Shiti09/Algerian-Forest-Fire

Developed a robust predictive model to forecast forest fires in Algeria and predict temperature trends. This project involved comprehensive data analysis and machine learning techniques, showcasing skills in statistical analysis and data visualization. # Algerian-Forest-Fire Welcome to the repository showcasing a **predictive model for Algerian forest fires**, utilizing data sourced from the UCI repository. This project focuses on the analysis and prediction of forest fire occurrences in two distinct regions of Algeria: the Bejaia region situated in the northeast and the Sidi Bel-abbes region positioned in the northwest. The dataset encapsulates a total of **244 instances**, evenly divided between these two regions, with 122 instances attributed to each. The time span covered within this dataset spans from June 2012 to September 2012, providing a comprehensive view of the forest fire occurrences during this period. Comprising **11 distinct attributes** and an additional **output attribute ('class')**, this dataset encompasses a diverse range of information crucial for understanding the factors influencing forest fires. Among the 244 instances, 138 instances have been classified as fire occurrences while the remaining 106 instances denote instances where fires were absent. This project delves into the application of machine learning algorithms to predict and classify forest fire incidents, aiming to offer insights into the patterns, factors, and conditions contributing to these occurrences in the aforementioned Algerian regions. The predictive model developed here serves as a valuable tool not only for understanding historical trends but also for preemptively assessing and managing potential forest fire risks in these regions. Through this repository, we present our analysis, methodology, and predictive models, aiming to contribute to the domain of forest fire prediction and provide a resource for researchers, environmentalists, and stakeholders invested in forest conservation and fire prevention efforts in Algeria. ## The Steps taken for this project is ### Data Preprocessing: - Data Collection: Obtained the dataset from the UCI repository. - Data Cleaning: Handled missing values, outliers, and inconsistenci …