What question did this study set out to answer?

This review aims to explore the role of machine learning in understanding traffic-related air pollution, especially non-exhaust emissions.

May 16, 2026Open Access

Beyond spatiotemporal modeling: a review of applications of machine learning for traffic-related air pollution toward non-exhaust emissions

Puntos clave

This review aims to explore the role of machine learning in understanding traffic-related air pollution, especially non-exhaust emissions.
Reviewed over 50 studies from 2020 to 2024 related to traffic-related air pollution and machine learning applications.
Focused on spatial modeling, identifying contributing factors, non-exhaust emission characterization, and source apportionment.
Highlighted challenges including data sparsity and feature inconsistency.
Identified key challenges in using machine learning for traffic-related air pollution, including data gaps and interpretability issues.
Suggests better integration and transparency of machine learning methods for improved environmental health assessments.
Emphasizes the importance of addressing non-exhaust emissions in traffic-related air pollution.

Resumen

Abstract Traffic-related air pollution (TRAP), increasingly shaped by non-exhaust emissions, remains a major urban health concern. This review provides a structured synthesis of over 50 studies (2020–2024) applying machine learning (ML) to TRAP, focusing on spatial modeling, contributing factor identification, non-exhaust emission characterization, and source apportionment. Key challenges include data sparsity, inconsistent features, and limited interpretability. Advancing ML integration and transparency is essential for improving exposure assessment and environmental health.

Me gusta

Guardar

Ver artículo completo