Weak Form Scientific Machine Learning: Test Function Construction for System Identification
–arXiv.org Artificial Intelligence
Weak form Scientific Machine Learning (WSciML) is a recently developed framework for data-driven modeling and scientific discovery. It leverages the weak form of equation error residuals to provide enhanced noise robustness in system identification via convolving model equations with test functions, reformulating the problem to avoid direct differentiation of data. The performance, however, relies on wisely choosing a set of compactly supported test functions. In this work, we mathematically motivate a novel data-driven method for constructing Single-scale-Local reference functions for creating the set of test functions. Our approach numerically approximates the integration error introduced by the quadrature and identifies the support size for which the error is minimal, without requiring access to the model parameter values. Through numerical experiments across various models, noise levels, and temporal resolutions, we demonstrate that the selected supports consistently align with regions of minimal parameter estimation error. We also compare the proposed method against the strategy for constructing Multi-scale-Global (and orthogonal) test functions introduced in our prior work, demonstrating the improved computational efficiency.
arXiv.org Artificial Intelligence
Jul-8-2025
- Country:
- North America > United States
- Colorado > Boulder County
- Boulder (0.14)
- District of Columbia > Washington (0.04)
- Florida > Palm Beach County
- Boca Raton (0.04)
- New Jersey > Hudson County
- Hoboken (0.04)
- New Mexico > Los Alamos County
- Los Alamos (0.04)
- New York > New York County
- New York City (0.04)
- Virginia > Hampton (0.04)
- Colorado > Boulder County
- North America > United States
- Genre:
- Overview (0.67)
- Research Report (0.50)
- Technology: