Learning Epidemiological Dynamics via the Finite Expression Method

TL;DR

This paper presents the Finite Expression Method, a symbolic learning approach using reinforcement learning to derive interpretable mathematical models for infectious disease dynamics, achieving high accuracy and revealing explicit epidemiological relationships.

Contribution

It introduces a novel symbolic learning framework that combines reinforcement learning with explicit expression derivation for epidemiological modeling, enhancing interpretability and predictive accuracy.

Findings

FEX accurately models disease spread on synthetic and real data.

It uncovers explicit relationships among epidemiological variables.

Demonstrates high predictive performance with interpretable models.

Abstract

Modeling and forecasting the spread of infectious diseases is essential for effective public health decision-making. Traditional epidemiological models rely on expert-defined frameworks to describe complex dynamics, while neural networks, despite their predictive power, often lack interpretability due to their ``black-box" nature. This paper introduces the Finite Expression Method, a symbolic learning framework that leverages reinforcement learning to derive explicit mathematical expressions for epidemiological dynamics. Through numerical experiments on both synthetic and real-world datasets, FEX demonstrates high accuracy in modeling and predicting disease spread, while uncovering explicit relationships among epidemiological variables. These results highlight FEX as a powerful tool for infectious disease modeling, combining interpretability with strong predictive performance to support practical applications in public health.