Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning

Abstract

Experimental data is often affected by uncontrolled variables that make analysis and interpretation difficult. For spatiotemporal systems, this problem is further exacerbated by their intricate dynamics. Modern machine learning methods are particularly well-suited for analyzing and modeling complex datasets, but to be effective in science, the result needs to be interpretable. We demonstrate an unsupervised learning technique for extracting interpretable physical parameters from noisy spatiotemporal data and for building a transferable model of the system. In particular, we implement a physics-informed architecture based on variational autoencoders that is designed for analyzing systems governed by partial differential equations (PDEs). The architecture is trained end-to-end and extracts latent parameters that parameterize the dynamics of a learned predictive model for the system. To test our method, we train our model on simulated data from a variety of PDEs with varying dynamical parameters that act as uncontrolled variables. Numerical experiments show that our method can accurately identify relevant parameters and extract them from raw and even noisy spatiotemporal data (tested with roughly 10% added noise). These extracted parameters correlate well (linearly with $R^2>0.95$) with the ground truth physical parameters used to generate the datasets. We then apply this method to nonlinear fiber propagation data, generated by an ab-initio simulation, to demonstrate its capabilities on a more realistic dataset. Our method for discovering interpretable latent parameters in spatiotemporal systems will allow us to better analyze and understand real-world phenomena and datasets, which often have unknown and uncontrolled variables that alter the system dynamics and cause varying behaviors that are difficult to disentangle.

arXiv comment19 pages, 9 figures, 2 tables

References in corpus (13)

• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Discovering physical concepts with neural networks
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• Variational Encoding of Complex Dynamics
• Data-driven discovery of PDEs in complex datasets
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks
• Emergent Quantum Mechanics in an Introspective Machine Learning Architecture

Cited by in corpus (17)

• Interpretable and Explainable Machine Learning for Materials Science and Chemistry
• AI Poincaré: Machine Learning Conservation Laws from Trajectories
• Unsupervised machine learning of topological phase transitions from experimental data
• Symbolic Pregression: Discovering Physical Laws from Distorted Video
• Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence
• Machine-Learning Non-Conservative Dynamics for New-Physics Detection
• Statistical physics through the lens of real-space mutual information
• Symmetries and phase diagrams with real-space mutual information neural estimation
• Constrained tandem neural network assisted inverse design of metasurfaces for microwave absorption
• Machine learning of Kondo physics using variational autoencoders and symbolic regression
• Decoding Structure-Spectrum Relationships with Physically Organized Latent Spaces
• Learning Order Parameters from Videos of Dynamical Phases for Skyrmions with Neural Networks
• Learning minimal representations of stochastic processes with variational autoencoders
• Explainable Representation Learning of Small Quantum States
• Discover the GellMann-Okubo formula with machine learning
• Interpretable Boosted Decision Tree Analysis for the Majorana Demonstrator
• Characterizing nonlinear dynamics by contrastive cartography