DEpiABS: Differentiable Epidemic Agent-Based Simulator

2026-02-12

AI Summary

Existing epidemic simulation tools struggle to simultaneously achieve computational efficiency, interpretability, and accurate representation of complex individual behaviors and dynamic epidemic processes such as viral mutation and reinfection. This work proposes the first individual-based epidemic simulator that integrates mechanistic detail, differentiability, and scalability, incorporating heterogeneous individual health states, behavioral variation, and resource constraints. By introducing a z-score scaling method, the framework enables efficient cross-scale mapping without auxiliary data, supporting gradient-based optimization, parameter calibration, and sensitivity analysis while maintaining high-fidelity predictions. Evaluated on COVID-19 mortality and influenza-like illness data, the model reduces the mean normalized error from 0.97 to 0.92 and from 0.41 to 0.32, respectively, demonstrating significantly improved predictive accuracy and generalization capability.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Security and Privacy: Large-scale security measurements

Abstract

The COVID-19 pandemic highlighted the limitations of existing epidemic simulation tools. These tools provide information that guides non-pharmaceutical interventions (NPIs), yet many struggle to capture complex dynamics while remaining computationally practical and interpretable. We introduce DEpiABS, a scalable, differentiable agent-based model (DABM) that balances mechanistic detail, computational efficiency and interpretability. DEpiABS captures individual-level heterogeneity in health status, behaviour, and resource constraints, while also modelling epidemic processes like viral mutation and reinfection dynamics. The model is fully differentiable, enabling fast simulation and gradient-based parameter calibration. Building on this foundation, we introduce a z-score-based scaling method that maps small-scale simulations to any real-world population sizes with negligible loss in output granularity, reducing the computational burden when modelling large populations. We validate DEpiABS through sensitivity analysis and calibration to COVID-19 and flu data from ten regions of varying scales. Compared to the baseline, DEpiABS is more detailed, fully interpretable, and has reduced the average normal deviation in forecasting from 0.97 to 0.92 on COVID-19 mortality data and from 0.41 to 0.32 on influenza-like-illness data. Critically, these improvements are achieved without relying on auxiliary data, making DEpiABS a reliable, generalisable, and data-efficient framework for future epidemic response modelling.

Problem

• epidemic simulation
• non-pharmaceutical interventions
• agent-based modeling
• computational efficiency
• model interpretability

Innovation

• differentiable simulation
• agent-based modeling
• epidemic forecasting
• gradient-based calibration
• population scaling