A physics-informed neural network based on mixed data sampling for solving modified diffusion equations

We developed a physics-informed neural network based on a mixture of Cartesian grid sampling and Latin hypercube sampling to solve forward and backward modified diffusion equations. We optimized the parameters in the neural networks and the mixed data sampling by considering the squeeze boundary con...

Descripción completa

Detalles Bibliográficos
Autores principales: Fang, Qian, Mou, Xuankang, Li, Shiben
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9925766/
https://www.ncbi.nlm.nih.gov/pubmed/36781943
http://dx.doi.org/10.1038/s41598-023-29822-3

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9925766/
https://www.ncbi.nlm.nih.gov/pubmed/36781943
http://dx.doi.org/10.1038/s41598-023-29822-3

Ejemplares similares