maheshsathe07/Forest-Fire-Weather-Index-Analysis-and-Prediction

Our project predicts forest fire weather conditions in Algeria using machine learning. It analyzes meteorological data, trains a Ridge regression model, and provides a user-friendly web interface for predicting forest fire risk. 🌲🔥 #ML #ForestFirePrediction # Forest Fire Weather Index Analysis and Prediction **Project Overview:** The "Forest Fire Weather Index Analysis and Prediction" project aims to analyze and predict forest fire weather conditions using data from Algeria. The project utilizes the Algerian Forest Fires Dataset sourced from Kaggle, which provides valuable insights into various environmental factors contributing to forest fire occurrences. The workflow involves exploratory data analysis (EDA) followed by model training and prediction using linear, Lasso, and Ridge regression techniques. Among these, the Ridge regression model emerged as the most effective in predicting forest fire weather index. **Dataset:** The dataset used in this project can be accessed through the following link: Algerian Forest Fires Dataset. It contains information on meteorological and environmental variables such as temperature, relative humidity, wind speed, rain, and forest fire weather index. These variables are crucial for understanding the dynamics of forest fire occurrences. **Project Workflow:** 1. **Exploratory Data Analysis (EDA):** - Conducted thorough exploration of the dataset to understand its structure, patterns, and distributions. - Analyzed correlations between different features and the forest fire weather index. - Visualized key insights using various graphs and charts to gain a deeper understanding of the data. 2. **Model Training:** - Utilized linear regression, Lasso regression, and Ridge regression techniques to train predictive models. - Evaluated the performance of each model based on metrics such as mean squared error, R-squared value, and cross-validation scores. - Identified Ridge regression as the optimal model for predicting forest fire weather index due to its superior performance. 3. **Model Persistence:** - Saved the trained Ridge regression model into a .pkl (pickle) format for future use. - Additionally, saved the StandardScaler object used for feature scaling alongside the model for co …