Data-driven discovery of coordinates and governing equations
From MaRDI portal
Publication:5218490
Abstract: The discovery of governing equations from scientific data has the potential to transform data-rich fields that lack well-characterized quantitative descriptions. Advances in sparse regression are currently enabling the tractable identification of both the structure and parameters of a nonlinear dynamical system from data. The resulting models have the fewest terms necessary to describe the dynamics, balancing model complexity with descriptive ability, and thus promoting interpretability and generalizability. This provides an algorithmic approach to Occam's razor for model discovery. However, this approach fundamentally relies on an effective coordinate system in which the dynamics have a simple representation. In this work, we design a custom autoencoder to discover a coordinate transformation into a reduced space where the dynamics may be sparsely represented. Thus, we simultaneously learn the governing equations and the associated coordinate system. We demonstrate this approach on several example high-dimensional dynamical systems with low-dimensional behavior. The resulting modeling framework combines the strengths of deep neural networks for flexible representation and sparse identification of nonlinear dynamics (SINDy) for parsimonious models. It is the first method of its kind to place the discovery of coordinates and models on an equal footing.
Recommendations
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Weak SINDy: Galerkin-based data-driven model selection
- Data-driven discovery of PDEs in complex datasets
- Data-driven sparse identification of nonlinear dynamical systems using linear multistep methods
- Deep hidden physics models: deep learning of nonlinear partial differential equations
Cited in
(only showing first 100 items - show all)- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Hierarchical deep learning neural network (HiDeNN): an artificial intelligence (AI) framework for computational science and engineering
- Time-series learning of latent-space dynamics for reduced-order model closure
- Deep learning of conjugate mappings
- Towards out of distribution generalization for problems in mechanics
- Multiresolution convolutional autoencoders
- Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation
- Data-driven discovery of coarse-grained equations
- Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
- System identification through Lipschitz regularized deep neural networks
- Model reduction for multi-scale transport problems using model-form preserving least-squares projections with variable transformation
- Data-driven discovery of multiscale chemical reactions governed by the law of mass action
- Discovery of slow variables in a class of multiscale stochastic systems via neural networks
- Data-driven discovery of governing equations for transient heat transfer analysis
- Unsupervised discovery of interpretable hyperelastic constitutive laws
- A nonlocal physics-informed deep learning framework using the peridynamic differential operator
- Learning nonlinear state-space models using autoencoders
- LaSDI: parametric latent space dynamics identification
- Predicting shallow water dynamics using echo-state networks with transfer learning
- Output-weighted and relative entropy loss functions for deep learning precursors of extreme events
- Multi-fidelity surrogate modeling using long short-term memory networks
- Bayesian operator inference for data-driven reduced-order modeling
- Physics-informed neural networks for data-driven simulation: advantages, limitations, and opportunities
- Mini-workshop: Analysis of data-driven optimal control. Abstracts from the mini-workshop held May 9--15, 2021 (hybrid meeting)
- Robust data-driven discovery of governing physical laws with error bars
- Reconstruction of normal forms by learning informed observation geometries from data
- Kernel-based parameter estimation of dynamical systems with unknown observation functions
- scientific article; zbMATH DE number 7370558 (Why is no real title available?)
- Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Prediction
- Deep learning models for global coordinate transformations that linearise PDEs
- Equation discovery from data: promise and pitfalls, from rabbits to Mars
- Reduced operator inference for nonlinear partial differential equations
- Generative Adversarial Network for Probabilistic Forecast of Random Dynamical Systems
- The structure of reconstructed flows in latent spaces
- Discovering transition phenomena from data of stochastic dynamical systems with Lévy noise
- Extracting non-Gaussian governing laws from data on mean exit time
- Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
- Weak SINDy: Galerkin-based data-driven model selection
- SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics
- Bayesian differential programming for robust systems identification under uncertainty
- Physics-constrained, data-driven discovery of coarse-grained dynamics
- DL-PDE: Deep-Learning Based Data-Driven Discovery of Partial Differential Equations from Discrete and Noisy Data
- On the role of nonlinear correlations in reduced-order modelling
- Data-driven sparse identification of nonlinear dynamical systems using linear multistep methods
- Multiscale model reduction for incompressible flows
- Low-dimensional models of single neurons: a review
- Reduced-order autodifferentiable ensemble Kalman filters
- Spiral-wave dynamics in excitable media: insights from dynamic mode decomposition
- Learning sparse nonlinear dynamics via mixed-integer optimization
- Deep learning‐based reduced order models for the real‐time simulation of the nonlinear dynamics of microstructures
- Data-Driven Discovery of Governing Equations for Coarse-Grained Heterogeneous Network Dynamics
- A framework for machine learning of model error in dynamical systems
- Discovering interpretable Lagrangian of dynamical systems from data
- Adaptive learning of effective dynamics for online modeling of complex systems
- Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions
- Airfoil-based convolutional autoencoder and long short-term memory neural network for predicting coherent structures evolution around an airfoil
- gLaSDI: parametric physics-informed greedy latent space dynamics identification
- Parsimony as the ultimate regularizer for physics-informed machine learning
- Energy determines multiple stability in time-delayed systems
- GPLaSDI: Gaussian process-based interpretable latent space dynamics identification through deep autoencoder
- Kernel functions embed into the autoencoder to identify the sparse models of nonlinear dynamics
- A Review of Data‐Driven Discovery for Dynamic Systems
- Quantum Mechanics for Closure of Dynamical Systems
- Double diffusion maps and their latent harmonics for scientific computations in latent space
- Data driven discovery of systems of ordinary differential equations using nonconvex multitask learning
- Data-driven reduced order models using invariant foliations, manifolds and autoencoders
- Discovering efficient periodic behaviors in mechanical systems via neural approximators
- Discrepancy Modeling Framework: Learning Missing Physics, Modeling Systematic Residuals, and Disambiguating between Deterministic and Random Effects
- Learning the flux and diffusion function for degenerate convection-diffusion equations using different types of observations
- Reinforcement learning in non-Markovian environments
- A data-driven framework for learning hybrid dynamical systems
- Machine learning enhanced Hankel dynamic-mode decomposition
- Symbolic regression via neural networks
- Adaptive integral alternating minimization method for robust learning of nonlinear dynamical systems from highly corrupted data
- Generalized quadratic embeddings for nonlinear dynamics using deep learning
- Calibrating multi-dimensional complex ODE from noisy data via deep neural networks
- Hausdorff metric based training of kernels to learn attractors with application to 133 chaotic dynamical systems
- Deep learning enhanced dynamic mode decomposition
- Learning the temporal evolution of multivariate densities via normalizing flows
- Data-driven identification of dynamical models using adaptive parameter sets
- Data-driven reduced-order modeling of spatiotemporal chaos with neural ordinary differential equations
- Model selection of chaotic systems from data with hidden variables using sparse data assimilation
- Constructing differential equations using only a scalar time-series about continuous time chaotic dynamics
- Identifying causality drivers and deriving governing equations of nonlinear complex systems
- Regularized least absolute deviation-based sparse identification of dynamical systems
- Koopman neural operator as a mesh-free solver of non-linear partial differential equations
- Data augmentation-based statistical inference of diffusion processes
- Optimal reconstruction of vector fields from data for prediction and uncertainty quantification
- tLaSDI: thermodynamics-informed latent space dynamics identification
- On sparse regression, \(L_p\)-regularization, and automated model discovery
- Phase autoencoder for limit-cycle oscillators
- Deep learning in computational mechanics: a review
- Dynamical system identification, model selection, and model uncertainty quantification by Bayesian inference
- EKF-SINDy: empowering the extended Kalman filter with sparse identification of nonlinear dynamics
- \(\Phi\)-DVAE: physics-informed dynamical variational autoencoders for unstructured data assimilation
- Machine learning in viscoelastic fluids via energy-based kernel embedding
- Machine learning methods for reduced order modeling
- Forecasting and predicting stochastic agent-based model data with biologically-informed neural networks
- Approximation identification for the stochastic time-delayed dynamical system
- SDYN-GANs: adversarial learning methods for multistep generative models for general order stochastic dynamics
This page was built for publication: Data-driven discovery of coordinates and governing equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5218490)
