MiCA: A Mobility-Informed Causal Adapter for Lightweight Epidemic Forecasting

2026-01-16

AI Summary

This work addresses the challenge of infectious disease forecasting, which is often hindered by noisy and indirect human mobility data alongside short, coarse-grained epidemic time series, limiting the effectiveness of complex models that rely on high-quality, large-scale data. To overcome this, the authors propose MiCA, a lightweight and architecture-agnostic module that infers inter-regional mobility relationships through causal discovery and integrates them into temporal prediction models via a gated residual mixing mechanism. Notably, MiCA leverages spatial structure without requiring graph neural networks or full attention mechanisms, maintaining model efficiency while enhancing predictive accuracy. Evaluated on four real-world epidemiological datasets—covering COVID-19 incidence and mortality, influenza, and dengue fever—the method achieves an average 7.5% reduction in relative error, matching the performance of state-of-the-art spatiotemporal models.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate forecasting of infectious disease dynamics is critical for public health planning and intervention. Human mobility plays a central role in shaping the spatial spread of epidemics, but mobility data are noisy, indirect, and difficult to integrate reliably with disease records. Meanwhile, epidemic case time series are typically short and reported at coarse temporal resolution. These conditions limit the effectiveness of parameter-heavy mobility-aware forecasters that rely on clean and abundant data. In this work, we propose the Mobility-Informed Causal Adapter (MiCA), a lightweight and architecture-agnostic module for epidemic forecasting. MiCA infers mobility relations through causal discovery and integrates them into temporal forecasting models via gated residual mixing. This design allows lightweight forecasters to selectively exploit mobility-derived spatial structure while remaining robust under noisy and data-limited conditions, without introducing heavy relational components such as graph neural networks or full attention. Extensive experiments on four real-world epidemic datasets, including COVID-19 incidence, COVID-19 mortality, influenza, and dengue, show that MiCA consistently improves lightweight temporal backbones, achieving an average relative error reduction of 7.5\% across forecasting horizons. Moreover, MiCA attains performance competitive with SOTA spatio-temporal models while remaining lightweight.

Problem

• epidemic forecasting
• human mobility
• noisy data
• lightweight modeling
• spatio-temporal prediction

Innovation

• causal discovery
• gated residual mixing
• lightweight forecasting
• mobility-informed modeling
• epidemic prediction