Unveiling Emitter Trends in Heavy Duty Vehicles using Extreme Gradient Boosting algorithm

The increasing use of Heavy-Duty Vehicles (HDV) has spurred the development of advanced techniques for analyzing and forecasting emission patterns. In this study, researchers present a novel method using the Extreme Gradient Boosting (XGBoost) algorithm to identify emission patterns in HDV. A sophisticated prediction model was constructed using a large dataset encompassing various vehicle aspects, such as engine specifications, operating conditions, and pollution levels. The XGBoost algorithm extracts intricate nonlinear correlations from the data, providing significant insights into emission patterns. The proposed model demonstrates improved precision in prediction and generalization capabilities through cross-validation and comparison with traditional predictive methods. The findings highlight crucial factors influencing emissions that benefit public and private stakeholders in mitigating environmental impact. This study showcases XGBoost’s ecological statistical capabilities and sets a foundation for future advancements in robust vehicle emission trend analysis.