README.md

metadata

title: Crop Recommendation System
emoji: 🌾
colorFrom: green
colorTo: yellow
sdk: docker
app_file: app.py
pinned: false
license: mit

🌾 Smart Farming: Crop Recommendation System for Popular Indian Crops

🔬 A Machine Learning-based Web Application to Recommend Suitable Crops Based on Environmental Conditions
👨‍🌾 Built by Saksham Pathak | IIIT Lucknow | 94.3% Accuracy | Deployed using Flask

---

📌 Overview

Smart Farming is a crop recommendation system that leverages machine learning to assist Indian farmers in selecting the most suitable crop for cultivation based on key environmental parameters. The system uses a Random Forest Classifier trained on soil and climatic data to suggest the best crop from a set of 22 popular Indian crops.

🌱 This project empowers sustainable agriculture, efficient resource utilization, and smarter farming decisions through AI.

---

🧠 Key Features

• ✅ ML-Powered Predictions (94.3% Accuracy)
• 🧪 Inputs: Nitrogen, Phosphorus, Potassium, Temperature, Humidity, pH, Rainfall
• 🌾 Outputs: Rice, Maize, Banana, Cotton, Sugarcane, etc.
• 📊 Model Used: Random Forest Classifier
• 🌐 Flask-based Web App with real-time crop suggestions
• 🎨 Clean and responsive UI (HTML + CSS + JS)

---

🚀 Live Demo

🔒 Link coming soon or hosted locally

---

🖥️ Tech Stack

Component	Technology
👨‍💻 Language	Python, HTML, CSS, JS
🔍 ML Model	Random Forest Classifier
⚙️ Backend	Flask (Python)
🖼 Frontend	HTML + CSS + JavaScript
📦 Deployment	Pickle Model Serialization

---

📂 Project Structure

📁 crop-recommendation
├── 📁 static/
│   └── images
├── 📁 templates/
│   └── index.html
├── 📄 app.py             # Flask backend
├── 📄 crop\minmaxscaler.pkl,standscaler.pkl    # Trained ML model
├── 📄 requirements.txt
├── 📄 Dockerfile
└── 📄 README.md

---

📊 Model Performance

Model	Accuracy	Precision	Recall	F1-Score
🌟 Random Forest	94.3%	92.7%	91.5%	92.1%
Gradient Boosting	92.1%	90.5%	89.3%	89.9%
XGBoost	91.4%	88.9%	87.5%	88.2%
SVM	85.7%	83.2%	81.6%	82.4%

📌 Key Factors Influencing Prediction:

• Rainfall
• Soil pH
• Temperature
• NPK (Nitrogen, Phosphorus, Potassium)

---

📥 How to Run Locally

1️⃣ Clone the Repository

git clone https://github.com/parthmax2/crop-recommendation-system.git
cd crop-recommendation-system

2️⃣ Install Dependencies

pip install -r requirements.txt

3️⃣ Run the Flask App

python app.py

4️⃣ Open in Browser

Visit http://localhost:5000/ to use the web app.

---

📈 Future Enhancements

• 🌤 Real-time Weather API Integration
• 📡 IoT-based Soil Sensor Integration
• 🐛 Pest & Disease Prediction Module
• 🌍 Satellite/GIS data for advanced insights
• 🌐 Multilingual and Offline Support

---

✍️ Author

Saksham Pathak M.Sc. AI & ML, IIIT Lucknow 🔗 GitHub | LinkedIn

---

📄 License

This project is licensed under the MIT License – see the LICENSE file for details.

---

📚 References

• IEEE Paper 1
• Crop Dataset - Kaggle
• Full list of academic references is included in the paper.pdf.

---

🌱 "Empowering farmers through AI-driven decisions for a greener tomorrow."