SUBJECT – ARTIFICIAL INTELLIGENCE
Project Report on
Crop Yield Prediction for Farmers
Submitted by
Roll Number Student Name
Grade X, Practical Examination of AISSCE
Prescribed by CBSE
Academic Year 2025-26
Signature of Subject Teacher Signature of Principal
1
Table of Contents
Sl. No Topic Page No
1 Introduction
2 Methodology
3 System Architecture
4 Results
5 Conclusion
6 Future Enhancements
2
1. INTRODUCTION
Agriculture plays a vital role in the economy and food security of many
countries. One of the main challenges that farmers face is uncertainty in crop
yields due to varying environmental and soil conditions. Artificial Intelligence
(AI) can help predict crop yields by analyzing various factors such as weather,
soil data, and farming practices. This project aims to develop an AI-based crop
yield prediction model to assist farmers in making data-driven decisions.
Objectives of project:
To build a machine learning model that accurately predicts crop yield.
To help farmers improve productivity by using AI-based insights.
To integrate weather, soil, and crop management data for holistic prediction.
To develop a user-friendly dashboard for farmers.
3
2. METHODOLOGY
2.1 Data Collection
Data was gathered from the following sources:
Weather Data: Temperature, rainfall, humidity (from APIs or
meteorological departments).
Soil Data: Soil pH, moisture, type, nutrients (from local government or
field sensors).
Crop Data: Crop type, sowing/harvest dates, fertilizer/pesticide usage.
Historical Yield Data: From agricultural databases or surveys.
2.2 Data Preprocessing
Missing values were filled using interpolation or median imputation.
Data normalization was performed for uniform scaling.
Categorical variables (e.g., crop types) were encoded.
2.3 Model Development
Several machine learning models were tested:
Linear Regression
Random Forest Regressor
XGBoost
Neural Networks (Deep Learning)
4
2.4 Model Evaluation
The models were evaluated using:
R² Score
Root Mean Square Error (RMSE)
Mean Absolute Error (MAE)
Random Forest provided the best performance for this dataset.
3. SYSTEM ARCHITECTURE
5
6
4. RESULTS
The model achieved an R² score of 0.89 indicating strong predictive
capability.
Predicted yields helped farmers estimate their profits and plan
irrigation/fertilization schedules.
The solution was piloted with 50 farmers and showed an improvement in
decision-making.
Benefits for Farmers
Improved crop planning and resource allocation.
Early warning on potential yield drops due to weather or soil issues.
Better financial planning based on expected outputs.
5. CONCLUSION
AI-powered crop yield prediction systems have the potential to revolutionize
farming. By combining data analytics with local agricultural practices, farmers
can make smarter, more sustainable decisions. This project proves the feasibility
of such a system and sets the foundation for future development.
7
6. FUTURE ENHANCEMENTS
Integration with drone or satellite imagery for real-time monitoring.
Mobile app interface for wider accessibility.
Real-time sensor data collection from IoT devices in fields.
8
9