Project Overview:

The AI-Powered Smart Farming System is a web-based IoT and Machine Learning solution designed to monitor and optimize crop health, irrigation, and environmental conditions in real-time. The system collects data such as soil moisture, temperature, humidity, and optionally leaf images, then applies AI/ML algorithms to predict crop diseases, watering schedules, or fertilizer needs.

This project promotes precision agriculture by helping farmers make data-driven decisions, reduce water usage, increase yield, and detect issues early.

Technologies Used:

Hardware:

• Microcontroller: ESP32 / Arduino Uno / Raspberry Pi

• Sensors:

  • DHT11/DHT22 – Temperature and humidity sensor

  • Soil Moisture Sensor

  • Light Sensor (optional)

  • Camera (optional for disease detection using leaf images)

Frontend:

• HTML, CSS, Bootstrap

• JavaScript (Chart.js for graphs, Leaflet.js for maps if needed)

Backend:

• Option 1: PHP with MySQL

• Option 2: Node.js with MongoDB

• Option 3: Java Spring Boot with PostgreSQL

AI/ML:

• Python (scikit-learn / TensorFlow)

• Algorithms:

  • Regression model for irrigation prediction

  • CNN model for crop disease detection (if using leaf images)

  • K-Means or Decision Tree for fertilizer recommendation

System Architecture:

1. Sensors collect environmental data from the farm.

2. Data is sent from IoT microcontroller to the backend server.

3. Database stores all readings and predictions.

4. The ML model processes the data:

   • Predicts whether irrigation is needed

   • Detects early signs of crop disease (if camera used)

   • Recommends fertilizer based on soil moisture and temperature

5. Web dashboard shows:

   • Real-time sensor data

   • Predictive insights (water/crop/disease status)

   • Historical trends and graphs

6. Sends alerts to farmers (SMS/email/notification) when crops need watering or disease risk is detected.