Deep level-set method for Stefan problems

Mykhaylo Shkolnikov, H. Mete Soner, Valentin Tissot-Daguette

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

We propose a level-set approach to characterize the region occupied by the solid in Stefan problems with and without surface tension, based on their recent probabilistic reformulation. The level-set function is parameterized by a feed-forward neural network, whose parameters are trained using the probabilistic formulation of the Stefan growth condition. The algorithm can handle Stefan problems where the liquid is supercooled and can capture surface tension effects through the simulation of particles along the moving boundary together with an efficient approximation of the mean curvature. We demonstrate the effectiveness of the method on a variety of examples with and without radial symmetry.

Original languageEnglish (US)
Article number112828
JournalJournal of Computational Physics
Volume503
DOIs
StatePublished - Apr 15 2024

All Science Journal Classification (ASJC) codes

  • Numerical Analysis
  • Modeling and Simulation
  • Physics and Astronomy (miscellaneous)
  • General Physics and Astronomy
  • Computer Science Applications
  • Computational Mathematics
  • Applied Mathematics

Keywords

  • Level-set method
  • Mushy region
  • Neural networks
  • Probabilistic solutions
  • Stefan problem
  • Surface tension

Fingerprint

Dive into the research topics of 'Deep level-set method for Stefan problems'. Together they form a unique fingerprint.

Cite this