lOMoARcPSD|35684657

Project Synopsis on
“Crop Cycle Prediction System”

Course name: PROJECT -II

Course code: PROJ-CSE-423

BACHELOR OF TECHNOLOGY

COMPUTER SCIENCE & ENGINEERING [

Submitted By
SAKSHI

(Roll No.:213035)

Under the Supervision of

Ms Preeti Shree
(Assistant Professor)

Department of Computer Science & Engineering

St. Andrews Institute of Technology &

Management Gurugram(Haryana)–122506
 lOMoARcPSD|35684657

TABLE OF CONTENTS

S.N CONTENT PAGE

O
1. Problem Statement

2. Introduction

3. Objective

4. Feasibility Study

5. Methodology

6. Software/Hardware
Requirements

7. Expected Outcomes

8. Conclusion

9. Future Scope

10. Bibliography
 lOMoARcPSD|35684657

PROBLEM STATEMENT

Failure of farmers to decide on the best suited crop for his land using traditional and non-scientific methods is a
serious issue for a country where approximately 50 percent of the population is involved in farming. Both
availability and accessibility of correct and up to date information hinders potential researchers from working
on developing country case studies. With resources within our reach we have proposed a system which can
address this problem by providing predictive insights on crop sustainability and recommendations based on
machine learning models trained considering essential environmental and economic parameters.

OBJECTIVE
 lOMoARcPSD|35684657

In Indian economy and employment agriculture plays major role. The most common problem faced by the
Indian farmers is they do not opt crop based on the necessity of soil, as a result they face serious setback in
productivity. This problem can be addressed through precision agriculture. This method takes three parameters
into consideration, viz: soil characteristics, soil types and crop yield data collection based on these parameters
suggesting the farmer suitable crop to be cultivated. Precision agriculture helps in reduction of non-suitable crop
which indeed increases productivity, apart from the following advantages like efficacy in input as well as output
and better decision making for farming. This method gives solutions like proposing a recommendation system
through an ensemble model with majority voting techniques using Random Forest and K - Nearest Neighbor as
learner to recommend suitable crop based on soil parameters with high specific accuracy and efficiency.
 lOMoARcPSD|35684657

FEASIBILITY STUDY

Technical Feasibility

 Data availability: Soil, weather, and crop yield data are available from various open-source platforms.
IoT and satellite data are also accessible, but may require significant infrastructure.
 Algorithms: Well-established machine learning algorithms for crop recommendation exist and have
been tested in various studies. However, model accuracy will depend on the quality and variety of the
data.
 Infrastructure: The system can be built on cloud platforms with scalable computing and storage
resources. IoT integration might require additional investments in sensor devices and communication
networks.
 Integration challenges: Combining data from multiple sources (satellites, sensors, and government
databases) can present challenges in terms of data compatibility and cleaning.

Economic Feasibility

 Development Costs: Developing a basic machine learning model for crop recommendation can be cost-
effective, especially with the use of open-source tools. However, integrating real-time data sources (like
IoT) could increase costs significantly.
 Farmers’ access: Providing this system to farmers in rural areas may require investments in mobile
technology, internet access, and training.
 Cost-benefit: Once deployed, the system can potentially help farmers improve yields and profitability
by choosing optimal crops based on data-driven recommendations.

Operational Feasibility

 User acceptance: Farmers, especially in rural areas, may need training and support to utilize the system
effectively. Providing a user-friendly interface (such as a mobile app) is crucial.
 Maintenance: Continuous data collection and updating will be necessary to keep the system reliable.
Maintenance of IoT infrastructure (sensors, data servers) may require a dedicated team.
 Partnerships: Collaboration with government agencies, local agricultural research stations, and
technology providers will be essential for accurate data collection and support.
 lOMoARcPSD|35684657

METHODOLOGY

INTRODUCTION TO MACHINE LEARNING

Machine learning is a branch of computer science that employs statistical techniques to enable computer
systems to "learn" (i.e., progressively improve performance on a specific task) from data without being
explicitly programmed. Arthur Samuel coined the term "machine learning" in 1959. Machine learning, which
evolved from the study of pattern recognition and computational learning theory in artificial intelligence,
investigates the study and construction of algorithms that can learn from and make predictions on data – such
algorithms overcome strictly static programme instructions by making data-driven predictions or decisions, by
building a model from sample inputs. Machine learning is used in a variety of computing tasks where designing
and programming explicit algorithms with high performance is difficult or impossible; examples include email
filtering, network intruder detection, and computer vision. Machine learning is closely related to (and frequently
overlaps with) computational statistics, which is also concerned with making predictions using computers. It has
strong ties to mathematical optimization, which provides the field with methods, theory, and application
domains. Machine learning is frequently confused with data mining, the latter of which focuses on exploratory
data analysis and is referred to as unsupervised learning. Machine learning is a method used in the field of data
analytics to create complex models and algorithms that lend themselves to prediction; in commercial use, this is
known as predictive analytics. Through learning from historical relationships and trends in the data, these
analytical models enable researchers, data scientists, engineers, and analysts to "produce reliable, repeatable
decisions and results" and uncover "hidden insights."

TRAINING THE DATA

There are basically two widely-used types of training that can be done to create a model: i. Supervised
Learning ii. Un-supervised Learning

1 SUPERVISED LEARNING

The machine learning task of learning a function that maps an input to an output based on example input-output
pairs is known as supervised learning. It derives a function from labelled training data, which consists of a set of
training examples. Each example in supervised learning is a pair consisting of an input object (typically a
vector) and desired output value (also called the supervisory signal). A supervised learning algorithm examines
the training data and generates an inferred function that can be used to map new examples. In an ideal scenario,
the algorithm will be able to correctly determine the class labels for unseen instances. This necessitates that the
learning algorithm generalize from the training data to previously unseen situations in a "reasonable" manner.

2 UNSUPERVISED LEARNING

The machine learning task of inferring a function that describes the structure of "unlabeled" data is known as
unsupervised machine learning (i.e., data that has not been classified or categorized). Because the examples
provided to the learning algorithm are unlabeled, there is no simple way to assess the accuracy of the structure
produced by the algorithm—a feature that distinguishes unsupervised learning from supervised learning and
reinforcement learning.

The type of training used in this model is SUPERVISED LEARNING.

SYSTEM ARCHITECTURE
 lOMoARcPSD|35684657

A system architecture is a conceptual model using which we can define the structure and behaviour of that
system. It is a formal representation of a system. Depending on the context, system architecture can be used to
refer to either a model to describe the system or a method used to build the system. Building a proper system
architecture helps in analysis of the project, especially in the early stages. Figure 1 depicts the system
architecture and is explained in the following section.

FIG.1 System Architect

 lOMoARcPSD|35684657

INTRODUCTION

Agriculture is the backbone of the country. It is continues to be one of the major sources of income for a
significant portion of the population in India, sustaining livelihoods and contributing to economic growth. More
than 50% of the people depend on agriculture. More than 60% of the land in the country is used for agriculture
to suffice the needs of 1.3 billion people [15]. A few decades ago, people used to do farming by using ancient
tools. But now, after the Green Revolution, and globalization, advanced technology has come. High yielding
varieties of food grains and vegetables have also been invented which has led to greater growth of agriculture in
India. Our country, India is the world’s largest producer of fresh fruits, vegetables, and food grains. For
all these correct nutrients of soils, weather forecast, and enough water is essential for the cultivation of crops.
For agriculture we require water which does not contain high amounts of salt. Water is a ubiquitous
resource that covers an astonishing 71% of the Earth's surface. But only 0.3% of the earth’s surface has
fresh water. So , many people follow many ways to conserve the rainwater. We have various kinds of land
water resources such as rivers, lakes, ponds, and groundwater resources such as wells, borewells etc.
Based on records from the previous years of 2018 and 2019, it can be estimated that there were approx. 145
million landholdings in India [9]. It results into negative impacts like farmer suicides, diversion of agricultural
land for non-agricultural purpose. On the other hand, 48% of farmers don't want their next generation to take
care of their agriculture and its land, instead want to settle down in urban areas [3]. The reasons behind doing
this dreadful act are wrong decisions about the crop selection like selection of a crop that won't give much yield
for the soil, planting in the wrong season, and so on. Farmers can be in a great loss if they do not know the
previous status of the land. If the family primarily depends on agriculture for the major source of income, then it
is very difficult to survive. So, to address these problems, a Crop Recommendation System has been proposed
for farmers which provides predictive insights on crop sustainability and recommendations based on Machine
Learning models trained. It is done by considering essential environmental parameters such as rainfall,
temperature, and geographical location, soil parameters such as Nitrogen(N), Phosphorus(P) and Potassium(K).
By considering all the above parameters, a suitable crop will be predicted to the farmer for their land. Varios
researchers has proposed their own Crop Recommendation System by using different Machine Learning and
Deep Learning algorithms. Some of the algorithms used for building Crop Recommendation Systems are
Random Forest algorithm, Decision Tree algorithms, K-NN, Neural Network, Linear and Logistic
Regression algorithms, SVR, Lasso and Ridge Regression algorithms, LSTM, RNN, Naïve Bayes algorithm,
ANN, and DNN. By comparing the performances of all the above-mentioned algorithms used in Crop
Recommendation System, Random Forest algorithm yields better accuracy and results. It gives precise
recommendation of crops to the farmer.
 lOMoARcPSD|35684657

SYSTEM REQUIREMENTS

Software requirements:
Operating system: Windows 11.
Coding Language: python
Tool: PyCharm, visual studio code
Libraries: Flask, Scikit-learn, numpy, pandas etc.

Hardware requirements:

System: Pentium i3 Processor.

Hard Disk: 500 GB.
Monitor: 15‘‘ LED
Input Devices: Keyboard, Mouse
Ram: 2 GB

EXPECTED OUTCOMES
 lOMoARcPSD|35684657

Improved Crop Yields: By recommending the most suitable crops for a region’s current conditions, farmers
can potentially increase their yields.

Resource Optimization: The system can help farmers make better use of water, fertilizer, and other inputs by
choosing crops that require fewer resources.

Sustainability: Data-driven farming can reduce environmental impact by selecting crops that align with local
soil and weather conditions, minimizing the need for heavy irrigation or chemical inputs.

Economic Upliftment: By growing crops that are in higher demand and better suited to their land, farmers
could improve their income.

CONCLUSION
 lOMoARcPSD|35684657

Machine learning techniques are applied in various fields of agriculture. Implement a system to predict crop
production from the collection of past data. Carry out an arrangement to conjecture generally upheld rural
creation. Plant creation is gotten ready for data handling strategies. Today, random forest is utilized to
characterize a fascinating yield as a genuine harvest. In agribusiness, it is for the most part consistent with
anticipate yields. The higher the yield, the higher the yield. The proposed procedures assist ranchers with
being careful about various harvest necessities and costs. This assists ranchers with picking what harvests to
plant. This work is frequently used to distinguish extra plants that can be gathered monetarily and
proficiently. This innovation can grow a wide assortment of yields. Indian ranchers might enjoy the benefit of
precisely foreseeing yields in various pieces of India.

FUTURE SCOPE
 lOMoARcPSD|35684657

This research work can be enhancing to the high level by building a recommender system of agriculture
production and distribution for farmer. India may be a country wherever agriculture is extremely vital. The
prosperity of the farmers ends up in the prosperity of the state. Thus, our work would assist farmers in sowing
the acceptable seed supported soil necessities so as to extend productivity and exploit such a way. As a result,
farmers will plant the acceptable crop, increasing their yield and therefore the nation's overall productivity.
Our future work can concentrate on associate degree improved knowledge set with an oversized variety of
attributes, in addition as yield prediction.

BIBLIOGRAPHY
 lOMoARcPSD|35684657

[1] Aruvansh Nigam, Saksham Garg, Archit Agrawal ―Crop Yield Prediction using ML Algorithms ―, 2019
Fifth International Conference on Image Information Processing (ICIIP)

[2] LeoBrieman, ―Random Forests‖, 2019 IEEE Transactions on Instrumentation and Measurement

[3] Priya, P., Muthaiah, U., Balamurugan, M.‖ Predicting Yield of the Crop Using Machine Learning
Algorithm‖,2020 International Journal of Engineering Sciences & Research Technology (IJESRT)

[4] Mishra, S., Mishra, D., Santra, G. H.,―Applications of machine learning techniques in agricultural crop
production‖,2020 Indian Journal of Science and Technology

[5] Dr.Y Jeevan Kumar,‖Supervised Learning Approach for Crop Production‖, 2020 5th International
Conference on Communication and Electronics Systems (ICCES)

[6] RameshMedar,Vijay S, Shweta, ―Crop Yield Prediction using Machine Learning Techniques ‖, 2018
International Journal of Engineering Sciences & Research Technology (IJESRT)

[7] Ranjini B Guruprasad, Kumar Saurav, Sukanya Randhawa,‖Machine Learning Methodologies for Paddy
Yield Estimation in India: A CASE STUDY‖, IGARSS 2019 - 2019 IEEE International Geoscience and
Remote Sensing Symposium

[8] https://en.wikipedia.org/wiki/Crop_yield

[9] https://en.wikipedia.org/wiki/Random_forest
lOMoARcPSD|35684657
lOMoARcPSD|35684657