Spatiotemporal Dynamics of Daily and Per Capita VMT in California: A County-Level Analysis (2019–2023)

Abstract:

Vehicle miles traveled (VMT) is a fundamental metric for assessing mobility trends and infrastructure needs. This study examines the spatial-temporal dynamics of daily VMT (DVMT) and per capita DVMT across California counties from 2019 to 2023, covering the pre-, mid-, and post-pandemic periods via GIS mapping and k-means clustering. To identify determinants of per capita DVMT, we compared traditional linear regression approaches (OLS, Ridge, LASSO, Elastic Net) with ensemble tree-based models. Specific results include: the ensemble models estimated using 2019–2022 data delivered substantially higher accuracy, achieving R² values exceeding 0.98; meanwhile, out-of-sample performance on 2023 data remained robust (R² ≈ 0.82 for Random Forest; R² ≈ 0.91 for Gradient Boosting), indicating strong model generalizability. Feature importance analysis identifies housing density, population density, and public transit mode share as the primary drivers of per capita DVMT. These findings underscore the utility of spatial analysis and advanced nonlinear modeling for regional transportation planning.

Publications:

Spatiotemporal Dynamics of Daily and Per Capita VMT in California: A County-Level Analysis (2019–2023) (Full Report)

Research Brief

Authors:

Yong Lao, PhD
Yong Lao is a Full Professor of Geography in the Department of Social Sciences and Global Studies at California State University (CSU), Monterey Bay. Dr. Lao's teaching and research interests are Geographic Information Systems (GIS), transportation planning, location theories, quantitative methods, and economic geography. He has collaborated with many government agencies and businesses on a wide range of GIS mapping and spatial analysis projects, including performance evaluation of bus lines, hazardous-material shipping, childcare facility selection, airline hub location, and ATM network planning.

Bo Yang, PhD
Bo Yang is an Assistant Professor of Environmental Studies at the University of California, Santa Cruz. He is the Director of the GISTAR M.A. program and leads the GeoFly Lab, where his research focuses on GIS, remote sensing, UAV/drone mapping, and geospatial AI for environmental and societal applications. His work spans wildfire risk assessment, transportation and infrastructure monitoring, and coastal ecosystem mapping, and has been supported by agencies including the NSF, NASA, USDOT, and CAL FIRE.

Published:

April 2026

Keywords:

Vehicle miles traveled

K-means clustering

Regression analysis

GIS