🌱 CultivaSense - Smart Crop Recommendation System

CultivaSense is a comprehensive AI-powered agricultural intelligence platform designed specifically for Indian agriculture. Using advanced machine learning algorithms and computer vision, it provides farmers with data-driven insights including crop recommendations, disease detection, and market price predictions to maximize yield and promote sustainable farming practices.

🎬 Demo Video

🎥 ▶ Watch the full demo on YouTube — See CultivaSense in action: Smart Farming Using AI & Machine Learning

✨ Features

🧠 Smart Crop Recommendation

95% Accuracy in crop recommendations using Random Forest Classifier
22 Different Crops analyzed and supported (Rice, Wheat, Maize, Cotton, and more)
Real-time soil condition analysis with 7 environmental parameters
Personalized suggestions based on NPK levels, pH, temperature, humidity, and rainfall
Instant comparison between your soil values and ideal conditions

🔬 Crop Disease Detection

Computer Vision-based disease identification from crop images
Supports 32 disease classes across major crops (Apple, Corn, Grape, Potato, Rice, Tomato, Wheat)
Instant diagnosis with confidence scores
Detailed treatment recommendations for each detected disease
Image upload with preview (supports JPG, PNG up to 5MB)
Covers diseases like:
- Rice: Brown Spot, Leaf Blast, Neck Blast
- Wheat: Brown Rust, Yellow Rust
- Tomato: Early Blight, Late Blight, Leaf Mold, Bacterial Spot, and more
- Potato, Corn, Apple, Grape diseases

💰 Market Price Prediction

AI-powered price forecasting using Random Forest Regressor
Predictions for 8 major crop categories (Rice, Wheat, Maize, Cotton, Sugarcane, Pulses, Vegetables, Fruits)
13 Indian states coverage (Maharashtra, Punjab, Haryana, UP, Bihar, and more)
Seasonal analysis with month-wise predictions
Weather-based market trend insights
Factors considered: Crop type, State, Month, Rainfall, Temperature

🧪 Comprehensive Soil Testing

NPK Analysis (Nitrogen, Phosphorus, Potassium)
pH Level monitoring and recommendations
Nutrient Deficiency detection with interactive recovery plans
Environmental factor analysis (temperature, humidity, rainfall)
Visual comparison charts (Your values vs Ideal values)

🌱 Interactive Recovery Solutions

Instant access to detailed recovery plans for each nutrient
Specific fertilizer recommendations with dosages
Application schedules and timing guidance
Separate plans for deficiency and excess conditions
Covers all parameters: N, P, K, pH, Temperature, Humidity, Rainfall

📊 Modern User Interface

Mobile-responsive design with glassmorphism effects
Dark mode optimized interface
Interactive animations and smooth transitions
Real-time validation with helpful error messages
Sample data loading for quick testing
Accessibility features with ARIA labels

💰 Financial Planning & ROI Calculator

Real-time ROI analysis for crop profitability planning
Input land area, expected yield, selling price, and cost breakdown
Calculates Total Investment, Revenue, Net Profit, and ROI %
Break-even yield analysis to understand minimum viable production
Risk assessment with color-coded indicators (Highly Profitable → High Risk)
Smart tips for improving profitability (cost optimization, scaling advice)
Supports per-acre cost breakdown: Seeds, Fertilizer, Labor, Miscellaneous

🤖 AI Agricultural Advisor

Powered by Google Gemini 2.0 Flash
Real-time interaction with a specialized agricultural AI
Personalized advice based on your local weather and soil conditions
Location-aware responses (using GPS coordinates)
Conversational interface for natural farming queries

🏗️ System Architecture

graph TB
    subgraph User Interface
        A["🌐 Web Browser"]
    end

    subgraph Flask Backend
        B["⚙️ Flask App (app.py)"]
    end

    subgraph ML Models
        C["🧠 Crop Recommendation<br/>Random Forest Classifier"]
        D["🔬 Disease Detection<br/>Computer Vision + CSV"]
        E["💰 Price Prediction<br/>Random Forest Regressor"]
    end

    subgraph External APIs
        F["🤖 Google Gemini API<br/>AI Chatbot"]
        G["🌤️ OpenWeather API<br/>Weather Data"]
    end

    subgraph Data Layer
        H["📊 Crop_recommendation.csv"]
        I["🦠 Crop_Disease.csv"]
        J["📈 market_price_data.csv"]
    end

    A -->|HTTP Requests| B
    B --> C
    B --> D
    B --> E
    B --> F
    B --> G
    C --> H
    D --> I
    E --> J

🚀 Quick Start

Prerequisites

Python 3.8 or higher
pip package manager
Modern web browser
(Optional) TensorFlow for disease detection model

Installation

Clone the repository

git clone https://github.com/dasouvik122005/Cultiva-Sense.git
cd Cultiva-Sense

Create virtual environment

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

Install dependencies
```
pip install -r requirements.txt
```
Set up environment variables
```
cp .env.example .env
# Edit .env file with your API keys
```
Required Keys:
- GEMINI_API_KEY: Get from Google AI Studio
- OPENWEATHER_API_KEY: Get from OpenWeatherMap
Run the application
```
python app.py
```
Open in browser Navigate to http://127.0.0.1:5000

🎯 Usage

1. Crop Recommendation

Navigate to the "Soil Analyzer" section
Enter soil nutrient values (N, P, K)
Input environmental conditions (temperature, humidity, pH, rainfall)
Click "Analyze Soil" for instant crop recommendations
View nutrient comparison and recovery plans

2. Disease Detection

Go to the "Crop Disease Detection" section
Upload a clear image of the affected crop (JPG/PNG, max 5MB)
Click "Detect Disease" for instant diagnosis
View disease name, confidence score, and treatment recommendations

3. Market Price Prediction

Navigate to "Market Price Prediction" section
Select crop type and state
Choose month and enter weather conditions
Click "Predict Price" for market forecasts
View predicted price and market trend analysis

4. Financial Planning & ROI

Scroll to the "Financial Planning & ROI" section
Enter your land area (acres), expected yield (kg/acre), and selling price (₹/kg)
Fill in per-acre costs: Seeds, Fertilizer, Labor, Other
Click "Calculate ROI" to see your full profitability analysis
Review Net Profit, ROI %, break-even yield, and smart tips

📁 Project Structure

Cultiva-Sense/
│
├── 📄 app.py                          # Main Flask application with all routes
├── 📄 config.py                       # Configuration management
├── 📄 setup.py                        # Project setup script
├── 📄 requirements.txt                # Python dependencies
├── 📄 .env.example                    # Environment variables template
│
├── 📊 Models & Data
│   ├── model.pkl                      # Trained crop recommendation model
│   ├── minmaxscaler.pkl               # Feature scaling model
│   ├── Crop_recommendation.csv        # Training dataset
│   ├── Crop_Disease.csv               # Disease detection database
│   ├── market_price_data.csv          # Market price historical data
│   └── models/
│       ├── plant_disease_model.h5     # CNN model for disease detection (optional)
│       ├── market_price_model.pkl     # Price prediction model
│       ├── price_scaler.pkl           # Price feature scaler
│       ├── disease_classes.json       # Disease class mappings
│       └── price_model_info.json      # Price model metadata
│
├── 📁 static/
│   ├── 🎨 style.css                   # Modern responsive styling
│   ├── ⚡ script.js                    # Interactive functionality
│   └── 🖼️ logo.png                    # Brand logo
│
├── 📁 templates/
│   └── 🌐 index.html                  # Main web interface
│
├── 📁 uploads/                        # Temporary storage for uploaded images
│
├── 🛠️ Utilities
│   ├── generate_disease_data.py       # Generate disease dataset
│   ├── generate_market_price_data.py  # Generate price dataset
│
├── 📓 Crop Classification...ipynb      # Jupyter notebook for model training
├── 📄 CONTRIBUTING.md                  # Contribution guidelines
├── 📄 CODE_OF_CONDUCT.md               # Code of conduct
├── 📄 SECURITY.md                      # Security policy
└── 📄 README.md                        # Project documentation

🛠️ Technology Stack

Backend

Flask 2.3.3 - Lightweight web framework
Python 3.8+ - Core programming language
Scikit-learn 1.3.0 - Machine learning library
Pandas 2.0.3 - Data manipulation and analysis
NumPy 1.24.3 - Numerical computing
Pillow - Image processing for disease detection
h5py - HDF5 file handling
Google Gemini API - AI-powered conversational advisor
Gunicorn - Production WSGI server

Frontend

HTML5 - Modern semantic markup
CSS3 - Responsive design with glassmorphism effects
JavaScript (Vanilla) - Interactive user experience
Responsive Design - Mobile-first approach
Accessibility - ARIA labels and semantic HTML

Machine Learning

Random Forest Classifier - Crop recommendation (95% accuracy)
Random Forest Regressor - Market price prediction
Computer Vision - Image-based disease detection
Min-Max Scaling - Feature normalization
Cross-validation - Model performance optimization

Optional

TensorFlow/Keras - Deep learning for advanced disease detection
CNN (Convolutional Neural Network) - Image classification

🌾 Supported Crops

CultivaSense provides recommendations for 22 major Indian crops:

🌾 Cereals: Rice, Wheat, Maize, Barley
🫘 Legumes: Chickpea, Kidney Beans, Pigeon Peas, Moth Beans, Mung Bean, Black Gram, Lentil
🥥 Plantation: Coconut, Coffee
🍎 Fruits: Apple, Banana, Grapes, Orange, Papaya, Pomegranate, Watermelon, Muskmelon
🌱 Cash Crops: Cotton, Jute

📊 Model Performance

Crop Recommendation System

Accuracy: 95%+ on validation dataset
Training Data: 2,200+ soil samples
Features: 7 soil and environmental parameters (N, P, K, Temperature, Humidity, pH, Rainfall)
Algorithm: Random Forest Classifier
Validation: K-fold cross-validation
Optimization: Grid search hyperparameter tuning

Disease Detection System

Disease Classes: 32 different diseases
Supported Crops: 7 major crops (Apple, Corn, Grape, Potato, Rice, Tomato, Wheat)
Detection Method: Computer Vision + CSV-based matching
Image Support: JPG, PNG (up to 5MB)
Features: Color analysis, affected area detection
Treatment Database: Comprehensive recommendations for each disease

Market Price Prediction

Crop Categories: 8 major categories
Geographic Coverage: 13 Indian states
Algorithm: Random Forest Regressor
Features: Crop ID, State ID, Month, Rainfall, Temperature
Feature Importance: Crop type (78.8%), Temperature (7.3%), Month (5.2%), Rainfall (5.3%), State (3.4%)
Seasonal Analysis: Month-wise trend predictions
Market Insights: Weather-based trend analysis

🌍 Environmental Impact

Sustainable Agriculture Goals:

🌿 Promote eco-friendly farming practices
💧 Optimize water usage through smart recommendations
🌱 Reduce chemical fertilizer dependency
📈 Increase crop yield efficiency
🌾 Support biodiversity in agricultural systems

📱 Mobile Responsiveness

CultivaSense is designed with a mobile-first approach:

✅ Fully Responsive - Works on all screen sizes
✅ Touch-Friendly - Optimized for mobile interactions
✅ Fast Loading - Optimized performance
✅ Progressive Web App - App-like experience

🤝 Contributing

We welcome contributions to make CultivaSense even better!

Please read our Contribution Guidelines and Code of Conduct before contributing.

How to Contribute:

Fork the repository
Create feature branch (git checkout -b feature/amazing-feature)
Commit changes (git commit -m 'Add amazing feature')
Push to branch (git push origin feature/amazing-feature)
Open Pull Request

Areas for Contribution:

🌾 Additional crop support
🧠 Model accuracy improvements
🎨 UI/UX enhancements
🌍 Localization support
📱 Mobile app development

🔐 Security

For security concerns, please review our Security Policy.

🙏 Acknowledgments

Indian Agricultural Research Institute - Dataset and domain expertise
Scikit-learn Community - Machine learning framework
Flask Team - Web framework development
Agricultural Experts - Domain knowledge and validation

🔮 Future Roadmap

Version 2.0 - Planned Features:

🛰️ Satellite Imagery - Remote sensing capabilities for field analysis
📊 Advanced Analytics Dashboard - Historical tracking and trend analysis
🌍 Multi-language Support - Hindi, Tamil, Telugu, Bengali, and other regional languages
📱 Progressive Web App - Offline capability and app-like experience
💾 User Accounts - Save predictions and track farming history
📧 Email Reports - Automated PDF reports via email

Version 3.0 - Vision:

🌾 Advanced Disease Detection - Deep learning CNN model with 98%+ accuracy
🎯 Precision Farming - GPS-guided field-specific recommendations
📡 IoT Integration - Smart sensor connectivity for real-time monitoring
📈 Yield Prediction - AI-powered harvest forecasting
🌐 Community Platform - Farmer forums and knowledge sharing
🏪 Marketplace Integration - Direct buyer-seller connections
📱 Native Mobile Apps - iOS and Android applications

✅ Recently Implemented (Current Version):

✅ Crop Disease Detection with 32 disease classes
✅ Market Price Prediction for 8 crop categories across 13 states
✅ Interactive Recovery Plans for all soil parameters
✅ Mobile-responsive modern UI with glassmorphism design
✅ Computer Vision-based disease analysis
✅ Seasonal market trend analysis
✅ Weather API Integration (OpenWeatherMap)
✅ AI Chatbot powered by Google Gemini 2.0 Flash
✅ Financial Planning & ROI Calculator with profitability analysis

📈 Statistics

⭐ 95% Model Accuracy (Crop Recommendation)
🌾 22 Supported Crops
🔬 32 Disease Classes Detected
💰 8 Crop Categories for Price Prediction
🗺️ 13 Indian States Coverage
📊 2,200+ Training Samples
🇮🇳 Pan-India Coverage
📱 100% Mobile Responsive

👥 Team

Name	GitHub
Souvik Das	@dasouvik122005
Soaham Behera	@SoahamBehera
Surajit Das	@surajitdas-gif
Nandini Verma	@nandiniverma29

🌱 Empowering Indian Agriculture with AI 🤖

Built with ❤️ for sustainable farming and food security

Five Powerful Features:
🧠 Crop Recommendation | 🔬 Disease Detection | 💰 Price Prediction | 📊 ROI Calculator | 🤖 AI Advisor

📧 Contact: dasouvik122005@gmail.com

Name		Name	Last commit message	Last commit date
.github		.github
models		models
static		static
templates		templates
uploads		uploads
.env.example		.env.example
.gitignore		.gitignore
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
Crop Classification With Recommendation System.ipynb		Crop Classification With Recommendation System.ipynb
Crop_Disease.csv		Crop_Disease.csv
Crop_recommendation.csv		Crop_recommendation.csv
LICENSE		LICENSE
README.md		README.md
SECURITY.md		SECURITY.md
app.py		app.py
config.py		config.py
generate_disease_data.py		generate_disease_data.py
generate_market_price_data.py		generate_market_price_data.py
market_price_data.csv		market_price_data.csv
minmaxscaler.pkl		minmaxscaler.pkl
model.pkl		model.pkl
requirements.txt		requirements.txt
setup.py		setup.py

Latest commit

History

Folders and files

Repository files navigation