Smart Farming IoT Recommendation System
Built an agricultural decision support system integrating IoT sensors, AI models, and web application. ESP32 collects soil condition data (moisture, pH, NPK) stored in MongoDB, processed by AI models to generate crop recommendations based on environmental factors and market prices. Results displayed through Streamlit dashboard.
Technologies Used
Project Overview
This project develops a smart farming system that integrates IoT sensors, AI models, and web applications for optimal crop recommendations based on real-time soil conditions and market price analysis. The system helps farmers make data-driven planting decisions for more efficient and sustainable agriculture.
Key Features
Real-Time Soil Monitoring: ESP32 sensors collect soil condition data including moisture, pH, and NPK levels continuously.
AI-Based Crop Recommendation: Machine learning models process environmental data and market prices to generate optimal crop recommendations.
Centralized Data Storage: MongoDB stores all sensor data and processing results in a scalable NoSQL database.
Interactive Web Dashboard: Streamlit-based dashboard displays sensor data and crop recommendations in visual format.
Market-Aware Decision Making: System considers both soil conditions and market prices for economically viable recommendations.
System Flow
Sensors monitor soil conditions and transmit data via ESP32.
Data is received and processed by AI model.
System compares soil conditions with AI predictions and market price data.
Best crop recommendations are generated.
Results are displayed on Streamlit-based website.
Project Outcome
✓ End-to-end agricultural recommendation system integrating IoT, AI, and web application