REVIEW 3 cited by
A penalized Allen-Cahn equation for the mean curvature flow of thin structures
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
read the original abstract
This paper addresses the approximation of the mean curvature flow of thin structures for which classical phase field methods are not suitable. By thin structures, we mean surfaces that are not domain boundaries, typically higher codimension objects such as 1D curves in 3D, i.e. filaments, or soap films spanning a boundary curve. To approximate the mean curvature flow of such surfaces, we consider a small thickening and we apply to the thickened set an evolution model that combines the classical Allen-Cahn equation with a penalty term that takes on larger values around the skeleton of the set. The novelty of our approach lies in the definition of this penalty term that guarantees a minimal thickness of the evolving set and prevents it from disappearing unexpectedly. We prove a few theoretical properties of our model, provide examples showing the connection with higher codimension mean curvature flow, and introduce a quasi-static numerical scheme with explicit integration of the penalty term. We illustrate the numerical efficiency of the model with accurate approximations of filament structures evolving by mean curvature flow, and we also illustrate its ability to find complex 3D approximations of solutions to the Steiner problem or the Plateau problem.
Forward citations
Cited by 3 Pith papers
-
Learning Gradient Flow: Using Equation Discovery to Accelerate Engineering Optimization
An optimizer that fits a SINDy polynomial model to recent optimization-variable trajectories and then integrates that surrogate flow instead of evaluating the true objective/gradient can cut gradient-evaluation counts...
-
Variational volume reconstruction with the Deep Ritz Method
A Deep Ritz variational method with a modified Cahn-Hilliard regularizer reconstructs volumes from sparse noisy slices without segmentation.
-
From inverse problems to neural operators: prediction, mechanism, and generalization of data-driven models
Data-driven models for physical systems share a common structure differing only in model class assumptions, with only mechanism-discovering models capable of generalization.
Discussion (0). Sign in to comment.