Epidemic forecasting supports public health decisions ranging from capacity planning to intervention timing, for which both point accuracy and calibrated uncertainty are essential. Although neural models have advanced point forecasting, producing reliable probabilistic predictions over multiple future horizons remains challenging. Renewal models encode epidemic propagation, while neural forecasters learn flexible multi-horizon representations; integrating these strengths within a probabilistic future rollout remains underexplored. We propose EPI-SST (Epidemic State Space Transformer), a probabilistic forecaster centered on an evidence-driven renewal transition. At each horizon, neural evidence produces a bounded update to an internal multiplier and advances a finite-memory renewal state that generates the future mean trajectory. A separate heteroscedastic Gaussian head controls predictive scale using a validation-selected log-variance penalty. Across four epidemic surveillance benchmarks, EPI-SST achieves the lowest pooled RMSE on every dataset, reducing RMSE by up to 14.2 percent relative to the strongest baseline. It also achieves the lowest continuous ranked probability score (CRPS) at horizons h = 4, 5, 6 on every dataset, with reductions of up to 43 percent relative to the strongest probabilistic baseline. During the abnormal 2019-2020 influenza season, EPI-SST reduces CRPS by 16.9 percent and calibration error by 78.9 percent; a three-seed replication preserves its distributional lead. Ablation studies and frozen-path interventions show that the renewal transition, attention conditioning, horizon coupling, and uncertainty-scale control make complementary contributions to predictive performance.


翻译:暂无翻译

0
下载
关闭预览

相关内容

VIP会员
最新内容
《美空军2026条令文件:对海压制作战》
专知会员服务
25+阅读 · 11月9日
人工智能与战争的未来
专知会员服务
10+阅读 · 11月8日
《Agent Mosaic:识别智能体LLM系统中的机密泄露》
专知会员服务
12+阅读 · 11月8日
人工智能在军事教育中的应用:若干视角与经验
专知会员服务
13+阅读 · 11月6日
“星链”减速与不断适应的乌克兰
专知会员服务
10+阅读 · 11月6日
美国中期选举之后:帕兰提尔面临不确定性?
专知会员服务
7+阅读 · 11月6日
Top
微信扫码咨询专知VIP会员