priyanshu94230-dot/algerian-forest-fire-fwi-prediction

Machine learning web application for predicting Forest Fire Weather Index (FWI) using Algerian forest fire data and a Ridge Regression model. 🔥 Algerian Forest Fire FWI Prediction A Machine Learning web application that predicts the *Fire Weather Index (FWI)* using meteorological and fire-weather data from the Algerian Forest Fires dataset. The project uses *Ridge Regression* for prediction and *StandardScaler* for feature preprocessing. A *Flask* web application provides a simple interface where users can enter the required values and get an FWI prediction. ## 🚀 Features - Machine Learning based FWI prediction - Ridge Regression model - Feature scaling using StandardScaler - Flask web application - Simple HTML user interface - Real-time prediction through a web form - Trained model saved using Pickle ## 🛠️ Technologies Used - Python - Flask - NumPy - Pandas - Scikit-learn - HTML/CSS - Pickle ## 📊 Dataset This project is based on the *Algerian Forest Fires Dataset*. The model uses the following features: - Temperature - Relative Humidity (RH) - Wind Speed (Ws) - Rain - Fine Fuel Moisture Code (FFMC) - Duff Moisture Code (DMC) - Drought Code (DC) - Initial Spread Index (ISI) - Buildup Index (BUI) - Classes - Region The target variable is: *FWI (Fire Weather Index)* ## 🤖 Machine Learning Model The project uses *Ridge Regression* to predict the Fire Weather Index. Before prediction, the input features are transformed using *StandardScaler*, using the same preprocessing approach used during model training. The trained files are: - ridge.pkl — trained Ridge Regression model - scaler.pkl — trained StandardScaler ## 📁 Project Structure ```text algerian-forest-fire-fwi-prediction/ │ ├── templates/ │ └── index.html │ ├── app.py ├── ridge.pkl ├── scaler.pkl ├── requirements.txt └── README.md