Project Report : Crop Yield

______________________________________________________________
Student Name: Pranay Pal
Institute name: University Institute of Technology, Burdwan University
Department: Information Technology
Academic Session: 3rd Year
Year: 2024
______________________________________________________________

Contents :
1. Abstract
2. Introduction
3. Literature Review
4. Methodology
5. Implementation
6. Results
7. Conclusion
8. Future Work
9. References
______________________________________________________________
Abstract

The Crop Yield Prediction application is designed to assist farmers and agricultural
planners by forecasting crop yields based on various environmental and biological
parameters. Utilizing machine learning, specifically a Linear Regression model, this
application aids in making informed decisions to optimize agricultural productivity.
The application is developed using Python's Flask framework and demonstrates the
practical application of AI, ML, and data science in agriculture.

______________________________________________________________
Introduction

Accurate crop yield prediction is essential for effective agricultural planning and
management. By leveraging machine learning techniques, this project aims to create
a web-based application that predicts crop yields based on a set of input parameters
such as clone size, bee populations, temperature ranges, and rainfall data. This
application is particularly useful for farmers and agricultural stakeholders who need
reliable predictions to make informed decisions about crop management and
resource allocation.
______________________________________________________________
Literature Review
[1] In this paper SVM method used to classify crop data and CNN is used to reduce
the relative error. By using these, methods losses of crop yield reduced irrespective
of environment distraction.
[2] In this paper K-means clustering is used to create clusters, Apriori algorithm is
used to count frequent features of a crop for specific location and Naïve Bayes
algorithm is used to find exact crop.
[3] In this paper Decision tree uses greedy methodology and Random Forest
algorithm used to predict the best crop. It helps the farmers in decision making of
which crop to cultivate in the field.
[4] In this paper K nearest algorithm, Naïve Bayes and Decision tree are used to
predict the crop yield. It helps the farmers to identify the yield of crops in different soil
and atmospheric conditions.
[5] In this paper J48 and IBK are used for classification, LWL used to assign instance
weights, LAD tree used to classify based on binary target value. It is useful to the
farmers for early prediction and decision making.
[6] In this paper naïve Bayes and KNN algorithm have been used inorder to achieve
maximum crop yield. By this we can also get the accuracy yield by checking for
different method.
[7] In this paper LSTM and Simple RNN methods are used to predict the temperature
and rainfall. Finally, we got know to that Random Forest Regressor will more
accuracy.
[8] In this paper Feed Forward Neural and Recurrent Neural Network techniques is
used. Comparing the FNN and RNN based on loss of error RNN has low error rate at
the same it is better for crop yield prediction.
[9] In this paper they have developed a user friendly webpage and the accuracy of
predictions are above 75 percent by Random Forest Algorithm.
[10] In this proposed work a Hadoop framework based on Random Forest Algorithm
described works faster

______________________________________________________________
Methodology
The methodology for developing the Crop Yield Prediction application involves the
following steps:

Data Collection: A dataset containing various agricultural parameters and

corresponding crop yields was collected.
Data Preprocessing: The dataset was cleaned to handle missing values, and
features were scaled to ensure consistency.
Model Selection: Linear Regression was selected as the predictive model due to its
simplicity and effectiveness.
Model Training: The model was trained on the preprocessed dataset to learn the
relationship between input parameters and crop yield.
Model Evaluation: The model's performance was evaluated using appropriate
metrics to ensure its accuracy and reliability.
 ______________________________________________________________
Implementation
The implementation of the Crop Yield Prediction application involved several key
components:

Backend Development: The backend was developed using Python's Flask

framework. The trained machine learning model was loaded and integrated into the
Flask application to handle predictions.

Frontend Development: A user-friendly HTML template was designed to allow users

to input data and receive predictions. The template included forms for input
parameters and a section to display the predicted yield.

Integration: The frontend and backend were integrated to create a seamless user
experience. The Flask application handled form submissions, processed the input
data, and returned the prediction to be displayed on the frontend.
______________________________________________________________
Results
The Crop Yield Prediction application was tested using a variety of input scenarios to
evaluate its performance. The Linear Regression model demonstrated a high degree
of accuracy with the following metrics:

Accuracy: 0.9915
Cross Validation: 0.9896
Root Mean Squared Error (RMSE): 125.01

These results indicate that the model is highly reliable and provides accurate
predictions for crop yields based on the provided input parameters. The application
successfully aids in effective agricultural planning by delivering consistent and
precise yield predictions.

______________________________________________________________
Conclusion
The Crop Yield Prediction application successfully demonstrates the practical
application of machine learning in agriculture. By leveraging Linear Regression, the
application provides accurate yield predictions based on key input parameters. This
tool can be highly beneficial for farmers and agricultural planners, helping them
make informed decisions and optimize crop management practices.

______________________________________________________________
Future Work
Future enhancements to the Crop Yield Prediction application could include:
Improved Model Accuracy: Experimenting with more advanced machine learning
algorithms and incorporating additional features could improve prediction accuracy.
Expanded Dataset: Using a larger and more diverse dataset could enhance the
model's generalizability and robustness.
User Interface Enhancements: Improving the user interface to provide a more
intuitive and interactive experience.
Real-time Data Integration: Integrating real-time data sources such as weather APIs
to provide up-to-date predictions.
Mobile Application: Developing a mobile version of the application to increase
accessibility for users in the field.

______________________________________________________________
References
[1] D. Jayanarayana Reddy and Dr. M. Rudrakumar “Crop Yield Prediction Using
Machine Learning Algorithm” in 2021[IEEE].
[2] Shreya V. Bhosale et.al “Crop Yield Prediction Using Data Analytics and Hybrid
Approach” in 2018[IEEE].
[3] Dr. Y. Jeevan Nagandrakumar et.al “Supervised Machine Learning Approach for
Crop Yield Prediction in Agriculture Sector” in 2020[IEEE].
[4] Shruthi Mishra, Priyanka Paygude et.al “Use of Data Mining in Crop Yield
Prediction” in 2018[IEEE].
[5] Pranay Malik et.al “Comparative Analysis of Soil Properties to Predict Fertility and
Crop Yield using Machine Learning Algorithm” in 2021[IEEE].
[6] Ramesh Medar et.al “Crop Yield Prediction Using Machine Learning Techniques”
in 2019[IEEE].
[7] Parul Agrawal et.al “Crop Yield Prediction Using Machine Learning Algorithm” in
2019[IEEE].
[8] Sivanandhini P and Prakash J “Crop Yield Prediction Using Feed Forward and
Recurrent Neural Network ” in 2020[IJISRT].
[9] Mayank Chamapveri et.al “Crop Yield Prediction Using Machine Learning” in
2018[IEEE].
[10] Shriya Sahu et.al “An Efficient Analysis of Crop Yield Prediction using Hadoop
Framework Based on Random Forest Approach” in 2017[IEEE].
[11] Mummaleti Keertana et.al “An Ensemble Algorithm for Crop Yield Prediction” in
2021[IEEE].
[12] Ms Kavitha and Pratistha Mathur “Crop Yield Estimation in India Using Machine
Learning” in
2020[IEEE].
[13] P. S Vijay Bhaskar et.al “Crop Prediction using Predictive Analytics” in
2017[IEEE].
[14] Shruthi Kulkarni et.al “Predictive Analysis to improve Crop Yield using a Neural
Network Model” in 2018[IEEE].
[15] Ankitha H. Tidake et.al “Design Efficient Model to Increase Crop Yield
Prediction” in 2020[IEEE].
[16] Shivani S. Kale “A Machine learning approach to Predict Crop Yield Prediction
and Success Rate” in 2019[IEEE].
[17] Marcelo Chan Fu Wei et. al “Carrot Yield Mapping: A Precision Agriculture
Approach based on Machine Learning” in 2020[IEEE].
[18] S. Bhanumathi et.al “Crop Yield Prediction using Efficient Use of Fertilizers” in
2019[IEEE].
[19] Anna Chlingaryan et.al “Machine Learning Approaches for Crop Yield Prediction
and Nitrogen Status Estimation in Precision Agriculture” in 2018[IEEE].
[20] Venkata Prashanth Yanambaka “Crop yield prediction using Deep Neural
Network” in 2020[IEEE]

______________________________________________________________