REVIEW 8 cited by
Scientific machine learning for closure models in multiscale problems: a review
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Scientific machine learning for closure models in multiscale problems: a review
read the original abstract
Closure problems are omnipresent when simulating multiscale systems, where some quantities and processes cannot be fully prescribed despite their effects on the simulation's accuracy. Recently, scientific machine learning approaches have been proposed as a way to tackle the closure problem, combining traditional (physics-based) modeling with data-driven (machine-learned) techniques, typically through enriching differential equations with neural networks. This paper reviews the different reduced model forms, distinguished by the degree to which they include known physics, and the different objectives of a priori and a posteriori learning. The importance of adhering to physical laws (such as symmetries and conservation laws) in choosing the reduced model form and choosing the learning method is discussed. The effect of spatial and temporal discretization and recent trends toward discretization-invariant models are reviewed. In addition, we make the connections between closure problems and several other research disciplines: inverse problems, Mori-Zwanzig theory, and multi-fidelity methods. In conclusion, much progress has been made with scientific machine learning approaches for solving closure problems, but many challenges remain. In particular, the generalizability and interpretability of learned models is a major issue that needs to be addressed further.
Forward citations
Cited by 8 Pith papers
-
A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds
MEEC equips point clouds with a discrete exterior calculus that satisfies exact conservation and is differentiable in point positions, allowing a single trained kernel to produce compatible physics on unseen geometrie...
-
Why Does the Future Branch? Identifiable Closure Tests for Stochastic Physical World Models
ClosurePairs uses paired microstate and disturbance interventions with variance decomposition to identify whether future branching is caused by state aliasing or process noise, which ordinary prediction scores cannot.
-
Generalized Forcing Method: Generation of Diverse Data for Training Linear Transport PDE Closure Models
Generalized Forcing Method generates diverse data for training linear transport PDE closure models via compatible body forces in zero-initial-condition simulations, with explicit and implicit variants applied to shear...
-
Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows
Conditional normalizing flows learn a probabilistic mapping from low-fidelity to high-fidelity ROM coefficients for closure correction in 2D Navier-Stokes vortex merging, with direct and residual strategies providing ...
-
Wavelet Flow Matching for Multi-Scale Physics Emulation
Wavelet Flow Matching emulates multi-scale PDE-governed systems by transporting velocities directly in a hierarchical wavelet representation via U-Net, yielding improved long-horizon stability and spectral accuracy on...
-
Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics
Case study applies SAE probing with enstrophy triage to a continuum-dynamics foundation model and reports intermittent feature consistency that does not align with standard physics while linking some output discrepanc...
-
Hybrid Neural Ordinary Differential Equations for Data-Efficient Polymerization Modeling with Incomplete Kinetics
Hybrid NODE retains mechanistic kinetics for free-radical polymerization and learns only the radical concentration closure, achieving RMSE 0.013 on noisy unseen conditions versus 0.31 and 0.68 for data-driven baseline...
-
Multiscale Physics-Informed Neural Network for Complex Fluid Flows with Long-Range Dependencies
DDS-PINN uses localized neural networks plus a unified global loss to model multiscale fluid flows with long-range dependencies, achieving CFD-comparable accuracy on laminar backward-facing step flow with zero data an...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.