Logo Lanfrica

Prasahant/Algerian-forest-fire-prediction

Domain:

environment and energy

Record type:

softwareproject
Creator:
Pra
Host:
This project is a Machine Learning web application that predicts the Fire Weather Index (FWI) based on meteorological and environmental conditions. # 🌲πŸ”₯ Algerian Forest Fire Prediction (FWI Predictor) ## πŸ“Œ Project Overview This project is a **Machine Learning web application** that predicts the **Fire Weather Index (FWI)** based on meteorological and environmental conditions. It helps estimate the likelihood and intensity of forest fires using real-world data from the Algerian Forest Fire dataset. The model is deployed as a **Flask web application** and hosted on **Render**, providing real-time predictions through a simple and interactive UI. --- ## 🎯 Objective The main objective of this project is to: - Predict forest fire risk using environmental parameters - Understand how weather conditions influence fire intensity - Build an end-to-end Machine Learning deployment pipeline --- ## 🧠 Machine Learning Approach - Algorithm Used: **Ridge Regression** - Dataset: **Algerian Forest Fire Dataset** - Steps involved: - Data Cleaning - Feature Engineering - Feature Scaling (StandardScaler) - Model Training - Model Evaluation - Deployment using Flask --- ## πŸ“Š Input Features The model takes the following inputs: - 🌑 Temperature - πŸ’§ Relative Humidity - 🌬 Wind Speed - 🌧 Rainfall - πŸ”₯ FFMC (Fine Fuel Moisture Code) - πŸ“ˆ DMC (Duff Moisture Code) - ⚑ ISI (Initial Spread Index) - 🏷 Classes (Fire / No-Fire condition) - 🌍 Region --- ## πŸš€ Live Demo πŸ‘‰ Deployed Application: alegerian-forest-fire-predi… --- ## 🧠 What I Learned in This Project Through this project, I gained hands-on experience in end-to-end Machine Learning development: ### πŸ“Œ Ridge Regression - Learned how Ridge Regression works by adding **L2 regularization** to reduce overfitting - Understood how it handles **multicollinearity** between features - Learned how tuning the **alpha parameter** affects model performance ### πŸ“Œ Regression Concepts - Difference between **Linear Regression vs Ridge Regression** - Importance of **bias-variance tradeoff** - How regression models predict continuous values like FWI ### πŸ“Œ Machine Lear …