AravChandra/ALGERIAN-FOREST-FIRES

# 🔥 Forest Fire Prediction using Machine Learning > Predicting wildfire risk through data-driven insights and machine learning. --- ## 🌍 Project Overview Wildfires are among the most destructive natural disasters, threatening ecosystems, wildlife, human lives, and infrastructure. In this project, I built a complete **Machine Learning pipeline** to analyze the **Algerian Forest Fires Dataset** and predict the **Fire Weather Index (FWI)** — a key metric used to assess wildfire danger levels. From raw data preprocessing to model comparison and performance evaluation, this project demonstrates a practical application of Machine Learning in solving real-world environmental challenges. --- ## 🎯 Objectives This project aims to: ✅ Analyze wildfire-related weather patterns ✅ Identify the most influential fire risk factors ✅ Build predictive models for Fire Weather Index (FWI) ✅ Compare multiple regression algorithms ✅ Evaluate model performance using industry-standard metrics ✅ Create a scalable workflow for future wildfire prediction systems --- ## 📊 Dataset Information The dataset contains meteorological observations and fire-related measurements collected from two regions of Algeria. ### Features Used | Feature | Description | |----------|-------------| | Temperature | Air Temperature (°C) | | RH | Relative Humidity (%) | | Ws | Wind Speed (km/h) | | Rain | Rainfall (mm) | | FFMC | Fine Fuel Moisture Code | | DMC | Duff Moisture Code | | DC | Drought Code | | ISI | Initial Spread Index | | BUI | Build-Up Index | | Classes | Fire / Not Fire | | Region | Geographic Region | | FWI | Fire Weather Index (Target Variable) | --- # ⚙️ Machine Learning Pipeline ## 1️⃣ Data Preprocessing Raw data rarely arrives in a model-ready format. The preprocessing stage included: - Handling missing values - Data cleaning and validation - Data type conversion - Feature engineering - Encoding categorical variables - Preparing training-ready datasets --- ## 2️⃣ …