Weak SINDy for partial differential equations

DA Messenger, DM Bortz - Journal of Computational Physics, 2021 - Elsevier
Abstract Sparse Identification of Nonlinear Dynamics (SINDy) is a method of system
discovery that has been shown to successfully recover governing dynamical systems from …

Towards data-driven discovery of governing equations in geosciences

W Song, S Jiang, G Camps-Valls, M Williams… - … Earth & Environment, 2024 - nature.com
Governing equations are foundations for modelling, predicting, and understanding the Earth
system. The Earth system is undergoing rapid change, and the conventional approaches for …

Data-driven deep learning of partial differential equations in modal space

K Wu, D **u - Journal of Computational Physics, 2020 - Elsevier
We present a framework for recovering/approximating unknown time-dependent partial
differential equation (PDE) using its solution data. Instead of identifying the terms in the …

Weak SINDy: Galerkin-based data-driven model selection

DA Messenger, DM Bortz - Multiscale Modeling & Simulation, 2021 - SIAM
We present a novel weak formulation and discretization for discovering governing equations
from noisy measurement data. This method of learning differential equations from data fits …

Data-driven prediction of general Hamiltonian dynamics via learning exactly-symplectic maps

R Chen, M Tao - International Conference on Machine …, 2021 - proceedings.mlr.press
We consider the learning and prediction of nonlinear time series generated by a latent
symplectic map. A special case is (not necessarily separable) Hamiltonian systems, whose …

Deep neural network modeling of unknown partial differential equations in nodal space

Z Chen, V Churchill, K Wu, D **u - Journal of Computational Physics, 2022 - Elsevier
We present a numerical framework for deep neural network (DNN) modeling of unknown
time-dependent partial differential equation (PDE) using their trajectory data. Unlike the …

Learning interaction kernels in heterogeneous systems of agents from multiple trajectories

F Lu, M Maggioni, S Tang - Journal of Machine Learning Research, 2021 - jmlr.org
Systems of interacting particles, or agents, have wide applications in many disciplines,
including Physics, Chemistry, Biology and Economics. These systems are governed by …

Partial differential equations discovery with EPDE framework: Application for real and synthetic data

M Maslyaev, A Hvatov, AV Kalyuzhnaya - Journal of Computational Science, 2021 - Elsevier
Data-driven methods provide model creation tools for systems where the application of
conventional analytical methods is restrained. The proposed method involves the data …

On generalized residual network for deep learning of unknown dynamical systems

Z Chen, D **u - Journal of Computational Physics, 2021 - Elsevier
We present a general numerical approach for learning unknown dynamical systems using
deep neural networks (DNNs). Our method is built upon recent studies that identified …

A Comprehensive Review of Latent Space Dynamics Identification Algorithms for Intrusive and Non-Intrusive Reduced-Order-Modeling

C Bonneville, X He, A Tran, JS Park, W Fries… - arxiv preprint arxiv …, 2024 - arxiv.org
Numerical solvers of partial differential equations (PDEs) have been widely employed for
simulating physical systems. However, the computational cost remains a major bottleneck in …