This study investigates the impact of automobile air conditioning systems on fuel consumption and gas emissions in hybrid and internal combustion engine vehicles using machine learning algorithms. Dynamic and static data were collected via an OBDII sensor from the vehicles examined, complemented by weather data sourced from the OpenWeatherMap API to capture external factors such as temperature and humidity during each trip. Machine learning models, including Linear Regression, XGBoost, and a Stacking ensemble model, were trained to predict fuel consumption rates over time, supplemented by an XGBoost Classifier to ascertain whether the air conditioning was in use during trips. The regressor models achieved low error scores after training and modifications, while the classifier achieved an accuracy of 99%. The findings from this research may inform future studies aimed at optimizing vehicle performance under varying road, driving, and weather conditions while minimizing energy consumption and harmful emissions.

California’s Mediterranean climate, characterized by mild and wet winters and hot and dry summers, makes the state particularly susceptible to wildfires. Increasingly severe fires, exacerbated by climate change, require accurate predictions to assess the risk of their occurrence. Machine learning models have been used in the past for wildfire prediction, but have been computationally intensive as they have focused on California in its entirety. This project aims to reduce the computational cost by focusing on three distinct prediction zones in California: the Southern Mediterranean coast, the Central Sierra Nevada Mountains, and the Northern California coast. Additionally, the imbalanced fire and non-fire data has resulted in low precision and recall scores in the past. This paper aims to improve the performance, specifically precision and recall, of fire prediction models when working with inherently imbalanced data. The processing times of our models were all under an hour, with the fastest being 36 minutes, indicating a decrease in the computational efforts needed. The best performing model, the Central Zone, had an accuracy of 99.96% with a recall and precision of 87.66% and 96.35% respectively. These results indicate that by separating California into multiple homogeneous ecosystem-based prediction zones the computational efforts were limited while the model performance was improved. Future work in this project includes extending the analyses to more ecosystems in California.