anirudh7371/Algerian_Wildfire_Predictor

The Algerian Wildfire Predictor is a machine learning project that forecasts forest fire likelihood in Algeria using environmental data. It helps predict and prevent wildfires by analyzing factors like temperature, humidity, and wind speed. # Algerian Wildfire Predictor ## Overview The Algerian Wildfire Predictor is a machine learning project aimed at predicting the likelihood of forest fires in Algeria based on various environmental factors. This project utilizes a dataset containing information about temperature, relative humidity, wind speed, rainfall, and other relevant features to train a predictive model. The trained model can then be used to provide insights into the potential occurrence of forest fires, aiding in fire prevention efforts. ## Project Structure - **notebooks/**: Directory containing Jupyter notebooks for data preprocessing (`Algerian_Forest_Fire.ipynb`) and model training (`model_training.ipynb`). - **dataset/**: Contains two datasets: one raw and the other cleaned. - **app.py**: Flask application for deploying the trained model as a web service. - **templates/**: Directory containing HTML templates for the web interface. - **models/**: Directory containing serialized trained models and scalers. - **requirements.txt**: List of Python dependencies required to run the project. - **README.md**: Documentation file providing an overview of the project and instructions for running it. ## Dataset Description The Algerian Wildfire Predictor project utilizes the Algerian Forest Fires dataset, which is publicly available on the UCI Machine Learning Repository. This dataset contains information about forest fires in Algeria, focusing on various environmental factors that may contribute to the occurrence of wildfires. Here's a brief overview of the dataset: - **Title**: Algerian Forest Fires Dataset - **Source**: UCI Machine Learning Repository - **URL**: Algerian Forest Fires Dataset - **Attributes**: 1. **day**: Day of the month (1-31). 2. **month**: Month of the year (1-12). 3. **year**: Year (2012 or 2013). 4. **temperature**: Temperature in Celsius degrees. 5. **RH**: Relative humidity (%). 6. **WSPM**: Wind speed in meters per second. 7. **rain**: Rainfall in millimeters per square …