Researchers have introduced a new large-scale dataset for forecasting electric vehicle (EV) charging demand, collected across Scotland from 2022 to 2025. This dataset aims to overcome the limitations of older benchmarks by reflecting the complexity of modern charging networks. The team developed a spatio-temporal latent Gaussian field model, utilizing Integrated Nested Laplace Approximation for inference, which offers accurate predictions along with uncertainty quantification and interpretable spatial and temporal insights. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Provides a new benchmark dataset and a probabilistic modeling framework for more accurate and interpretable EV charging demand forecasting.
RANK_REASON The cluster describes a new academic paper introducing a novel dataset and a probabilistic modeling approach for EV charging demand.