krotov22/Algerian-Forest_Fire_Prediction

# 🔥 Algerian Forest Fire Prediction (End-to-End ML Project with Flask Deployment) ## 🚀 Project Overview Forest fires are heavily influenced by environmental factors such as temperature, humidity, wind speed, and rainfall. This project builds a **machine learning model to predict the Forest Fire Weather Index (FWI)** using meteorological data. The workflow includes **data preprocessing, exploratory data analysis (EDA), feature engineering, model training, and deployment using Flask**. A **web application interface** allows users to enter environmental parameters and instantly receive predictions from the trained model. ## 📊 Dataset The project uses the **Algerian Forest Fires Dataset**, which contains meteorological and environmental data collected from two regions of Algeria. Dataset information: - Total Records: **244** - Regions: **Bejaia and Sidi Bel-Abbes** - Time Period: **June – September 2012** Features include: - Temperature - Relative Humidity - Wind Speed - Rain - FFMC - DMC - ISI 🔗 Dataset Link Algerian Forest Fires Datas… ## 🤖 Machine Learning Workflow 1. **Data Cleaning** - Removed unnecessary columns - Handled missing values 2. **Exploratory Data Analysis (EDA)** - Visualized relationships between weather variables and fire risk - Identified important features affecting forest fires 3. **Feature Engineering** - Selected relevant features - Applied **StandardScaler** for feature scaling 4. **Model Training** - Trained multiple regression models - Selected **Ridge Regression** for better generalization 5. **Model Deployment** - Saved the trained model using **pickle** - Integrated the model into a **Flask web application** ## 🌐 Web Application The Flask web application allows users to input environmental parameters and receive predictions. User inputs include: - Temperature - Relative Humidity - Wind Speed - Rain - FFMC - DMC - ISI The system processes the input data, scales it using …