A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge

Abstract

Discovering a meaningful symbolic expression that explains experimental data is a fundamental challenge in many scientific fields. We present a novel, open-source computational framework called Scientist-Machine Equation Detector (SciMED), which integrates scientific discipline wisdom in a scientist-in-the-loop approach, with state-of-the-art symbolic regression (SR) methods. SciMED combines a wrapper selection method, that is based on a genetic algorithm, with automatic machine learning and two levels of SR methods. We test SciMED on five configurations of a settling sphere, with and without aerodynamic non-linear drag force, and with excessive noise in the measurements. We show that SciMED is sufficiently robust to discover the correct physically meaningful symbolic expressions from the data, and demonstrate how the integration of domain knowledge enhances its performance. Our results indicate better performance on these tasks than the state-of-the-art SR software packages , even in cases where no knowledge is integrated. Moreover, we demonstrate how SciMED can alert the user about possible missing features, unlike the majority of current SR systems.

References in corpus (8)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• A Survey of Deep Meta-Learning
• PySINDy: A comprehensive Python package for robust sparse system identification
• Contemporary Symbolic Regression Methods and their Relative Performance
• Robust learning from noisy, incomplete, high-dimensional experimental data via physically constrained symbolic regression
• Feature engineering and symbolic regression methods for detecting hidden physics from sparse sensors
• Shape-constrained Symbolic Regression -- Improving Extrapolation with Prior Knowledge
• Symbolic Regression by Exhaustive Search: Reducing the Search Space Using Syntactical Constraints and Efficient Semantic Structure Deduplication

Cited by in corpus (15)

• Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical laws
• Symbolic Regression as Feature Engineering Method for Machine and Deep Learning Regression Tasks
• Knowledge-integrated AutoEncoder Model
• SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for Compression
• Inferring the Equation of State from Neutron Star Observables via Machine Learning
• The Scientometrics and Reciprocality Underlying Co-Authorship Panels in Google Scholar Profiles
• SymbolFit: Automatic Parametric Modeling with Symbolic Regression
• Discovering Nuclear Models from Symbolic Machine Learning
• Using machine learning to find exact analytic solutions to analytically posed physics problems
• Individual Variation Affects Outbreak Magnitude and Predictability in an Extended Multi-Pathogen SIR Model of Pigeons Vising Dairy Farms
• Improved Prediction of Settling Behaviour of Solid Particles through Machine Learning Analysis of Experimental Retention Time Data
• Machine learning-guided construction of an analytic kinetic energy functional for orbital free density functional theory
• SPINEX_ Symbolic Regression: Similarity-based Symbolic Regression with Explainable Neighbors Exploration
• Universal nonanalytic features in response functions of anisotropic superconductors
• Deep learning of thermodynamic laws from microscopic dynamics