Learning Coupled System Dynamics under Incomplete Physical Constraints and Missing Data
This addresses a fundamental challenge in physics-informed machine learning for partially observed systems, though it is an incremental improvement over existing methods.
The paper tackles the problem of modeling coupled systems when governing equations are only known for some variables and data is available only for others, by introducing MUSIC, a multitask neural network framework that integrates partial physical constraints with data-driven learning, which accurately learns solutions and outperforms non-sparse formulations under data-scarce and noisy conditions.
Advances in data acquisition and computational methods have accelerated the use of differential equation based modelling for complex systems. Such systems are often described by coupled (or more) variables, yet governing equation is typically available for one variable, while the remaining variable can be accessed only through data. This mismatch between known physics and observed data poses a fundamental challenge for existing physics-informed machine learning approaches, which generally assume either complete knowledge of the governing equations or full data availability across all variables. In this paper, we introduce MUSIC (Multitask Learning Under Sparse and Incomplete Constraints), a sparsity induced multitask neural network framework that integrates partial physical constraints with data-driven learning to recover full-dimensional solutions of coupled systems when physics-constrained and data-informed variables are mutually exclusive. MUSIC employs mesh-free (random) sampling of training data and sparsity regularization, yielding highly compressed models with improved training and evaluation efficiency. We demonstrate that MUSIC accurately learns solutions (shock wave solutions, discontinuous solutions, pattern formation solutions) to complex coupled systems under data-scarce and noisy conditions, consistently outperforming non-sparse formulations. These results highlight MUSIC as a flexible and effective approach for modeling partially observed systems with incomplete physical knowledge.