A physics-informed neural network method for the approximation of slow invariant manifolds for the general class of stiff systems of ODEs
arXiv:2403.11591 · doi:10.1137/24M1656402
Abstract
We present a physics-informed neural network (PINN) approach for the discovery of slow invariant manifolds (SIMs), for the most general class of fast/slow dynamical systems of ODEs. In contrast to other machine learning (ML) approaches that construct reduced order black box surrogate models using simple regression, and/or require a priori knowledge of the fast and slow variables, our approach, simultaneously decomposes the vector field into fast and slow components and provides a functional of the underlying SIM in a closed form. The decomposition is achieved by finding a transformation of the state variables to the fast and slow ones, which enables the derivation of an explicit, in terms of fast variables, SIM functional. The latter is obtained by solving a PDE corresponding to the invariance equation within the Geometric Singular Perturbation Theory (GSPT) using a single-layer feedforward neural network with symbolic differentiation. The performance of the proposed physics-informed ML framework is assessed via three benchmark problems: the Michaelis-Menten, the target mediated drug disposition (TMDD) reaction model and a fully competitive substrate-inhibitor(fCSI) mechanism. We also provide a comparison with other GPST methods, namely the quasi steady state approximation (QSSA), the partial equilibrium approximation (PEA) and CSP with one and two iterations. We show that the proposed PINN scheme provides SIM approximations, of equivalent or even higher accuracy, than those provided by QSSA, PEA and CSP, especially close to the boundaries of the underlying SIMs.
References in corpus (18)
- Deep learning for universal linear embeddings of nonlinear dynamics
- Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
- Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration
- A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
- Constructive Methods of Invariant Manifolds for Kinetic Problems
- A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
- Coarse-scale PDEs from fine-scale observations via machine learning
- Differential Geometry and Mechanics Applications to Chaotic Dynamical Systems
- Analysis of the accuracy and convergence of equation-free projection to a slow manifold
- Reduced-space Gaussian Process Regression for Data-Driven Probabilistic Forecast of Chaotic Dynamical Systems
- Constructing coarse-scale bifurcation diagrams from spatio-temporal observations of microscopic simulations: A parsimonious machine learning approach
- Slow invariant manifolds as curvature of the flow of dynamical systems
- Data-driven Control of Agent-based Models: an Equation/Variable-free Machine Learning Approach
- Double Diffusion Maps and their Latent Harmonics for Scientific Computations in Latent Space
- Data-driven modelling of brain activity using neural networks, Diffusion Maps, and the Koopman operator
- Slow Invariant Manifolds of Singularly Perturbed Systems via Physics-Informed Machine Learning
- From partial data to out-of-sample parameter and observation estimation with Diffusion Maps and Geometric Harmonics
- Optimal criteria and their asymptotic form for data selection in data-driven reduced-order modeling with Gaussian process regression