Data augmentation and feature selection for automatic model recommendation in computational physics

TL;DR

This paper presents novel algorithms for feature selection and data augmentation tailored to physics data, improving classification accuracy in computational physics applications despite limited and high-dimensional training data.

Contribution

Introduces two algorithms specifically designed for feature selection and data augmentation in physics-based classification tasks, addressing key challenges of data scarcity and high dimensionality.

Findings

Achieved 90% accuracy with ensemble classifiers on nonlinear structural mechanics data.

Demonstrated effectiveness of tailored data augmentation for physics data.

Validated the combined approach across various classifiers.

Abstract

Classification algorithms have recently found applications in computational physics for the selection of numerical methods or models adapted to the environment and the state of the physical system. For such classification tasks, labeled training data come from numerical simulations and generally correspond to physical fields discretized on a mesh. Three challenging difficulties arise: the lack of training data, their high dimensionality, and the non-applicability of common data augmentation techniques to physics data. This article introduces two algorithms to address these issues, one for dimensionality reduction via feature selection, and one for data augmentation. These algorithms are combined with a wide variety of classifiers for their evaluation. When combined with a stacking ensemble made of six multilayer perceptrons and a ridge logistic regression, they enable reaching an accuracy of 90% on our classification problem for nonlinear structural mechanics.