AgroAI -Crop Prediction Using AI

🚀 Project Overview

This repository contains the project Crop Prediction Using AI, developed for JIS IDEAJAM by Asansol Engineering College. The project leverages AI and machine learning to help farmers predict crop yields and choose the best crops based on soil and weather conditions.

💡 Problem Statement

Global Issues:

• Food insecurity due to unpredictable crop yields.
• Economic disparities affecting small-scale farmers.

Challenges Faced:

• Unpredictable crop yields due to climate change.
• Impact of pests, soil degradation, and sudden weather changes.
• Financial losses and increased debt for farmers.

💡 Proposed Solution

The AI-driven platform offers:

• Crop Suggestions: Top 3 best crops based on soil reports and external conditions.
• Data Forecasting: Accurate predictions using machine learning models.
• Chatbot Support: Seamless interaction with a user-friendly chatbot.
• Multi-language Support: Options for farmers to choose their preferred language.

🛠️ Technologies Used

Frontend:

• HTML, CSS, JavaScript, React.js (Responsive UI)

Backend:

• Node.js, Express.js (API handling)

Machine Learning:

• Python (pandas, numpy, scikit-learn)

Database:

• MongoDB (Scalable data storage)

📊 Data Pipeline Workflow

1. Farmer Input: Location, crop type, land area, fertilizers, pesticides, and soil report.
2. Data Fetching: Real-time weather and temperature data via APIs.
3. Yield Prediction: ML models (Random Forest Regression & Classifier, 97.8% accuracy).
4. Dashboard Insights: Interactive results and recommendations.

🌟 Key Benefits

• Social: Enhances food security and educates farmers.
• Economic: Boosts agricultural output and attracts investments.
• Farmer-Centric: Reduces losses and improves resource management.
• Environmental: Promotes sustainable farming and climate resilience.

💰 Financial Feasibility

• Revenue Model: Free basic features with premium AI-driven insights.
• Scalability: Region-specific AI models for wider market expansion.
• Cost-Efficient: Uses scalable cloud solutions to minimize expenses.

🧩 Challenges Faced

• Data collection and preprocessing issues.
• Balancing model accuracy and computational efficiency.
• Promoting farmer awareness and trust in AI-based solutions.

📚 References

• Datasets:
  • Kaggle Crop Recommendation
  • Kaggle Indian Crop Yield
• Research:
  • MDPI Computer Research
  • Agriculture Journal - Crop Selection
• Documentation:
  • Express.js Middleware Guide
  • JavaScript W3Schools
  • MDN JavaScript Guide

---

🚀 Empowering Farmers with AI for Smarter Agriculture 🌾