Graph Neural Ordinary Differential Equations for Coarse-Grained Socioeconomic Dynamics
This work addresses the problem of modeling complex socioeconomic systems for policymakers and researchers, offering a method for expedited 'what if' studies and sensitivity analyses, though it appears incremental in applying existing techniques to a specific domain.
The researchers tackled modeling complex socioeconomic dynamics by developing a data-driven machine learning approach that coarse-grains fine-scale observations into tractable ordinary differential equations, preserving critical behaviors. Their case study in Baltimore, MD, demonstrated this model as a powerful tool for understanding interactions between social factors, geography, and stressors, enabling forecasting and resilience planning.
We present a data-driven machine-learning approach for modeling space-time socioeconomic dynamics. Through coarse-graining fine-scale observations, our modeling framework simplifies these complex systems to a set of tractable mechanistic relationships -- in the form of ordinary differential equations -- while preserving critical system behaviors. This approach allows for expedited 'what if' studies and sensitivity analyses, essential for informed policy-making. Our findings, from a case study of Baltimore, MD, indicate that this machine learning-augmented coarse-grained model serves as a powerful instrument for deciphering the complex interactions between social factors, geography, and exogenous stressors, offering a valuable asset for system forecasting and resilience planning.