🔥 Algerian Forest Fire Risk Analyzer

A Machine Learning web application built with Flask that predicts the Fire Weather Index (FWI) using meteorological conditions from two Algerian regions.

This project demonstrates an end-to-end Machine Learning workflow including data preprocessing, model training, model serialization, and deployment-ready web development.

---

🌐 Live Demo

Try the application here:

https://algerian-forest-fire-risk-analyzer.onrender.com

---

📌 Project Overview

The application predicts the Fire Weather Index (FWI) from weather measurements collected in:

• 📍 Bejaia
• 📍 Sidi-Bel Abbes

Users enter meteorological information through a simple web interface and the trained Linear Regression model predicts the expected Fire Weather Index.

The application also categorizes the predicted fire danger into different risk levels and provides a recommendation.

---

🚀 Features

• Predict Fire Weather Index (FWI)
• Supports two Algerian regions
• Linear Regression model
• StandardScaler preprocessing
• Flask backend
• Bootstrap-based frontend
• Risk level classification
• Fire safety recommendation

---

📊 Input Features

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)
• Region

---

🎯 Target Variable

• Fire Weather Index (FWI)

---

🧠 Machine Learning Workflow

1. Data Cleaning
2. Exploratory Data Analysis (EDA)
3. Correlation Analysis
4. Feature Selection
5. Train-Test Split
6. Feature Scaling using StandardScaler
7. Linear Regression Model Training
8. Model Evaluation
9. Model Serialization using Pickle
10. Flask Deployment

---

🛠 Technologies Used

• Python
• Flask
• Scikit-Learn
• Pandas
• NumPy
• HTML
• Bootstrap
• Pickle

---

📁 Project Structure

Algerian-Forest-Fire-Risk-Analyzer/

│

├── application.py

├── requirements.txt

├── README.md

├── .gitignore

│

├── models/

│ ├── linear_regression_model.pkl

│ └── standard_scaler.pkl

│

├── notebooks/

│ ├── ALGERIAN_LR.ipynb

│ └── Algerian_forest_fire_cleaned.csv

│

└── templates/

├── home.html

└── index.html

---

⚙️ Installation

Clone the repository

git clone https://github.com/YOUR_USERNAME/Algerian-Forest-Fire-Risk-Analyzer.git

Move into the project directory

cd Algerian-Forest-Fire-Risk-Analyzer

Create a virtual environment

python -m venv .venv

Activate the environment

Windows

.venv\Scripts\activate

Install dependencies

pip install -r requirements.txt

Run the application

python application.py

The application will be available at

http://127.0.0.1:5000

---

📈 Model

Algorithm:

Linear Regression

Preprocessing:

StandardScaler

Framework:

Flask

---

📷 Screenshots

(Add screenshots after deployment)

• Home Page
• Prediction Form
• Prediction Result

---

👨‍💻 Author

Pratham Singh

Machine Learning | Artificial Intelligence | Python Developer

---

📄 License

This project is intended for educational and portfolio purposes.