AkshayYede/Algerian-Forest-Fire-Prediction-System

# Algerian-Forest-Fire-Prediction-System ### **Project Description** This project aims to predict the likelihood of fire occurrences based on weather and environmental conditions, using machine learning algorithms. By analyzing historical weather data, such as temperature, relative humidity, wind speed, rainfall, and specific indices like FFMC (Fine Fuel Moisture Code), DMC (Duff Moisture Code), ISI (Initial Spread Index), the system can forecast the likelihood of fire across different regions. This project is designed to help environmental agencies, fire departments, and local governments proactively manage wildfire risks and allocate resources more efficiently. The FWI prediction will help in preventing the destruction of valuable ecosystems, reduce the cost of firefighting efforts, and increase public safety. ### **Problem Statement** Wildfires are a growing concern globally due to rising temperatures, irregular weather patterns, and climate change. Predicting the likelihood of a wildfire before it happens can save resources, lives, and ecosystems. This project uses machine learning techniques to predict whether a fire will occur in a specific region based on weather data. The goal is to build a reliable, deployable model that can give an accurate prediction of fire risk based on real-time weather parameters. ### **Objectives** - Build a machine learning model that predicts whether a wildfire will occur based on environmental data. - Use historical weather data to train the model and predict fire incidents across different regions. - Develop a user-friendly web application where users can input real-time weather data and get fire risk predictions. ### **Dataset** The dataset used for training the model includes various weather-related parameters such as: - **Temperature** (°C) - **Relative Humidity** (%) - **Wind Speed** (km/h) - **Rainfall** (mm) - **FFMC Index**: Represents the moisture content of fine fuels. - **DMC Index**: Repre …