PREDICTING CROP

YIELDS WITH MACHINE

LEARNING INSIGHTS
GUIDE : TEAM MEMBERS :
MS. J. PRIYADHARSHINI AP/IT T.S.JANANI
L.SANTHIYA
S.SWATHI
OBJECTIVES:

 To predict the right crop for cultivation and recommend that to farmers.

 To recommend the fertilizers to the farmers.

 To predict the pesticides and to give suggestion to cure pests problem

ABSTRACT:

• Agriculture growth mainly depends on diverse soil parameters, namely Nitrogen,

Phosphorus, Potassium, Crop rotation, Soil moisture, pH, surface temperature and
weather aspects like temperature, rainfall, etc.

• Technology will prove to be beneficial to agriculture which will increase crop

productivity resulting in better yields to the farmer.

• The proposed project provides a solution for Smart Agriculture by monitoring the
agricultural field which can assist the farmers in increasing productivity to a great extent.

• The technique used in proposed system is DSS.

EXISTING SYSTEM:

• The existing system lacks automation and predictive capabilities, resulting in inefficient
agricultural practices and suboptimal crop yields.
• Farmers rely on traditional methods and personal experience to make crop selection,
fertilizer application, and pest management decisions.
• The technique used in existing system is Deep Learning.
DISADVANTAGE OF EXISTING SYSTEM:

• Manual Processes: The existing system relies heavily on manual processes for crop selection,
fertilizer application, and pest management. This manual approach is time-consuming, labor-
intensive, and prone to human error.
• Limited Data Utilization: Farmers often lack access to comprehensive data regarding soil
composition, weather patterns, and historical crop performance. Without this data, it's
challenging to make informed decisions about crop selection and management practices.
• Dependency on Expertise: Successful crop management in the existing system often depends
on the expertise and experience of individual farmers. This dependency can be a barrier for
new or inexperienced farmers who may lack the necessary knowledge and skills.
PROPOSED SYSTEM:

• The proposed Crop Yield Management ARCHITECTURE

System aims to address the limitations of DIAGRAM:
the existing system by leveraging
technology, data analytics, and predictive
modeling to optimize agricultural
practices and enhance crop yields.
• The Technique used in proposed system
is DSS.
PROBLEM IDENTIFICATION AND SOLUTION:

• Agriculture is one of the main sources of income in India. There is need to improve the
sustainability of agriculture with the rate of increase in suicides of farmer due to crop failure
and less yield and losses. Hence, it is a significant contribution towards the economic and
agricultural welfare of the countries across the world.
• The Problem Statement revolves around prediction of yield of crops considering different
climatic conditions of India including various attributes.
• Goal of this project is to help the farmers to choose the suitable crop to grow in order to get
the required yield and the profit. Need for the crop yield prediction is very much essential at
this point of time for selecting the right crop.
MODULE DESCRIPTION:

User Registration:

The User Registration module enables new users to create accounts within
the system. Users provide necessary information such as username, email address,
and password to register. Upon successful registration, users gain access to
personalized features and functionalities offered by the system. Users fill out a
registration form with required details. Users create a secure password following
specified criteria.
MODULE DESCRIPTION:

User Login:

The User Login module allows registered users to access their accounts
securely. Users provide their credentials, typically a username or email address
along with a password, to authenticate and gain access to account-specific
information and features. Users enter their credentials into a login form for
authentication.
MODULE DESCRIPTION:

Admin Login:

The Admin Login module is designed for system administrators to access the
admin panel for managing system settings, user accounts, and data. Admins provide
their credentials to authenticate and gain access to administrative privileges. Access
to an exclusive admin panel with administrative functionalities and controls. Admin
enter their username along with a password for authentication.
MODULE DESCRIPTION:

Crop Prediction:

The Crop Prediction module utilizes predictive analytics algorithms to

forecast suitable crops for specific agricultural conditions. Users input relevant
data such as soil type, climate, and historical data, and the system generates
predictions based on analyzed factors. Users input agricultural data including soil
type, climate conditions, and geographical location.
MODULE DESCRIPTION:

Fertilizer Prediction:

• The Fertilizer Prediction module predicts appropriate fertilizer

recommendations for specific crops and soil conditions. Users need to
choose their crop in User Interface. According to the choosen crop, the
required fertilizer will be detected.
FLOW DIAGRAM:
IMPLEMENTATION OF HOME PAGE:
LOGIN PAGE:
REGISTRATION:
USER DASHBOARD:
CROP PREDICT:
PREDICTED CROP:
FERTILIZER PREDICT:
FERTILIZATION DETAILS:
PESTICIDE FDETAILS:
ADMIN LOGIN:
EDIT PESTICIDE:
CONCLUSION:

• Decision support systems (DSSs) represent a transformative technology that holds immense
potential for revolutionizing agriculture.
• From crop yield prediction to fertilizer and pesticide recommendation, DSSs offer a comprehensive
solution for optimizing agricultural practices, maximizing productivity, and minimizing time
consuming during prediction.
• By promoting precision agriculture, resource efficiency, and sustainability, DSSs contribute to the
resilience, profitability, and long-term viability of agricultural systems in a rapidly changing world.
• Continue to embrace innovation and technology in agriculture, DSSs will play an increasingly vital
role in shaping the future of farming, ensuring food security, and safeguarding the health of our
planet
FUTURE ENHANCEMENT:

Incorporate spatial analysis techniques to account for spatial autocorrelation in the data.
This can help capture the spatial variability of crop yield and improve the accuracy of
predictions.
Develop interactive visualization tools to allow users to explore the predicted crop yields
and understand the factors influencing the predictions. This can help users make informed
decisions related to crop management and planning.
Our future work is to examine hybrid machine learning such as random forest, support
vector machine, multiple regressor, logistic regressor and deep learning algorithms, such as
deep convolution neural network(DCNN),and long short-term memory(LSTM) which
might provide a fast and accurate solution to this problem.
THANK YOU