Next Article in Journal
Global Prevalence and Distribution of Human Sarcocystosis: A Systematic Review and Meta-Analysis
Previous Article in Journal
Reply to Asgarian et al. Comment on “Nejati et al. Spatiotemporal Patterns and Historical Overview of Aedes Mosquitoes in Iran: A Systematic Review. Trop. Med. Infect. Dis. 2026, 11, 131”
Previous Article in Special Issue
Climate-Driven Distribution and Ecological Niche Modeling of Three Anopheles Species in China Using the Biomod2 Ensemble Framework
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
TropicalMed
Volume 11
Issue 9
10.3390/tropicalmed11090240
tropicalmed-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Climate-Aware Self-Retrospective Representation Learning for Spatio-Temporal Epidemic Forecasting †

by
Qi Yuan
1,
Han Shu
2,
Yizhi Pan
2,
Tianshuo Li
1,
Hangyi Shen
1,
Weiqi Jiang
1,
Zidan Zhu
1,
Pengpeng Zhang
1,
Ningli Xi
1,
Junyi Xin
1,*,
Kai Li
1,* and
Guanqun Sun
1,*
1
School of Information Science, Hangzhou Medical College, Hangzhou 311399, China
2
School of Information Science, Japan Advanced Institute of Science and Technology, Nomi 9231292, Ishikawa, Japan
*
Authors to whom correspondence should be addressed.
†
This paper is an extended version of our paper published in CyberSciTech 2025
Trop. Med. Infect. Dis. 2026, 11(9), 240; https://doi.org/10.3390/tropicalmed11090240
Submission received: 7 July 2026 / Revised: 9 August 2026 / Accepted: 17 August 2026 / Published: 24 August 2026
(This article belongs to the Special Issue Advances in Infectious Disease Surveillance: Climate-Sensitive, Biostatistical, and Simulation Modeling Approaches)
Versions Notes

Abstract

Spatio-temporal epidemic forecasting aims to predict future outbreak trajectories across interconnected regions from historical epidemiological observations and meteorological covariates. However, existing approaches often fail to preserve historically salient epidemic states or to fully exploit delayed and region-varying meteorological associations, leading to unstable temporal representations and insufficient meteorological-context-aware spatio-temporal context for prediction at later forecast horizons. In this paper, we propose CASRL, a Climate-Aware Self-Retrospective Representation Learning network for stable and meteorological-context-aware spatio-temporal epidemic forecasting. CASRL first employs a Self-Retrospective Epidemic Encoder (SREE) to retrospectively aggregate historically salient epidemic states through query-guided weighting and adaptive gating, thereby preserving informative historical epidemic states within the look-back window. It then introduces a Climate-Adaptive Graph Message Passing (CAGMP) module that breaks away from traditional passive feature concatenation. Instead, it constructs a separate meteorological-view predictive graph conditioned on the static spatial prior and adaptively fuses it with the incidence-associated topology to model complex cross-regional predictive associations. By integrating self-retrospective epidemic representations with meteorological-view spatio-temporal interactions, CASRL produces forecasts with improved predictive stability at later forecast horizons. Extensive experiments on two public influenza benchmarks show that CASRL is competitive at shorter forecast horizons and provides clearer advantages at later forecast horizons, particularly in phase-alignment-related evaluation and 15-week-ahead forecasting.
Keywords: epidemic forecasting; spatio-temporal graph neural networks; meteorological-view predictive graph; retrospective temporal modeling epidemic forecasting; spatio-temporal graph neural networks; meteorological-view predictive graph; retrospective temporal modeling

Share and Cite

MDPI and ACS Style

Yuan, Q.; Shu, H.; Pan, Y.; Li, T.; Shen, H.; Jiang, W.; Zhu, Z.; Zhang, P.; Xi, N.; Xin, J.; et al. Climate-Aware Self-Retrospective Representation Learning for Spatio-Temporal Epidemic Forecasting. Trop. Med. Infect. Dis. 2026, 11, 240. https://doi.org/10.3390/tropicalmed11090240

AMA Style

Yuan Q, Shu H, Pan Y, Li T, Shen H, Jiang W, Zhu Z, Zhang P, Xi N, Xin J, et al. Climate-Aware Self-Retrospective Representation Learning for Spatio-Temporal Epidemic Forecasting. Tropical Medicine and Infectious Disease. 2026; 11(9):240. https://doi.org/10.3390/tropicalmed11090240

Chicago/Turabian Style

Yuan, Qi, Han Shu, Yizhi Pan, Tianshuo Li, Hangyi Shen, Weiqi Jiang, Zidan Zhu, Pengpeng Zhang, Ningli Xi, Junyi Xin, and et al. 2026. "Climate-Aware Self-Retrospective Representation Learning for Spatio-Temporal Epidemic Forecasting" Tropical Medicine and Infectious Disease 11, no. 9: 240. https://doi.org/10.3390/tropicalmed11090240

APA Style

Yuan, Q., Shu, H., Pan, Y., Li, T., Shen, H., Jiang, W., Zhu, Z., Zhang, P., Xi, N., Xin, J., Li, K., & Sun, G. (2026). Climate-Aware Self-Retrospective Representation Learning for Spatio-Temporal Epidemic Forecasting. Tropical Medicine and Infectious Disease, 11(9), 240. https://doi.org/10.3390/tropicalmed11090240

Article Metrics

Back to TopTop