Level-Set Curvature Neural Networks: A Hybrid Approach

We present a hybrid strategy based on deep learning to compute mean curvature in the level-set method. The proposed inference system combines a dictionary of improved regression models with standard numerical schemes to estimate curvature more accurately. The core of our framework is a switching mechanism that relies on well-established numerical techniques to gauge curvature. If the curvature magnitude is larger than a resolution-dependent threshold, it uses a neural network to yield a better approximation. Our networks are multi-layer perceptrons fitted to synthetic data sets composed of circular- and sinusoidal-interface samples at various configurations. To reduce data set size and training complexity, we leverage the problem's characteristic symmetry and build our models on just half of the curvature spectrum. These savings result in compact networks able to outperform any of the system's numerical or neural component alone. Experiments with static interfaces show that our hybrid approach is suitable and notoriously superior to conventional numerical methods in under-resolved and steep, concave regions. Compared to prior research, we have observed outstanding gains in precision after including training data pairs from more than a single interface type and other means of input preprocessing. In particular, our findings confirm that machine learning is a promising venue for devising viable solutions to the level-set method's numerical shortcomings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/18/2022

Machine learning algorithms for three-dimensional mean-curvature computation in the level-set method

We propose a data-driven mean-curvature solver for the level-set method....
research
02/04/2020

A Deep Learning Approach for the Computation of Curvature in the Level-Set Method

We propose a deep learning strategy to compute the mean curvature of an ...
research
01/22/2022

Error-Correcting Neural Networks for Two-Dimensional Curvature Computation in the Level-Set Method

We present an error-neural-modeling-based strategy for approximating two...
research
12/14/2021

Learning phase field mean curvature flows with neural networks

We introduce in this paper new, efficient numerical methods based on neu...
research
05/14/2021

A numerical stability analysis of mean curvature flow of noncompact hypersurfaces with Type-II curvature blowup

We present a numerical study of the local stability of mean curvature fl...
research
04/23/2021

Consistent and symmetry preserving data-driven interface reconstruction for the level-set method

Recently, machine learning has been used to substitute parts of conventi...
research
05/21/2021

Dewetting dynamics of anisotropic particles – a level set numerical approach

We extend thresholding methods for numerical realization of mean curvatu...

Please sign up or login with your details

Forgot password? Click here to reset