abinash-ml/algerian_forest_fire_predictor

# 🌲 Algerian Forest Fire Predictor A machine learning application to predict the Fire Weather Index (FWI) in Algerian forests based on environmental and meteorological data. ## 📌 Project Overview The Algerian Forest Fire Predictor is a web-based system that uses machine learning to assess the likelihood of forest fires. By analyzing environmental and weather parameters, the model helps support early detection and mitigation strategies for forest fire management in Algeria. **Live Demo:** algerian-forest-fire-predic… ## 🔍 Features - Predicts the Fire Weather Index (FWI) using multiple environmental variables - Uses ElasticNetCV model with high accuracy (R² Score: 0.98) - Responsive web interface for easy access on multiple devices - Input validation and data preprocessing - Detailed results with prediction confidence ## 🛠️ Tech Stack - **Machine Learning:** Python, scikit-learn, ElasticNetCV - **Backend:** Flask - **Frontend:** HTML, CSS, JavaScript - **Deployment:** Render ## 📊 Model Details The system predicts the Fire Weather Index (FWI) from the following parameters: | Parameter | Description | Range | |-----------|-------------|-------| | RH | Relative Humidity | 21% to 90% | | WS | Wind Speed | 6 to 29 km/h | | Rain | Total day in mm | 0 to 16.8 mm | | FFMC | Fine Fuel Moisture Code | 28.6 to 92.5 | | DMC | Duff Moisture Code | 1.1 to 65.9 | | ISI | Initial Spread Index | 0 to 18.5 | | Classes | Fire (1) or Not Fire (0) | Binary | | Region | Bejaia region (0) or Sidi Bel Abbes region (1) | Binary | ### Model Performance - **Model Type:** ElasticNetCV (with L1 and L2 regularization) - **Mean Absolute Error:** 0.658 - **R² Score:** 0.981 ## 🚀 Installation & Local Setup 1. Clone the repository: ```bash git clone github.com cd algerian_forest_fire_predictor ``` 2. Create a virtual environment and activate it: ```bash python -m venv venv source venv/bin/activate # On …