Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Ecological Connectivity to Outbreak Risk: A Heterogeneous Graph Network for Epidemiological Reasoning under Sparse Spatiotemporal Data

Haley Stone, Jing Du, Yang Yang, Ashna Desai, Rebecca Dawson, Hao Xue, David Heslop, Matthew Scotch, Andreas Züfle, C. Raina MacIntyre, Flora Salim

TL;DR

ZooNet is developed, 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 to show persistence and spatial risk structure to be inferred from detection-driven wildlife surveillance data.

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.

From Ecological Connectivity to Outbreak Risk: A Heterogeneous Graph Network for Epidemiological Reasoning under Sparse Spatiotemporal Data

TL;DR

ZooNet is developed, 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 to show persistence and spatial risk structure to be inferred from detection-driven wildlife surveillance data.

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.
Paper Structure (15 sections, 5 equations, 4 figures, 1 table)

This paper contains 15 sections, 5 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Overview of zooNet
  3. Emergent Flyway Patterns of Transmission
  4. Spatiotemporal Variability in Prediction
  5. Migration Bottlenecks as Amplifiers of Viral Spread
  6. Discussion
  7. Methods
  8. Graph Construction and Layer Definition
  9. Cross-layer Smoothing and Graph Fusion
  10. Temporal Graph Sequence Modelling
  11. Augmented case simulation via ecologically structured SEI modelling
  12. Genetic distance imputation for unsequenced and augmented cases
  13. Experimental Setup
  14. Ablation Study
  15. zooNet Dataset

Figures (4)

  • 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 metadata-driven quantile regression model. Cases are represented as nodes in a multilayer graph, linked by spatial, temporal, and genetic edges. Graph fusion and cross-layer smoothing are applied to unify these relationships, and temporal dynamics are captured through an autoregressive graph encoder–decoder.
  • Figure 2: Effect of module removal on prediction error and standard deviation across flyways.
  • Figure 3: County-level case forecasts for the United States, stratified by avian flyway, simulated by zooNet, covering the weeks 31 January - 30 October 2022.
  • Figure 4: Weekly simulated prevalence, shown as percentage per 10,000, of A/H5 avian influenza in wild birds across North American states covering the weeks 31 January - 30 October 2022.