A Multi-Modal Spatial Risk Framework for EV Charging Infrastructure Using Remote Sensing

TL;DR

This paper presents RSERI-EV, a comprehensive multi-modal risk assessment framework that uses remote sensing and spatial analytics to evaluate the resilience of EV charging stations against environmental threats.

Contribution

The paper introduces a novel spatially explicit framework combining remote sensing, infrastructure data, and graph analytics for assessing EV charging station vulnerability.

Findings

Demonstrated the framework's feasibility on Wales EV data

Showcased the integration of diverse data layers for resilience scoring

Highlighted the importance of multi-source data fusion in infrastructure resilience

Abstract

Electric vehicle (EV) charging infrastructure is increasingly critical to sustainable transport systems, yet its resilience under environmental and infrastructural stress remains underexplored. In this paper, we introduce RSERI-EV, a spatially explicit and multi-modal risk assessment framework that combines remote sensing data, open infrastructure datasets, and spatial graph analytics to evaluate the vulnerability of EV charging stations. RSERI-EV integrates diverse data layers, including flood risk maps, land surface temperature (LST) extremes, vegetation indices (NDVI), land use/land cover (LULC), proximity to electrical substations, and road accessibility to generate a composite Resilience Score. We apply this framework to the country of Wales EV charger dataset to demonstrate its feasibility. A spatial $k$-nearest neighbours ($k$NN) graph is constructed over the charging network to enable neighbourhood-based comparisons and graph-aware diagnostics. Our prototype highlights the value of multi-source data fusion and interpretable spatial reasoning in supporting climate-resilient, infrastructure-aware EV deployment.