Data-Driven Models Support a Vision for Over-the-Air Vehicle Emission Inspections

Emissions inspection and maintenance (I/M) programs for light-duty motor vehicles manage ambient air quality by enforcing emissions standards and requiring non-compliant vehicles to be repaired or retired. I/M programs in the United States typically identify over-emitters through on-board diagnostics (OBD) systems and vehicles’ proprietary firmware (i.e., indirect tests), rather than through physical measurements of exhaust gases (i.e., tailpipe tests). Analyzing data from Colorado’s I/M program, this study finds the OBD test to have an accuracy of 87%, but a false pass rate of 50%, when predicting the result of a corresponding tailpipe test. As an alternative, transparent data-driven models—using logistic regression and gradient boosting machines—to consistently identify over-emitting vehicles are proposed. These models were up to 24% more accurate, or 85% more sensitive than the current OBD test in a stratified data sample. A key benefit of transparent statistical models—jurisdictions’ ability to tune the test methods to best suit program needs—is also assessed. Finally, this study shows how these results support a vision for cloud-based, selective I/M programs where statistical models are applied to OBD data—collected over-the-air from vehicles—to identify and require additional inspection for only the most probable over-emitters.

I. Introduction

Thirty-one U.S. states and the District of Columbia require that light-duty motor vehicles (LDV’s) undergo periodic inspections to identify and remedy over-emitting vehicles (i.e., vehicles whose emissions at the time of inspection are higher than the prescribed standards in effect when the vehicles were manufactured), to improve and maintain ambient air quality. Inspection & maintenance (I/M) programs may be viewed as an enforcement mechanism for vehicle emissions standards (which manufacturers must meet for all new vehicles) over the lifetime of the vehicles [1]. These programs gained popularity nationwide after 1977, when amendments to the Clean Air Act [2] required that jurisdictions unable to attain the National Ambient Air Quality Standards (NAAQS) [3] must apply one or more pollution control measures from a list of approved methods (which included the establishment of an I/M program). The primary aim of I/M programs is to identify and remedy vehicles with high emissions of three key pollutants: carbon monoxide (CO), hydrocarbons (HCx) and the oxides of nitrogen (NOx).