ak-pydev/ForestFirePrediction

Prediction of forest fire occurrence based on ridge regression on Algerian Regions "Bejaia" and "Sidi Bel Abbes"" # 🔥 Forest Fire Prediction System **A machine learning web application for predicting forest fire occurrence in Algeria using environmental factors** Demo • Features • Installation • Usage • API • Contributing ## 📋 Overview This project implements a machine learning-powered web application that predicts forest fire occurrence in two Algerian regions: **Bejaia** (northeast) and **Sidi Bel-abbes** (northwest). The system uses a Ridge Regression model trained on environmental and meteorological data to provide real-time fire risk assessments. ### 🎯 Key Features - **Real-time Predictions**: Web interface for instant fire risk assessment - **Scientific Accuracy**: Based on Fire Weather Index (FWI) system components - **Regional Coverage**: Supports both Bejaia and Sidi Bel-abbes regions - **Responsive Design**: Modern, mobile-friendly web interface - **Dockerized Deployment**: Easy containerized deployment - **REST API**: Programmatic access to predictions ## 🔬 Dataset Information The model is trained on the **Algerian Forest Fires Dataset** containing: - **244 instances** across two Algerian regions - **122 instances per region** (Bejaia and Sidi Bel-abbes) - **Data period**: June 2012 to September 2012 - **Classification**: Fire (138 instances) vs No Fire (106 instances) ### Input Features | Feature | Description | Range | | --------------- | -------------------------------- | --------- | | **Temperature** | Maximum daily temperature (°C) | 22-42 | | **RH** | Relative Humidity (%) | 21-90 | | **Ws** | Wind Speed (km/h) | 6-29 | | **Rain** | Daily rainfall (mm) | 0-16.8 | | **FFMC** | Fine Fuel Moisture Code | 28.6-92.5 | | **DMC** | Duff Moisture Code | 1.1-65.9 | | **ISI** | Initial Spread Index | 0-18.5 | | **Classes** | Fire vs No Fire classification | Binary | | …