payaswini126/Algerian-Forest-Fire-Risk-Prediction

Algerian Forest Fire Risk Prediction 📌 Project Overview This project focuses on predicting forest fire risk using meteorological data from the Algerian Forest Fires dataset. The goal is to analyze weather conditions and Fire Weather Index (FWI) components to identify high-risk fire scenarios using machine learning techniques. 📂 Dataset Source: Algerian Forest Fires Dataset Features: Temperature, Relative Humidity, Wind Speed, Rainfall, and Fire Weather Index (FWI) variables Target: Fire occurrence (Fire / No Fire) 🛠️ Tech Stack Programming: Python Libraries: Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn Tools: Jupyter Notebook, Google Colab 🔍 Exploratory Data Analysis (EDA) Analyzed data distribution, trends, and correlations Identified key factors influencing fire occurrence Detected class imbalance and feature relationships Visualized insights using Matplotlib and Seaborn ⚙️ Data Preprocessing Handled missing and inconsistent values Corrected data types and encoded categorical variables Scaled numerical features Performed feature selection and engineering to reduce multicollinearity 🤖 Machine Learning Models The following models were implemented and evaluated: Logistic Regression Decision Tree Random Forest Support Vector Machine (SVM) 📊 Model Evaluation Models were compared using: Accuracy Precision Recall F1-Score Confusion Matrix Hyperparameter tuning and cross-validation were applied to improve performance. ✅ Results Identified the most effective model for predicting forest fire risk Achieved reliable performance in classifying high-risk fire conditions Demonstrated practical application of machine learning in environmental risk analysis 🚀 Conclusion This project showcases end-to-end data analysis and machine learning workflow, from EDA and preprocessing to model building and evaluation, highlighting the use of data-driven techniques for environmental safety and decision-making.