rajat-relkar/Forest-Fire-ML-Project

This project predicts the Fire Weather Index (FWI), a numerical indicator of fire risk using meteorological and environmental parameters from the Algerian Forest Fires Dataset. # Algerian Forest Fire Weather Index Prediction ## Overview This project predicts the **Fire Weather Index (FWI)** — a numerical indicator of fire risk — using meteorological and environmental parameters from the **Algerian Forest Fires Dataset**. The project includes: - **Exploratory Data Analysis (EDA) and Feature Engineering** - **Model Training and Evaluation** - A **Flask Web Application** for live predictions - Deployment on **AWS Elastic Beanstalk** --- ## Dataset **Dataset name:** Algerian Forest Fires Dataset **Source:** UCI Machine Learning Repository The dataset includes **244 samples** collected from two Algerian regions — **Bejaia** and **Sidi Bel-Abbès** — between **June and September 2012**. | Feature | Description | |----------|--------------| | Temp | 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 | Buildup Index | | FWI | Fire Weather Index (Target Variable) | --- ## Project Workflow ### 1. **Data Preprocessing and EDA** - Cleaned missing and inconsistent data - Merged regional datasets - Encoded categorical features - Visualized correlations using heatmaps and pairplots - Removed multicollinear features ### 2. **Model Training** - Split data: 75% training / 25% testing - Applied scaling and normalization - Trained multiple regression models (e.g., Linear Regression, Random Forest, Ridge, Lasso) - Evaluated using metrics: **R², MAE, RMSE** ### 3. **Model Selection and Serialization** - Chose the best model (highest R² on test data) - Serialized model using `pickle` for Flask integration ### 4. **Flask Web App** - Flask web interface to input weather parameters - Model predicts **FWI value** - Displays result dynamically on the same page --- ## Tech Stack | Component | Technology | |------------|-------------| | Language | Python 3.x | | Framework | Flask | | Da …