Temperature and electric vehicle adoption: A ZIP code-level analysis in the US

Electric vehicle (EV) users living in colder or warmer climates experience shorter traveling ranges, slower acceleration, and longer recharge times, which might discourage EV adoption. Using data from seven US states, we analyze the link between temperature and EV adoption at the ZIP code level. We collect land surface and air temperature data, along with sociodemographic, infrastructure, land cover, elevation, and electoral data. Using random forest regression, we predict battery electric (BEV) and plug-in hybrid electric (PHEV) vehicle population change rates and penetrations. Our findings reveal that temperature variation and temperature extremes are among the top predictors of BEV and PHEV adoption. Understanding this relationship is crucial for assessing EV feasibility in diverse climates and ensuring equitable access to the technology. This study underscores the importance of incorporating environmental factors in strategies to promote EV adoption. •Studies temperature dynamics and EV adoption at the US ZIP code level.•Includes land surface temperature, landscape, and electoral data.•Uses machine learning for predicting BEV and PHEV population change rates and penetration.•Reveals critical temperature factors in BEV and PHEV adoption predictors.