GeoAI helps find best locations for electric vehicle charging stations
Electric Vehicle Charging Station Location Selection using Geospatial Artificial Intelligence (GeoAI)
Machine Learning
Summary
Electric cars need charging stations placed in the right spots to be useful. The authors use a new computer method that looks at maps, traffic, population, and current station data to find good places for new charging spots. Their method combines special AI tools to learn from many details and figure out where future stations should go. Tested in Texas, this approach found new candidate locations better than older methods. They also showed different ways to choose spots depending on goals like making travel shorter or matching existing station patterns.
What this means in practice
- •For urban planners: Identify promising sites for new EV charging stations by analyzing spatial and usage data to support local infrastructure development.
- •For transportation planners: Optimize placement of EV charging stations to reduce overall travel distance and improve accessibility in growing electric mobility networks.
- •For energy infrastructure companies: Develop targeted EV charging station deployment strategies using AI-driven geospatial analysis to improve operational performance and customer coverage.$Commercial implications: Enables commercial providers to sell tailored location planning services for EV charging infrastructure based on AI modeling.
Tested on one dataset.
Authors
Eun Hak Lee, Euntak Lee
Abstract
As electric vehicle (EV) adoption increases, ensuring efficient and well-distributed charging infrastructure has become a critical challenge. While many EV charging station location problem (CSLP) studies focus on minimizing costs or travel distance, it is crucial to consider the surrounding geospatial characteristics of existing stations that influence operational performance. This study proposes a geospatial artificial intelligence (GeoAI)-based framework that integrates high-dimensional EV-related geospatial data, including EV usage, land-use, population, and traffic attributes. We incorporate a variational autoencoder (VAE) and a graph convolutional network (GCN) into the model to capture similarities among existing charging stations, and to identify suitable locations for future stations. The VAE compresses high-dimensional EV input data into a low-dimensional latent space, and the GCN uses this latent representation to predict locations suitable for charging stations. Using real-world data from Bryan-College Station, Texas, US, the proposed model outperforms state-of-the-art baselines, achieving an F1-score of 0.87 in distinguishing existing station locations from non-station locations. The model also identifies 27 additional candidate locations that show geospatial characteristics similar to those of existing stations, based on a similarity score. We further evaluate two policy implementation scenarios, maximizing geospatial similarity and minimizing total travel distance, each yielding different outcomes aligned with distinct strategic objectives. The findings highlight the importance of incorporating spatial context into CSLP and provide valuable insights for future EV infrastructure planning, promoting both efficiency and accessibility in the rapidly growing electric mobility sector.