Abhinav-frfr/Algerian_Forest_Model

# Algerian Forest Model This project aims to predict the Fire Weather Index (FWI) using meteorological and fire-related attributes from the Algerian Forest Fires Dataset. The Fire Weather Index is a crucial indicator used to assess fire risk and intensity, helping in early warning and prevention planning. A Ridge Regression model is trained after comprehensive data preprocessing and feature scaling to ensure numerical stability and reduce overfitting. The complete machine learning pipeline is deployed as a Flask web application, enabling users to interactively input environmental parameters and receive real-time FWI predictions. 📌 Problem Statement Forest fires pose a serious threat to ecosystems, human life, and property. Accurate prediction of fire risk based on weather and environmental conditions can significantly aid in disaster prevention and management. This project addresses the challenge by leveraging machine learning to model the relationship between climate variables and fire severity. 🧪 Dataset Source: Algerian Forest Fires Dataset Regions: Bejaia & Sidi Bel-Abbes Features Used: Temperature Relative Humidity (RH) Wind Speed (Ws) Rain FFMC (Fine Fuel Moisture Code) DMC (Duff Moisture Code) ISI (Initial Spread Index) Region Code Fire Class (Encoded) ⚙️ Machine Learning Pipeline Data Cleaning & Preparation Handling missing values Encoding categorical features Feature Scaling Standardization using StandardScaler Model Training Ridge Regression for regularized linear prediction Model Evaluation Performance measured using regression metrics Model Serialization Trained model and scaler saved using pickle Deployment Flask-based web application for inference 🌐 Web Application The Flask web interface allows users to: Enter real-time meteorological values Submit data via an HTML form View predicted Fire Weather Index (FWI) instantl …