Electric vehicles (EVs) are an emerging mode of transportation that has the potential to reshape the transportation sector by significantly reducing carbon emissions thereby promoting a cleaner environment and pushing the boundaries of climate progress. Nevertheless, there remain significant hurdles to the widespread adoption of electric vehicles in the United States ranging from the high cost of EVs to the inequitable placement of EV charging stations (EVCS). A deeper understanding of the underlying complex interactions of social, economic, and demographic factors that may lead to such emerging disparities in EVCS placements is, therefore, necessary to mitigate accessibility issues and improve EV usage among people of all ages and abilities. In this study, we develop a machine learning framework to examine spatial disparities in EVCS placements by using a predictive approach. We first identify the essential socioeconomic factors that may contribute to spatial disparities in EVCS access. Second, using these factors along with ground truth data from existing EVCS placements we predict future ECVS density at multiple spatial scales using machine learning algorithms and compare their predictive accuracy to identify the most optimal spatial resolution for our predictions. Finally, we compare the most accurately predicted EVCS placement density with a spatial inequity indicator to quantify how equitably these placements would be for Orange County, California. Our method achieved the highest predictive accuracy (94.9%) of EVCS placement density at a spatial resolution of 3 km using Random Forests. Our results indicate that a total of 11.04% of predicted EVCS placements in Orange County will lie within a high spatial inequity zone – indicating populations with the lowest accessibility may require greater investments in EVCS placements. 69.52% of the study area experience moderate accessibility issues and the remaining 19.11% face the least accessibility issues w.r.t EV charging stations. Within the least accessible areas, 7.8% of the area will require a low density of predicted EVCS placements, 3.4% will require a medium density of predicted EVCS placements and 0.55% will require a high density of EVCS placements. The moderately accessible areas would require the highest placements of EVCS but mostly with low-density placements covering 54.42% of the area. The findings from this study highlight a generalizable framework to quantify inequities in EVCS placements that will enable policymakers to identify underserved communities and facilitate targeted infrastructure investments for widespread EV usage and adoption for all. The findings from this study highlight a generalizable framework to quantify inequities in EVCS placements that will enable policymakers to identify underserved communities and facilitate targeted infrastructure investments for widespread EV usage and adoption for all.

Related Publications

other

Story Map: Examining Spatial Disparities in Electric Vehicle Charging Station Placements Using Machine Learning

published journal article

Examining Spatial Disparities in Electric Vehicle Charging Station Placements in Orange County

published journal article

Telecommuting and Travel during COVID-19: An Exploratory Analysis across Different Population Geographies in the U.S.A.

Publication Date

April 1, 2023

Associated Project

Teleworking, Travel, and Quality of Life Before, During, and After the Pandemic Across Different Population Groups in the U.S.

Author(s)

Rezwana Rafiq, Michael McNally

Areas of Expertise

Travel Behavior, Land Use, & the Built Environment

View published journal article

Abstract

This study explores the impact of the COVID-19 pandemic on telecommuting (working from home) and travel during the first year of the pandemic in the U.S.A. (from March 2020 to March 2021), with a particular focus on examining the variation in impact across different U.S. geographies. We divided 50 U.S. states into several clusters based on their geographic and telecommuting characteristics. Using K-means clustering, we identified four clusters comprising 6 small urban states, 8 large urban states, 18 urban-rural mixed states, and 17 rural states. Combining data from multiple sources, we observed that nearly one-third of the U.S. workforce worked from home during the pandemic, which was six times higher than in the pre-pandemic period, and that these fractions varied across the clusters. More people worked from home in urban states compared with rural states. As well as telecommuting, we examined several activity travel trends across these clusters: reduction in the number of activity visits; changes in the number of trips and vehicle miles traveled; and mode usage. Our analysis showed there was a greater reduction in the number of workplace and nonworkplace visits in urban states compared with rural states. The number of trips in all distance categories decreased except for long-distance trips, which increased during the summer and fall of 2020. The changes in overall mode usage frequency were similar across urban and rural states with a large drop in ride-hailing and transit use. This comprehensive study can provide a better understanding of the regional variation in the impact of the pandemic on telecommuting and travel, which can facilitate informed decision-making.

presentation

Streamlining the Permitting Process for Transit-Oriented Development: The Case of California's Senate Bill 375

Publication Date

April 25, 2024

Associated Project

Streamlining the CEQA Process in Transit Rich Areas

Areas of Expertise

Travel Behavior, Land Use, & the Built Environment

View presentation

Related Publications

published journal article

Can Governments Streamline Environmental Impact Analysis to Promote Transit Oriented Development? Evidence from California

preprint journal article

A Comparison of Time-use for Telecommuters, Potential Telecommuters, and Commuters during the COVID-19 Pandemic

Publication Date

January 15, 2024

Associated Project

Connecting Telework, Travel Behavior, and System Performance During the COVID-19 Pandemic

Author(s)

Rezwana Rafiq, Michael McNally

Areas of Expertise

Infrastructure Delivery, Operations, & Resilience Travel Behavior, Land Use, & the Built Environment

View preprint journal article

Abstract

Throughout the ongoing COVID-19 pandemic, changes in daily activity-travel routines and time-use behavior, including the widespread adoption of telecommuting, have been manifold. This study considers how telecommuters have responded to the changes in activity-travel scheduling and time allocation. In particular, the research team considers how workers utilized time during the pandemic by comparing workers who telecommuted with workers who continued to commute. Commuters were segmented into those who worked in telecommutable jobs (potential telecommuters) and those who did not (commuters). Our empirical analysis suggested that telecommuters exhibited distinct activity participation and time use patterns from the commuter groups. It also supported the basic hypothesis that telecommuters were more engaged with in-home versus out-of-home activity compared to potential telecommuters and commuters. In terms of activity time use, telecommuters spent less time on work activities but more time on caring for household members, household chores, eating, socializing, and recreation activities than their counterparts. During weekdays, a majority of telecommuters did not travel and in general this group made fewer trips per day compared to the other two groups. Compared to telecommuters, potential telecommuters made more trips on both weekdays and weekends while non-telecommutable workers made more trips only on weekdays. The findings of this study provide initial insights on time use and the associated activity-travel behavior of both telecommuter and commuter groups during the pandemic.

preprint journal article

Impacts of the COVID-19 Pandemic on Telecommuting and Travel

Publication Date

January 15, 2023

Associated Project

Analyzing Telecommuting and Travel in California Before, During, and After the Pandemic

Author(s)

Rezwana Rafiq, Michael McNally

Areas of Expertise

Travel Behavior, Land Use, & the Built Environment

View preprint journal article

Abstract

This chapter examines changes in telecommuting and the resulting activity-travel behavior during the COVID-19 pandemic, with a particular focus on California. A geographical approach was taken to “zoom in” to the county level and to major regions in California and to “zoom out” to comparable states (New York, Texas, Florida). Nearly one-third of the domestic workforce worked from home during the pandemic, a rate almost six times higher than the pre-pandemic level. At least one member from 35 percent of U.S. households replaced in-person work with telework; these individuals tended to belong to higher-income, White, and Asian households. Workplace visits have continued to remain below pre-pandemic levels, but visits to non-work locations initially declined but gradually increased over the first nine months of the pandemic. During this period, the total number of trips in all distance categories except long-distance travel decreased considerably. Among the selected states, California experienced a higher reduction in both work and non-workplace visits, and the State’s urban counties had higher reductions in workplace visits than rural counties. The findings of this study provide insights to improve our understanding of the impact of telecommuting on travel behavior during the pandemic

published journal article

Electric Vehicles in Urban Delivery Fleets: How Far can They Go?

Publication Date

April 24, 2024

Associated Project

Understanding the Benefits, Challenges, and Opportunities Related to Changes in Consumer Shopping and Last‐Mile Delivery

Author(s)

Michael Hyland, Dingtong Yang

Areas of Expertise

Freight, Logistics, & Supply Chain

View published journal article

Abstract

The goal of this study is to provide insights into the expected role of medium-duty electric vehicles (EVs) in urban delivery fleets and to analyze the effectiveness of EV subsidies on EV fleet penetration and tailpipe emissions. To meet this goal, we propose a modeling framework that determines the minimum-cost fleet size and fleet mix (of EVs and conventional vehicles) and vehicle routes for a profit-maximizing delivery company. Second, we conduct extensive analyses using this modeling framework and Southern California network data; we vary the EV driving range, per-mile cost of EVs, demand rate, service region size/structure, driver working hours, and network travel times. We find that the optimal fleet mix nearly always includes EVs and conventional vehicles. Moreover, we find that EV subsidies have limited effectiveness with current EV batteries and service regions designed around conventional vehicles. Hence, improving EV battery technology is critical to electrifying urban delivery fleets.

Related Publications

research report

Benefits, Challenges, and Opportunities of Different Last-Mile Delivery Strategies

policy brief

Automated Vehicles and Transportation Network Companies Will Likely Impact the Efficacy of Transportation Pricing Strategies

Publication Date

July 1, 2024

Associated Project

Transport Pricing Policies and Emerging Mobility Innovations

Author(s)

Michael Hyland, Arash Ghaffar, Tanjeeb Ahmed, Daisik Nam

Areas of Expertise

Intelligent Transportation Systems, Emerging Technologies, & Big Data Transportation Economics, Funding, & Finance

View policy brief

Related Publications

research report

Transport Pricing Policies and Emerging Mobility Innovations

white paper

White Paper: A Blueprint for Improving Automated Driving System Safety

Publication Date

July 1, 2024

Associated Project

Safety Considerations for Automated Vehicles

Author(s)

Mollie Cohen D'Agostino, Cooper Michael, Marilia Ramos, Camila Correa Jullian

Areas of Expertise

Intelligent Transportation Systems, Emerging Technologies, & Big Data Safety, Public Health, & Mobility Justice

View white paper

Abstract

Vehicle automation represents a new safety frontier that may necessitate a repositioning of the safety oversight systems. This white paper serves as a primer on the technical and legal landscape of automated driving system (ADS) safety. It introduces the latest AI and machine learning techniques that enable ADS functionality. The paper also explores the definitions of safety from the perspectives of standards-setting organizations, federal and state regulations, and legal disciplines. The paper identifies key policy options building on topics raised in the White House’s Blueprint for an AI Bill of Rights, outlining a Blueprint for ADS safety. The analysis concludes that potential ADS safety reforms might include either reform of the Federal Motor Vehicle Safety Standards (FMVSS), or a more holistic risk analysis “safety case” approach. The analysis also looks at caselaw on liability in robotics, as well as judicial activity on consumer and commercial privacy, recognizing that the era of AI will reshape liability frameworks, and data collection must carefully consider how to build in accountability and protect the privacy of consumers and organizations. Lastly, this analysis highlights the need for policies addressing human-machine interaction issues, focusing on guidelines for safety drivers and remote operators. In conclusion, this paper reflects on the need for collaboration among engineers, policy experts, and legal scholars to develop a comprehensive Blueprint for ADS safety and highlights opportunities for future research.

policy brief

Perceptions of Neighborhood Change in a Latinx Transit Corridor

Publication Date

July 1, 2024

Associated Project

Social Impacts of Transit Oriented Development on Disadvantaged Communities

Author(s)

Douglas Houston, Michelle E. Zuniga

Areas of Expertise

Safety, Public Health, & Mobility Justice Travel Behavior, Land Use, & the Built Environment

View policy brief

Abstract

Understanding how residents feel about neighborhood changes due to new development along transit corridors (often referred to as transit-oriented development) remains understudied despite growing concerns over displacement and gentrification. Studies that examined these concerns are largely based on analyzing land use, housing values, and socio-economic shifts (i.e., who is moving in and out of neighborhoods), and do not provide conclusive evidence that transit-oriented development (TOD) is linked to neighborhood gentrification and displacement. Prior surveys of residents living near transit indicate a generally positive assessment of TOD in terms of improved walkability and accessibility but also express concerns over pedestrian safety and parking related to increased traffic and new commercial development. However, recent studies counter this relatively positive assessment of TOD, particularly among activists and community organizers in low-income communities of color.

Related Publications

published journal article

The Promise and Pitfalls of Early Project Notification Meetings: Illuminating Santa Ana’s Sunshine Ordinance

published journal article