Promising directions of machine learning for partial differential equations

SL Brunton, JN Kutz - Nature Computational Science, 2024 - nature.com
Partial differential equations (PDEs) are among the most universal and parsimonious
descriptions of natural physical laws, capturing a rich variety of phenomenology and …

Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control

U Fasel, JN Kutz, BW Brunton… - Proceedings of the …, 2022 - royalsocietypublishing.org
Sparse model identification enables the discovery of nonlinear dynamical systems purely
from data; however, this approach is sensitive to noise, especially in the low-data limit. In this …

Learning dynamical models of single and collective cell migration: a review

D Brückner, CP Broedersz - Reports on Progress in Physics, 2024 - iopscience.iop.org
Single and collective cell migration are fundamental processes critical for physiological
phenomena ranging from embryonic development and immune response to wound healing …

Deeptime: a Python library for machine learning dynamical models from time series data

M Hoffmann, M Scherer, T Hempel… - Machine Learning …, 2021 - iopscience.iop.org
Generation and analysis of time-series data is relevant to many quantitative fields ranging
from economics to fluid mechanics. In the physical sciences, structures such as metastable …

Parsimony as the ultimate regularizer for physics-informed machine learning

JN Kutz, SL Brunton - Nonlinear Dynamics, 2022 - Springer
Data-driven modeling continues to be enabled by modern machine learning algorithms and
deep learning architectures. The goals of such efforts revolve around the generation of …

Physics-constrained, low-dimensional models for magnetohydrodynamics: First-principles and data-driven approaches

AA Kaptanoglu, KD Morgan, CJ Hansen, SL Brunton - Physical Review E, 2021 - APS
Plasmas are highly nonlinear and multiscale, motivating a hierarchy of models to
understand and describe their behavior. However, there is a scarcity of plasma models of …

Benchmarking sparse system identification with low-dimensional chaos

AA Kaptanoglu, L Zhang, ZG Nicolaou, U Fasel… - Nonlinear …, 2023 - Springer
Sparse system identification is the data-driven process of obtaining parsimonious differential
equations that describe the evolution of a dynamical system, balancing model complexity …

Sparse nonlinear models of chaotic electroconvection

Y Guan, SL Brunton… - Royal Society Open …, 2021 - royalsocietypublishing.org
Convection is a fundamental fluid transport phenomenon, where the large-scale motion of a
fluid is driven, for example, by a thermal gradient or an electric potential. Modelling …

Machine learning for partial differential equations

SL Brunton, JN Kutz - arxiv preprint arxiv:2303.17078, 2023 - arxiv.org
Partial differential equations (PDEs) are among the most universal and parsimonious
descriptions of natural physical laws, capturing a rich variety of phenomenology and multi …

An empirical mean-field model of symmetry-breaking in a turbulent wake

JL Callaham, G Rigas, JC Loiseau, SL Brunton - Science Advances, 2022 - science.org
Improved turbulence modeling remains a major open problem in mathematical physics.
Turbulence is notoriously challenging, in part due to its multiscale nature and the fact that …