MohammadMaaz6229/Algeria-Forest-Fire-Prediction-using-Machine-Learning

machine-learning data-science python scikit-learn exploratory-data-analysis eda forest-fire regression jupyter-notebook data-analysis To run flask application ``` python app.py ``` ======= # 🌲 Algeria Forest Fire Prediction using Machine Learning ## 📌 Project Overview This project focuses on analyzing the **Algerian Forest Fires Dataset** to identify patterns in forest fire occurrences and build a machine learning model capable of predicting the **Fire Weather Index (FWI)** based on meteorological conditions. The project demonstrates the complete data science workflow, including data cleaning, exploratory data analysis (EDA), feature engineering, model training, evaluation, and visualization. --- ## 📂 Dataset The dataset contains weather observations collected from two regions of Algeria: * **Bejaia Region** * **Sidi Bel-Abbes Region** ### Features * Temperature (°C) * 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) * Fire Weather Index (FWI) * Fire Class (Fire / Not Fire) * Region --- ## 🎯 Project Objectives * Clean and preprocess raw wildfire data. * Perform exploratory data analysis to understand wildfire patterns. * Visualize relationships between weather variables. * Engineer useful features for machine learning. * Train regression models for wildfire prediction. * Evaluate model performance using standard regression metrics. --- ## 🛠️ Technologies Used * Python * NumPy * Pandas * Matplotlib * Seaborn * Scikit-learn * Jupyter Notebook --- ## 📊 Exploratory Data Analysis The project includes several visualizations, such as: * Monthly fire occurrence analysis * Distribution plots * Histograms * Correlation heatmap * Boxplots * Pairplots * Feature distributions These analyses help identify relationships between environmental conditions and wildfire activity. --- ## 🤖 Machine Learning Workflow 1. Data Cleaning 2. Feature Engineering 3. Train-Test Split 4. Feature Scaling 5. Model Training 6. Model Evaluation 7. Performance Comparison --- ## 📈 …