Overview • Key Features • Tech Stack • Architecture • Demo • Installation • Usage •
KrishiDhaara is a comprehensive smart agriculture platform built to empower farmers with cutting-edge technology. By seamlessly integrating IoT sensors, AI-powered analytics, and intelligent automation, KrishiDhaara transforms traditional farming practices into precise, data-driven operations that improve crop yields, conserve resources, and detect problems before they affect harvests.
Our platform bridges the technology gap in agriculture, making sophisticated tools accessible to farmers of all scales through an intuitive interface available in both English and Hindi. KrishiDhaara addresses the key challenges farmers face daily: irrigation management, disease detection, weather uncertainties, and resource optimization.
- Real-time soil moisture monitoring with precise sensor data visualization
- Automated irrigation scheduling based on soil conditions and weather forecasts
- Water consumption analytics with filterable date ranges and usage patterns
- Anomaly detection for identifying leaks and system malfunctions
- Interactive irrigation history with detailed session logs (duration, volume, timestamps)
- Disease identification with 99.09% accuracy using ResNet50 model
- Fast API with Hugging Face integration for seamless processing
- Early detection alerts before diseases spread throughout crops
- Treatment recommendations with severity assessment
- Historical tracking of disease occurrences and treatments
- GPS-accurate field visualization with custom boundary definition
- Sensor positioning and management throughout mapped fields
- Real-time sensor status indicators directly on field map
- Map/satellite view switching for comprehensive field visualization
- React-Leaflet integration for high-precision mapping
- Mobile-friendly interface for in-field use and adjustments
- Open weather API integration for localized forecasting
- 7-day detailed forecasts with hourly predictions
- Wind speed and precipitation data for farming operations planning
- Weather-based irrigation adjustments to optimize water usage
- Historical weather pattern analysis for seasonal planning
- GROQ API integration for natural language understanding
- Farming-specific context for relevant advice and information
- AI hallucination detection with expert review suggestions
- Multi-language support (English and Hindi)
- Query routing to specialized knowledge domains (irrigation, diseases, weather)
- Centralized overview of all farm operations and sensor data
- Multi-timeframe visualization (daily, monthly, yearly views)
- Sensor performance monitoring and maintenance alerts
- Customizable reports for complete farm analysis
- Responsive design for desktop and mobile access
- Real-time AI-powered notifications for unusual patterns
- LSTM model implementation for predictive analysis
- Configurable alert thresholds with on/off toggles
- Historical anomaly tracking for pattern recognition
- AI-trained model for optimal crop selection
- Soil-specific recommendations based on sensor data
- Seasonal planting advice integrated with weather forecasts
- Yield prediction based on historical data and conditions
- Krishi Jagran integration via web scraping using cheerio
- Categorized agricultural news with custom filtering
- Featured articles highlighting important developments
- Pagination system for easy content browsing
- Hindi <-> English translation throughout the entire platform
- Report generation for comprehensive farm analysis
- Responsive design for all devices and screen sizes
KrishiDhaara System Architecture Diagram (Click to expand)
KrishiDhaara follows a modular microservices architecture consisting of five key components:
- Web Client: React-based responsive dashboard that provides visualization, control center, and user management
- Mobile App: Kotlin-based Android application that enables on-field monitoring, control, and disease detection
- IoT Server: Python-based middleware that handles sensor communications, data processing, and automation
- AI Server: Specialized service for disease detection, anomaly detection, and intelligent data analysis
- Backend Server: Core application logic, database management, and API gateway services
This architecture ensures scalability, maintainability, and fault tolerance across the platform.
Click the image to watch our comprehensive demonstration video
- Node.js (v14+)
- Python (v3.8+)
- MongoDB
- Android Studio (for mobile app)
- IoT sensors (see hardware specifications in docs)
git clone https://github.com/yourusername/KrishiDhaara.git
cd KrishiDhaaracd client
npm install
npm run devcd server
npm install
cp .env.example .env # Configure your environment variables
npm startcd IoT_Server
pip install -r requirements.txt
python index.pycd AI_Server/diseaseDetectionServer
pip install -r requirements.txt
python app.pycd mobileApp
# Open in Android Studio and build the project-
Initial Configuration:
- Set up your farm's geographical details
- Connect and position IoT sensors
- Define crop types and field boundaries
-
Daily Monitoring:
- Check dashboard for real-time soil moisture, temperature, and other sensor readings
- Review weather forecasts for upcoming farming operations
- Monitor anomaly notifications for potential issues
-
Disease Detection:
- Upload plant images through web or mobile app
- Review AI analysis results for disease identification
- Implement recommended treatments if issues are detected
-
Irrigation Management:
- Monitor soil moisture levels across fields
- Adjust automated irrigation schedules or trigger manual irrigation
- Analyze water usage patterns to optimize consumption
-
Insights & Planning:
- Generate custom reports for farm operations
- Use crop recommendation system for planting decisions
- Leverage chatbot for farming advice and troubleshooting
- Firebase for real-time database capabilities
- Groq for AI language processing
- React for the web frontend framework
- Jetpack Compose for modern Android UI
- OpenWeather for weather data integration
- Krishi Jagran for agricultural news content
- TensorFlow and PyTorch for AI model training