Learning effective good variables from physical data

Abstract

We assume that a sufficiently large database is available, where a physical property of interest and a number of associated ruling primitive variables or observables are stored. We introduce and test two machine learning approaches to discover possible groups or combinations of primitive variables: The first approach is based on regression models whereas the second on classification models. The variable group (here referred to as the new effective good variable) can be considered as successfully found, when the physical property of interest is characterized by the following effective invariant behaviour: In the first method, invariance of the group implies invariance of the property up to a given accuracy; in the other method, upon partition of the physical property values into two or more classes, invariance of the group implies invariance of the class. For the sake of illustration, the two methods are successfully applied to two popular empirical correlations describing the convective heat transfer phenomenon and to the Newton's law of universal gravitation.

arXiv comment24 pages (main), 8 pages (suppi), 12 figures (main), 3 figures (suppi)

References in corpus (12)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Simulation-based optimal Bayesian experimental design for nonlinear systems
• Sparse Identification of Nonlinear Dynamics for Rapid Model Recovery
• iMapD: intrinsic Map Dynamics exploration for uncharted effective free energy landscapes
• Data-driven discovery of intrinsic dynamics
• Bayesian optimization package: PHYSBO
• Data-driven model reduction, Wiener projections, and the Koopman-Mori-Zwanzig formalism
• Reduced models in chemical kinetics via nonlinear data-mining
• Quasi Equilibrium Grid Algorithm: geometric construction for model reduction
• Approximation of slow and fast dynamics in multiscale dynamical systems by the linearized Relaxation Redistribution Method
• Leveraging Composition-Based Material Descriptors for Machine Learning Optimization

Cited by in corpus (1)

• Classification-based detection and quantification of cross-domain data bias in materials discovery