Skip to main content
QUICK REVIEW

[论文解读] From Ecological Connectivity to Outbreak Risk: A Heterogeneous Graph Network for Epidemiological Reasoning under Sparse Spatiotemporal Data

Haley Stone, Jing Du|arXiv (Cornell University)|Jan 8, 2026
Zoonotic diseases and public health被引用 0
一句话总结

ZooNet 是一个基于图的方法框架,融合生态传输仿真、元数据驱动的基因距离推断和时空图学习,用于在稀疏监测下推断美国 A/H5 禽流感的爆发动态。

ABSTRACT

Estimating population-level prevalence and transmission dynamics of wildlife pathogens can be challenging, partly because surveillance data is sparse, detection-driven, and unevenly sequenced. Using highly pathogenic avian influenza A/H5 clade 2.3.4.4b as a case study, we develop zooNet, a graph-based epidemiological framework that integrates mechanistic transmission simulation, metadata-driven genetic distance imputation, and spatiotemporal graph learning to reconstruct outbreak dynamics from incomplete observations. Applied to wild bird surveillance data from the United States during 2022, zooNet recovered coherent spatiotemporal structure despite intermittent detections, revealing sustained regional circulation across multiple migratory flyways. The framework consistently identified counties with ongoing transmission weeks to months before confirmed detections, including persistent activity in northeastern regions prior to documented re-emergence. These signals were detectable even in areas with sparse sequencing and irregular reporting. These results show that explicitly representing ecological processes and inferred genomic connectivity within a unified graph structure allows persistence and spatial risk structure to be inferred from detection-driven wildlife surveillance data.

研究动机与目标

  • 在稀疏、偏倚监测数据下,推动对野生动物人群水平流行率与传播的估计。
  • 开发一个模块化框架,将生态、基因组和流行病学信息融合为统一的图表示。
  • 在观测不全的情况下,实现爆发连通性与传播动态的推断。
  • 评估美国候鸟迁徙走廊中 A/H5 的时空传播模式。

提出的方法

  • 构建一个包含爆发事件与行政区域的双层异构图。
  • 用 SEI 基于生态仿真来扩增检测,生成合成感染事件。
  • 通过使用 K80 距离的元数据驱动分位数回归模型,对未测序或被扩增的病例的基因距离进行推断。
  • 通过跨层平滑和图融合,整合生态、遗传和空间关系,同时保持图的性质。
  • 使用自回归图编码器-解码器对随时间步进的动态进行建模。
  • 在美国鸟类走廊上通过交叉验证评估性能,并与基线方法进行比较。
Figure 1: zooNet integrates ecological simulation, genetic distance imputation, and multilayer graph learning to forecast the spread of avian influenza A/H5 in wild birds. SEI-based simulation generates synthetic infections using environmental and host factors. Genetic distances are imputed using a
Figure 1: zooNet integrates ecological simulation, genetic distance imputation, and multilayer graph learning to forecast the spread of avian influenza A/H5 in wild birds. SEI-based simulation generates synthetic infections using environmental and host factors. Genetic distances are imputed using a

实验结果

研究问题

  • RQ1在稀疏、检测驱动的监测下,ZooNet 是否能恢复 A/H5 爆发的时空结构的一致性?
  • RQ2生态连通性、遗传连通性与空间相关性如何协同预测走廊上的爆发风险?
  • RQ3结合 SEI 增强和基因距离推断的预测性能与信号效用如何?
  • RQ4在不同迁徙走廊及监测季节的进行中,性能有何变化?

主要发现

  • 即使检测间断,ZooNet 仍在美国迁徙走廊中产生了与 A/H5 风险相关的连贯时空模式。
  • 预测性能因走廊而异,大西洋走廊的均方误差(MSE)最低为 49.85 ± 10.48,太平洋走廊最高为 155.81 ± 48.91。
  • 检测的 F1 分数在中部走廊为 0.0565 ± 0.0233,在太平洋走廊为 0.1383 ± 0.0725,表明召回率高于精确度。
  • 预测趋势的皮尔逊相关在太平洋走廊最高(0.2173 ± 0.0644),在中部走廊最低(0.0950 ± 0.0280)。
  • 消融实验表明完整的 ZooNet 通常优于变体;SEI 增强与基因距离推断对各走廊的贡献存在差异。
  • 该框架捕捉到季节性与空间异质性,部分 counties 的预测爆发在某些确认为检测之前出现。
Figure 2: Effect of module removal on prediction error and standard deviation across flyways.
Figure 2: Effect of module removal on prediction error and standard deviation across flyways.

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。