A novel sequential method to train physics informed neural networks for Allen Cahn and Cahn Hilliard equations
Top Cited Papers
- 4 January 2022
- journal article
- research article
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 390
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Science Foundation (1937983)
- National Science Foundation (ACI-1548562)
- National Science Foundation (MSS200004)
- National Science Foundation (CMMI MoMS)
This publication has 48 references indexed in Scilit:
- Physical, mathematical, and numerical derivations of the Cahn–Hilliard equationComputational Materials Science, 2014
- Precipitation in aqueous lithium–oxygen batteries: a model-based analysisEnergy & Environmental Science, 2013
- A Data-Driven Stochastic Method for Elliptic PDEs with Random CoefficientsSIAM/ASA Journal on Uncertainty Quantification, 2013
- THERMODYNAMICALLY CONSISTENT, FRAME INDIFFERENT DIFFUSE INTERFACE MODELS FOR INCOMPRESSIBLE TWO-PHASE FLOWS WITH DIFFERENT DENSITIESMathematical Models and Methods in Applied Sciences, 2012
- Numerical approximations of Allen-Cahn and Cahn-Hilliard equationsDiscrete and Continuous Dynamical Systems, 2010
- Computation of geometric partial differential equations and mean curvature flowActa Numerica, 2005
- Exponential Time Differencing for Stiff SystemsJournal of Computational Physics, 2002
- Quasi–incompressible Cahn–Hilliard fluids and topological transitionsProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998
- A microscopic theory for antiphase boundary motion and its application to antiphase domain coarseningActa Metallurgica, 1979
- Free Energy of a Nonuniform System. I. Interfacial Free EnergyThe Journal of Chemical Physics, 1958