Prior Knowledge-enhanced Spatio-temporal Epidemic Forecasting

2026-02-25

AI Summary

Existing spatiotemporal epidemic forecasting methods suffer from insufficient sensitivity to weak signals, oversimplified modeling of spatial relationships, and unstable parameter estimation. To address these limitations, this work proposes the STOEP framework, which integrates implicit spatiotemporal priors with explicit expert knowledge through three core components: context-aware adjacency learning, spatially informed parameter estimation, and filter-based prediction. This approach dynamically models regional dependencies, enhances weak epidemiological signals, and regularizes model parameters. Evaluated on real-world COVID-19 and influenza datasets, STOEP achieves an 11.1% reduction in RMSE compared to the best-performing baseline and has been deployed in a provincial Center for Disease Control and Prevention in China.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Stochastic Optimization
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Spatio-temporal epidemic forecasting is critical for public health management, yet existing methods often struggle with insensitivity to weak epidemic signals, over-simplified spatial relations, and unstable parameter estimation. To address these challenges, we propose the Spatio-Temporal priOr-aware Epidemic Predictor (STOEP), a novel hybrid framework that integrates implicit spatio-temporal priors and explicit expert priors. STOEP consists of three key components: (1) Case-aware Adjacency Learning (CAL), which dynamically adjusts mobility-based regional dependencies using historical infection patterns; (2) Space-informed Parameter Estimating (SPE), which employs learnable spatial priors to amplify weak epidemic signals; and (3) Filter-based Mechanistic Forecasting (FMF), which uses an expert-guided adaptive thresholding strategy to regularize epidemic parameters. Extensive experiments on real-world COVID-19 and influenza datasets demonstrate that STOEP outperforms the best baseline by 11.1% in RMSE. The system has been deployed at one provincial CDC in China to facilitate downstream applications.

Problem

• spatio-temporal epidemic forecasting
• weak epidemic signals
• spatial relations
• parameter estimation

Innovation

• spatio-temporal forecasting
• epidemic modeling
• prior knowledge integration
• adaptive parameter estimation
• dynamic adjacency learning