Rapid Assessments of Light-Duty Gasoline Vehicle Emissions Using On-Road Remote Sensing and Machine Learning

TL;DR

This study develops an ensemble machine learning model to rapidly assess real-world emissions of light-duty gasoline vehicles using remote sensing data, offering a practical tool for urban air quality management.

Contribution

It introduces a novel ensemble model framework combining neural networks, XGBoost, and random forests for on-road vehicle emission assessment using remote sensing data.

Findings

Model accurately assesses vehicle emissions (CO, HC, NO) in real-time.

Identifies 2.33% of vehicles as high emitters and 74.92% as low emitters.

Enables day-to-day supervision of vehicle emissions, improving over traditional I/M procedures.

Abstract

In-time and accurate assessments of on-road vehicle emissions play a central role in urban air quality and health policymaking. However, official insight is hampered by the Inspection/Maintenance (I/M) procedure conducted in the laboratory annually. It not only has a large gap to real-world situations (e.g., meteorological conditions) but also is incapable of regular supervision. Here we build a unique dataset including 103831 light-duty gasoline vehicles, in which on-road remote sensing (ORRS) measurements are linked to the I/M records based on the vehicle identification numbers and license plates. On this basis, we develop an ensemble model framework that integrates three machining learning algorithms, including neural network (NN), extreme gradient boosting (XGBoost), and random forest (RF). We demonstrate that this ensemble model could rapidly assess the vehicle-specific emissions (i.e., CO, HC, and NO). In particular, the model performs quite well for the passing vehicles under normal conditions (i.e., lower VSP (< 18 kw/t), temperature (6 ~ 32 {\deg}C), relative humidity (< 80%), and wind speed (< 5m/s)). Together with the current emission standard, we identify a large number of the dirty (2.33%) or clean (74.92%) vehicles in the real world. Our results show that the ORRS measurements, assisted by the machine-learning-based ensemble model developed here, can realize day-to-day supervision of on-road vehicle-specific emissions. This approach framework provides a valuable opportunity to reform the I/M procedures globally and mitigate urban air pollution deeply.