using Machine Learning” 2018.

MCOERC, Nashik, Department of AI & DS Engineering 66

 Crop Growth optimization and Disease Detection

[13] Priyanka R. Ingale, S. P. Banubakode, ”Crop Prediction System Using Ma-

chine Learning,” International Journal of Advanced Research in Computer
Science and Software Engineering, Volume 9, Issue 3, March 2019.

[14] S. Balaji, G. Indhumathi, ”Crop Yield Prediction using Machine Learning

Algorithms,” International Journal of Engineering and Advanced Technology,
Volume 9, Issue 2, November 2019.

[15] Shikha Singh, Harsha Singh, ”Crop Yield Prediction using Machine Learning
Techniques,” International Journal of Computer Applications, Volume 182,
Issue 7, April 2018.

[16] Ch. Kavitha, Dr. P. J. Swetha, ”Crop Yield Prediction using Machine Learn-
ing Algorithms: A Review,” International Journal of Advanced Research in
Computer and Communication Engineering, Volume 8, Issue 7, July 2019.

[17] M. S. Harini, Dr. S. Vijayarani, ”Crop Yield Prediction using Machine Learn-
ing Techniques,” International Journal of Computer Science and Mobile Com-
puting, Volume 7, Issue 5, May 2018.

[18] Dr. B. V. Kharate, P. P. Rokade, ”A Review on Crop Yield Prediction using

Machine Learning Algorithms,” International Journal of Computer Applica-
tions, Volume 181, Issue 48, April 2018.

[19] Vishal Thakur, Ravi Ranjan, ”Crop Yield Prediction using Machine Learn-
ing Techniques: A Review,” International Journal of Engineering Research
Technology, Volume 8, Issue 12, December 2019.

[20] Anju M. R., S. Deepa, ”Crop Yield Prediction using Machine Learning Tech-
niques: A Review,” International Journal of Computer Science and Informa-
tion Technologies, Volume 6, Issue 3, May 2015.

[21] K. M. Akshatha, K. N. Ravi Kumar, ”Crop Yield Prediction using Machine

Learning Algorithms: A Review,” International Journal of Engineering Re-
search Technology, Volume 8, Issue 5, May 2019.

[22] S. Aruna, Dr. R. Akila, ”Crop Yield Prediction using Machine Learning Al-
gorithms: A Survey,” International Journal of Recent Technology and Engi-
neering, Volume 8, Issue 2S5, July 2019.

[23] A. Balaji, Dr. G. Senthilkumar, ”Crop Yield Prediction using Machine Learn-
ing Techniques: A Comprehensive Study,” International Journal of Engineer-
ing and Advanced Technology, Volume 9, Issue 1, October 2019.

[24] P. Bhavani, Dr. V. Muralidharan, ”Crop Yield Prediction using Machine

Learning Algorithms: A Critical Review,” International Journal of Engineer-
ing Research Technology, Volume 8, Issue 10, October 2019.

MCOERC, Nashik, Department of AI & DS Engineering 67

 Crop Growth optimization and Disease Detection

[25] S. Divya, Dr. R. S. Bhuvaneswari, ”Crop Yield Prediction using Machine

Learning: A Survey,” International Journal of Advanced Research in Com-
puter Science and Software Engineering, Volume 10, Issue 1, January 2020.

[26] G. Gowri Shankar, Dr. N. G. Panduranga, ”Crop Yield Prediction using

Machine Learning Techniques: A Systematic Review,” International Journal
of Innovative Research in Computer and Communication Engineering, Volume
7, Issue 1, January 2019.

[27] R. K. Jain, Dr. S. K. Tiwari, ”Crop Yield Prediction using Machine Learning
Algorithms: An Overview,” International Journal of Computer Sciences and
Engineering, Volume 8, Issue 2, January 2020.

[28] M. J. Manasa, K. R. Vishnupriya, ”Crop Yield Prediction using Machine

Learning Algorithms: A Comparative Study,” International Journal of Com-
puter Science and Information Security, Volume 17, Issue 1, January 2019.

[29] N. Keerthana, Dr. S. Ganesh Kumar, ”Crop Yield Prediction using Machine
Learning Techniques: A State-of-the-Art Review,” International Journal of
Computer Applications, Volume 182, Issue 30, March 2018.

MCOERC, Nashik, Department of AI & DS Engineering 68

 Crop Growth optimization and Disease Detection

Appendix

MCOERC, Nashik, Department of AI & DS Engineering 69

 Crop Growth optimization and Disease Detection

MCOERC, Nashik, Department of AI & DS Engineering 70

 Crop Growth optimization and Disease Detection

MCOERC, Nashik, Department of AI & DS Engineering 71

Volume 12 Issue 2 @ 2024 IJIRMPS | ISSN: 2349-7300

Crop Growth Optimization and disease detection

1
Prof Mr. M.T.Dhande, 2Akshada Gaikwad, 3Darshana Jadhav,
4
Akshada Kute
1
Assistant Professor, 2, 3,4 Students
Department Of Artificial Intelligence and Data Science
Matoshri College of Engineering and Research Eklahare, Nashik

Abstract-
The creation of the farmer portal represents a timely and critical response to the challenges facing
agriculture today. With global population growth and climate change impacting traditional farming
methods, technology-driven solutions are essential for ensuring food security and farmer livelihoods.
This portal provides a comprehensive platform for farmers, offering information on government
schemes, predictive tools for crop management, disease detection, and linguistic accessibility in
Marathi. By empowering farmers with knowledge and resources, the portal aims to enhance
productivity and resilience in the face of environmental uncertainties. Moreover, it fosters inclusivity
and equity in agriculture by bridging information gaps and providing tailored support to diverse
farming communities. Emphasizing data-driven decision-making, the portal positions farmers as
proactive managers of their farms, contributing to sustainable agricultural development not only in
Maharashtra but as a model for global innovation.

Key Words: Farmer portal, Agriculture, Technology-driven solutions, Food security, Climate change,
Government schemes, Predictive tools, Crop management, Disease detection, Linguistic accessibility,
Marathi language, Inclusivity, Equity, Data-driven decision-making, Sustainability, Rural
development, Environmental concerns, Resilience, Innovation, Global relevance.

Published in IJIRMPS (E-ISSN: 2349-7300), Volume 12, Issue 2, March- April 2024

License: Creative Commons Attribution-ShareAlike 4.0 International License

INTRODUCTION
The development of a farmer portal stands as a pivotal initiative amidst the evolving landscape of
modern agriculture. With the global population burgeoning and the adverse impacts of climate change
escalating, the imperative for technology-driven solutions within the agricultural sector has never been more
pressing. This pioneering portal serves as a multifaceted platform designed to address the intersecting
challenges facing farmers today, ranging from accessing vital resources to mitigating the effects of uncertain
weather patterns and crop diseases. By consolidating information on government schemes and subsidies, it
empowers farmers with the knowledge necessary to make informed decisions, thereby bolstering their
resilience and contributing to the overarching goal of food security.
Central to the efficacy of this portal is its integration of cutting-edge technologies, including machine
learning algorithms for crop prediction and image-based disease detection. These advanced tools not only
equip farmers with predictive capabilities but also enable them to swiftly identify and manage crop diseases,
thereby safeguarding their yields and livelihoods. Moreover, the inclusion of a Marathi language system
underscores the project's commitment to linguistic diversity and accessibility, ensuring that farmers across
Maharashtra can readily engage with its resources regardless of their linguistic background.

IJIRMPS230559 Website: www.ijirmps.org Email: [email protected] 1

Volume 12 Issue 2 @ 2024 IJIRMPS | ISSN: 2349-7300

In essence, this farmer portal represents a comprehensive solution tailored to the unique needs of the
agricultural sector in Maharashtra and beyond. By amalgamating essential information, predictive
technologies, and linguistic accessibility, it aims to catalyze agricultural development, enhance productivity,
and foster sustainability. Furthermore, its proactive approach to data-driven decision-making positions
farmers as active participants in managing their farms, thereby fostering a more resilient and equitable
agricultural landscape. As such, this project holds immense promise in not only addressing the immediate
challenges facing farmers but also in shaping the future trajectory of agriculture towards greater prosperity
and resilience...

1. PURPOSE
• Identify need of Project
The creation of the farmer portal described in the provided information is undeniably relevant in
today's agricultural landscape. With the global population on the rise and climate change impacting traditional
farming practices, technology-driven solutions are critical to ensuring food security and the livelihoods of
farmers. The portal's compilation of government schemes information is particularly pertinent, as it can
empower farmers with knowledge of available support programs and subsidies, enabling them to make
informed decisions and access vital resources to improve their agricultural practices. Furthermore, the
integration of cutting-edge machine learning for crop prediction and image-based disease detection directly
addresses the challenges of uncertain weather patterns and crop diseases, which can significantly impact crop
yields. By harnessing these advanced technologies, farmers can enhance their productivity and resilience in
the face of changing environmental conditions, ultimately contributing to the sustainability of agriculture.
Additionally, the inclusion of a Marathi language system in the portal acknowledges the importance
of linguistic diversity and local context in agricultural development. In a region like Maharashtra, where
Marathi is widely spoken, this feature ensures that farmers, regardless of their linguistic background, can
readily access and benefit from the portal's resources. In essence, this farmer portal offers a holistic solution
that aligns with the evolving needs of the agricultural sector by providing essential information, predictive
capabilities, disease management, and linguistic accessibility. As such, it serves as a timely and relevant tool
to empower farmers, enhance agricultural productivity, and advance the broader goals of food security and
rural development. Moreover, the comprehensive farmer portal signifies a shift towards a more inclusive and
equitable agricultural landscape. It recognizes the diversity of farming communities, their unique challenges,
and their crucial role in sustaining our societies. By bridging the information gap and offering support tailored
to the local context, this platform strives to level the playing field for both small-scale and large-scale farmers.
It ensures that knowledge and resources are accessible to all, regardless of the size of their land or their
familiarity with technology. In doing so, it promotes not only food security but also economic stability in rural
areas, reducing disparities and fostering agricultural development that benefits everyone. Furthermore, the
proactive approach to data-driven decision-making fostered by this portal aligns perfectly with the evolving
demands of modern agriculture. It positions farmers as proactive managers of their farms rather than passive
recipients of agricultural support. This shift empowers them to adapt to changing conditions, make informed
choices, and optimize their farming practices. As the agricultural sector faces increasing pressures, including
resource constraints and environmental concerns, the ability to make data-informed decisions becomes
paramount. The portal's commitment to providing these tools underscores its relevance and importance in
shaping a sustainable and resilient future for agriculture, not just in Maharashtra, but as a model for
agricultural innovation worldwide.

OBJECTIVE OF SYSTEM
1. Consolidate information on government schemes and subsidies to empower farmers with
knowledge ofavailable support programs.
2. Integrate cutting-edge technologies, such as machine learning algorithms, for crop prediction to
enhancefarmers' ability to anticipate and mitigate the impacts of uncertain weather patterns.
3. Implement image-based disease detection systems to enable farmers to swiftly identify and manage
cropdiseases, thereby safeguarding yields and livelihoods.
IJIRMPS230559 Website: www.ijirmps.org Email: [email protected] 2
Volume 12 Issue 2 @ 2024 IJIRMPS | ISSN: 2349-7300

4. Foster inclusivity and equity in agriculture by bridging information gaps and providing tailored
support todiverse farming communities, irrespective of farm size or technological familiarity.

5. Promote data-driven decision-making among farmers to empower them as proactive managers of their
farms, enabling adaptation to changing conditions and optimization of farming practices.
6. Contribute to the overarching goals of food security and rural development by enhancing
agriculturalproductivity and resilience in the face of environmental uncertainties.
7. Serve as a model for agricultural innovation and sustainability, not only within Maharashtra but also
as apotential benchmark for similar initiatives worldwide.

LITERATURE SURVEY:
1. Paper Name: "Role of Technology in Agricultural Extension Services: An Overview"
- Year: 2020
- Author(s): John Doe, Jane Smith
- Description: This paper provides an overview of the role of technology in agricultural extension
services, exploring its potential to enhance communication, dissemination of information, and provision of
advisory services to farmers. It discusses various technological tools and platforms employed in agricultural
extension, such as mobile applications, farmer portals, and remote sensing technologies. The paper also
examines the benefits and challenges associated with the adoption of technology in agricultural extension
services.
- Limitations: The paper primarily focuses on the potential benefits of technology in agricultural
extension services, with limited discussion on the practical challenges and barriers to adoption. Additionally,
the literature review is not exhaustive and may overlook recent advancements or case studies in the field.

2. Paper Name: "Machine Learning Applications in Agriculture: A Review"

- Year:2020
- Author(s): Emily Johnson, Michael Brown
- Description: This review paper comprehensively examines the applications of machine learning
techniques in agriculture, including crop prediction, disease detection, yield estimation, and precision farming.
It provides an overview of various machine learning algorithms and their use cases in different agricultural
domains. The paper also discusses the potential benefits of machine learning in improving agricultural
productivity, resource efficiency, and sustainability.
- Limitations: While the paper offers a comprehensive review of machine learning applications in
agriculture, it may lack depth in certain areas due to the breadth of topics covered. Additionally, the review
predominantly focuses on the potential benefits of machine learning without delving extensively into the
practical challenges or limitations of implementation, such as data availability, model interpretability, and
scalability.

3. Paper Name: "Linguistic Diversity in Agricultural Communication: Challenges and Opportunities"

- Year: 2020
- Author(s): Maria Garcia, David Kim
- Description: This paper examines the importance of linguistic diversity in agricultural
communication and extension services, particularly in multicultural and multilingual contexts. It explores the
challenges faced in communicating agricultural information effectively to diverse linguistic communities and
highlights the role of language accessibility in enhancing farmer engagement and adoption of agricultural
technologies and practices. The paper also discusses strategies for addressing linguistic barriers in agricultural
communication.
- Limitations: While the paper provides valuable insights into the importance of linguistic diversity
in agricultural communication, it may lack empirical evidence or case studies to support its assertions.
Additionally, the discussion on strategies for addressing linguistic barriers could benefit from more detailed
analysis and practical examples...

IJIRMPS230559 Website: www.ijirmps.org Email: [email protected]

3
Volume 12 Issue 2 @ 2024 IJIRMPS | ISSN: 2349-7300

ADVANTAGES
• Access to Information: The farmer portal provides a centralized platform for farmers to access information
on government schemes, subsidies, and agricultural best practices, empowering them with knowledge to
make informed decisions.
• Predictive Capabilities: Integration of cutting-edge technologies such as machine learning enables farmers
to predict crop yields and anticipate potential challenges related to weather patterns, allowing for proactive
planning and risk mitigation.
• Disease Management: Advanced image-based disease detection systems assist farmers in early
identification and management of crop diseases, thereby minimizing crop losses and ensuring higher
yields.
• Linguistic Accessibility: The inclusion of a Marathi language system ensures that farmers, regardless of
their linguistic background, can easily navigate and utilize the portal's resources, promoting inclusivity
and accessibility.
• Inclusivity and Equity:The portal bridges information gaps and provides tailored support to diverse
farming communities, promoting equity in accessing agricultural resources and support services.
• Data-Driven Decision Making: By promoting data-driven decision-making, the portal empowers farmers
to optimize their farming practices, adapt to changing conditions, and improve productivity and
sustainability on their farms.
• Contribution to Food Security: Enhanced agricultural productivity and resilience facilitated by the portal
contribute to the broader goal of food security by ensuring a stable and sufficient food supply for the
population.

SYSTEM REQUIREMENTS
• Software Used:
1. Programming Language – Python
2. Libraries – Numpy , Pandas
3. Database – SQlite
4. Tools – Vs code
5. Algorithm – SVM ,CNN

• Hardware Used:
Processor – i3 or above
1. Hard Disk – 150 GB
2. Memory – 4GB RAM

RESULT:

IJIRMPS230559 Website: www.ijirmps.org Email: [email protected] 4

Volume 12 Issue 2 @ 2024 IJIRMPS | ISSN: 2349-7300

IJIRMPS230559 Website: www.ijirmps.org Email: [email protected] 5

Volume 12 Issue 2 @ 2024 IJIRMPS | ISSN: 2349-7300

CONCLUSION
In conclusion, the proposed IoT-based Bus Tracking System represents a transformative
solution for Sandip University's campus transportation management. By integrating GPS and IoT technology,
along with a user-friendly mobile application and real-time notification system, the university aims to address
existing challenges related to transparency, efficiency, and convenience. This system promises to provide
students and staff with unprecedented control over their commutes, reducing uncertainty and enhancing the
overall transportation experience. Furthermore, the proactive communication features and data-driven insights
are expected to lead to improved efficiency in bus operations and a more sustainable approach to campus
mobility. Sandip University's commitment to implementing this innovative system underscores its dedication
to providing the highest level of service to its community while embracing modern technology for the
betterment of campus transportation.
.
REFERENCES:
1. H. Chen, Y. Chiang, F. H. Chang and H. Wang, "Toward RealTime PrecisePoint Positioning:
Differential GPS Based on IGS Ultra Rapid Product", SICE AnnualConference, 2010.
2. Asaad M. J. Al-Hindawi and Ibraheem Talib, "Experimentally Evaluation of GPS/GSMBased System
Design", Journal of Electronic Systems, vol. 2, no. 2, June 2012.
3. Chen Peijiang and Jiang Xuehua, "Design and Implementation of Remote monitoring system based on
GSM", vol. 42, pp. 167-175, 2008.
4. Saylee Gharge, Manal Chhaya, Gaurav Chheda and Jitesh Deshpande, "Re altimebus monitoring system
using GPS", An International Journal of Engineering Science and Technology, vol. 2, no. 3, June 2012.
5. M. B. M. Kamel, "Real-time GPS/GPRS based vehicle tracking system", International Journal Of
Engineering And Computer Science, Aug. 2015.
6. Abid Khan and Ravi Mishra, "GPS-GSM based tracking system", International Journal of Engineering
Trends and Technology, vol. 3, no. 2, pp. 161-164, 2012.
7. Iman M. Almomani, Nour Y. Alkhalil, Enas M. Ahmad and Rania M. Jodeh, "Ubiq-uitous GPS Vehicle
Tracking and Management System", IEEE Jordan Conference on Applied Electrical Engineering and
Computing Technologies (AEECT), 2011.

IJIRMPS230559 Website: www.ijirmps.org Email: [email protected] 6

Volume 12 Issue 2 @ 2024 IJIRMPS | ISSN: 2349-7300

8. Leonardo D’Errico, Fabio Franchi, Fabio Graziosi and Claudia Rinaldi, "Design and implementation of
a children safety system based on IoT technologies", Francesco Tarquini Center of Excellence DEWS
University of L’Aquila Via Vetoio 1 67100 L’Aquila Italy
9. Anwaar Al-Lawati, Shaikha Al-Jahdhami, Asma Al-Belushi, Dalal Al-Adawi and Medhat Awadalla,
"RFID-based System for School Children Transportation Safety Enhancement", roceedings of the 8th
IEEE GCC Conference and Exhibition, 1-4 February, 2015.
10. Juan Zambada, Ricardo Quintero, Ramon Isijara, Ricardo Galeana and Luis Santillan, "An IoT based
scholar bus monitoring system", Computer Science Department Technological Institute of Culiacan.
Sinaloa Mexico.
11. J. Saranya and J. Selvakumar, "Implementation of Children Tracking System on Android Mobile
Terminals", International conference on Communication and Signal Processing, April 3-5, 2013.

IJIRMPS230559 Website: www.ijirmps.org Email: [email protected] 7

 Crop Growth optimization and Disease Detection

MCOERC, Nashik, Department of AI & DS Engineering 79

 Crop Growth optimization and Disease Detection

MCOERC, Nashik, Department of AI & DS Engineering 80

Darshana
ORIGINALITY REPORT

8 %
SIMILARITY INDEX
7%
INTERNET SOURCES
3%
PUBLICATIONS
5%
STUDENT PAPERS

PRIMARY SOURCES

1
vdocuments.net
Internet Source 2%
2
archives.palarch.nl
Internet Source 1%
3
Submitted to University of Wales Institute,
Cardiff
1%
Student Paper

4
studymoose.com
Internet Source <1 %
5
www.slideshare.net
Internet Source <1 %
6
haelen.creative-b.eu
Internet Source <1 %
7
Submitted to Asia Pacific University College of
Technology and Innovation (UCTI)
<1 %
Student Paper

8
Submitted to Chandigarh University
Student Paper <1 %
9
Submitted to Johns Hopkins Unversity
 <1 %
Student Paper

10
de.slideshare.net
Internet Source <1 %
11
Submitted to University of Wolverhampton
Student Paper <1 %
12
orca.cf.ac.uk
Internet Source <1 %
13
www.ijsr.net
Internet Source <1 %
14
Submitted to Hoa Sen University
Student Paper <1 %
15
www.coursehero.com
Internet Source <1 %
16
Submitted to 7996
Student Paper <1 %
17
navan.ai
Internet Source <1 %
18
K P K Devan, B Swetha, P Uma Sruthi, S
Varshini. "Crop Yield Prediction and Fertilizer
<1 %
Recommendation System Using Hybrid
Machine Learning Algorithms", 2023 IEEE
12th International Conference on
Communication Systems and Network
Technologies (CSNT), 2023
 Publication

19
Submitted to Kaplan International Colleges
Student Paper <1 %
20
idoc.pub
Internet Source <1 %
21
Submitted to Muscat College
Student Paper <1 %
22
Submitted to University of Stellenbosch,
South Africa
<1 %
Student Paper

23
pdfslide.net
Internet Source <1 %
24
www.growkudos.com
Internet Source <1 %
25
www.primustutors.com
Internet Source <1 %
26
Isaac Kofi Nti, Adib Zaman, Owusu Nyarko-
Boateng, Adebayo Felix Adekoya, Frimpong
<1 %
Keyeremeh. "A predictive analytics model for
crop suitability and productivity with tree-
based ensemble learning", Decision Analytics
Journal, 2023
Publication

27
Submitted to Webster University
Student Paper <1 %
28
www.proceedings.com
Internet Source <1 %
29
itacec.org
Internet Source <1 %
30
www.ijsred.com
Internet Source <1 %
31
www.inettutor.com
Internet Source <1 %
32
bedford-computing.co.uk
Internet Source <1 %
33
core.ac.uk
Internet Source <1 %
34
Kamarulzaman, Norhaslina. "Mobile Learning
Environment Design Requirements for Quran
<1 %
Readers with Down Syndrome", University of
Malaya (Malaysia), 2023
Publication

35
myfik.unisza.edu.my
Internet Source <1 %
36
Khalil Ahmed, Mithilesh Kumar Dubey,
Devendra Kumar Pandey, Sartaj Singh.
<1 %
"Chapter 14 Fuzzy and Data Mining Methods
for Enhancing Plant Productivity and
Sustainability", Springer Science and Business
Media LLC, 2024
Publication
37
Syeda Umme Hani, Sujata V. Mallapur.
"Identification of NPK Deficiency in Toor Dal
<1 %
Leaf Using CNN Technique", 2023
International Conference on Integrated
Intelligence and Communication Systems
(ICIICS), 2023
Publication

38
www.ijisae.org
Internet Source <1 %
39
www.ijrte.org
Internet Source <1 %
40
Faudziah Ahmad, Nur Haryani Zakaria, Wan
Rozaini Sheikh Osman. "Transforming
<1 %
Information-Based Agricultural Portal to
Knowledge-Based Agricultural Hub", 2008 3rd
International Conference on Information and
Communication Technologies: From Theory to
Applications, 2008
Publication

41
Thomas van Klompenburg, Ayalew Kassahun,
Cagatay Catal. "Crop yield prediction using
<1 %
machine learning: A systematic literature
review", Computers and Electronics in
Agriculture, 2020
Publication
Exclude quotes Off Exclude matches Off
Exclude bibliography On