Researchers have introduced SpatialEpiBench, a new benchmark designed to evaluate spatiotemporal models for epidemic forecasting. The benchmark includes 11 datasets and standardized rolling evaluations to better reflect real-world public health scenarios. Initial evaluations revealed that most current models struggle to outperform a simple baseline, failing to anticipate outbreaks, handle noisy data, or effectively utilize geographic information. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Establishes a new standard for evaluating spatiotemporal AI models in epidemic forecasting, highlighting current limitations.
RANK_REASON This is a research paper introducing a new benchmark for evaluating AI models.