This project aimed to enhance wildfire prediction and management in Southern California by comparing machine learning techniques on county-specific models. The primary objective was to identify the counties in Southern California most impacted by wildfires, construct and compare various machine learning models for predicting wildfire occurrences, and determine county-specific factors influencing wildfire risk. Four machine learning models were compared: Random Forest Classifier, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Decision Trees. The Random Forest Classifier demonstrated the highest accuracy and F1 scores for Los Angeles and Riverside Counties. Key findings highlighted NDVI (Normalized Difference Vegetation Index) and average temperature as critical drivers of wildfire occurrences.