Deep neural networks to correct sub-precision errors in CFD

Deep neural networks to correct sub-precision errors in CFD

Information loss in numerical physics simulations can arise from various sources when solving discretised partial differential equations. In particular, errors related to numerical precision (“sub-precision errors”) can accumulate in the quantities of interest when the simulations are performed usin...

Full description

Bibliographic Details
Main Authors: Akash Haridas, Nagabhushana Rao Vadlamani, Yuki Minamoto
Format: Article
Language:English
Published: Elsevier 2022-12-01
Series:Applications in Energy and Combustion Science
Subjects:
Deep learning
Computational fluid dynamics
Machine learning for physics
Differentiable programming
Floating point
Numerical precision
Online Access:http://www.sciencedirect.com/science/article/pii/S2666352X22000243

Internet

http://www.sciencedirect.com/science/article/pii/S2666352X22000243

Similar Items