anamika3012/Fire-Prediction

Forest Fire Prediction using Machine Learning on UCI Algerian Forest Dataset ; For Major project in 8th Semester # Forest Fire Prediction ## Description This repository includes the necessary code and dataset to develop and train a predictive model (Uses Regression Models) for detecting potential forest fires. ## Dataset Description Source : UCI - Algerian Forest Dataset The dataset includes 244 instances that regroup a data of two regions of Algeria,namely the Bejaia region located in the northeast of Algeria and the Sidi Bel-abbes region located in the northwest of Algeria. - 122 instances for each region. - The period from June 2012 to September 2012. - The dataset includes 11 attribues and 1 output attribue (class) - The 244 instances have been classified into fire (138 classes) and not fire (106 classes) classes. ## Key Features and Highlights - Utilizes regression Models to predict Fire Weather Index using inputs given by user for Algeria region. - Input Features are- - Temperature - Relative Humidity (RH) - Wind Speed (Ws) - Rain - Fine Fuel Moisture Code (FFMC) - Duff Moisture Code (DMC) - Initial Spread Index (ISI) - Region - Displays the Predicted FWI value and Risk level classification (based on predefined FWI thresholds). ## Installation To run the project, follow these steps: 1. Clone the repository: ```bash git clone github.com ``` 2. Install the required dependencies: ```bash pip install -r requirements.txt ``` 3. Run application: ```bash python application.py ``` 4. Open your web browser and navigate to localhost ## Dependencies The project has the following dependencies: - NumPy - Pandas - Scikit-learn - Matplotlib ## Thesis and PPT Thesis PPT ##