GMLS-Nets: Scientific Machine Learning Methods for Unstructured Data
- US Department of Energy
Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gaining benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a nonparametric technique for estimating linear bounded functionals from scattered data, and has recently been used in the literature for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators and to regress quantities of interest. The results suggest the architectures to be an attractive foundation for data-driven model development in scientific machine learning applications
- Research Organization:
- University of California Santa Barbara
- Sponsoring Organization:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
- DOE Contract Number:
- SC0019246
- OSTI ID:
- 1633915
- Country of Publication:
- United States
- Language:
- English
Similar Records
GMLS-Nets: A Framework for Learning from Unstructured Data
Parameterized Pseudo-Differential Operators for Applying CNNs to Unstructured Mesh Data