Search

Image Details

View Article Bookmark & Share

Choose export citation format:

Export Citation
Large resolution
Hi-Resolution Export to PDF

diffhydro: Inverse Multiphysics Modeling and Embedded Machine Learning in Astrophysical Flows

  • Authors: Benjamin Horowitz, Zarija Lukić, Kentaro Nagamine, Yuri Oku

Benjamin Horowitz et al 2026 The Astrophysical Journal 1012 .

  • Provider: AAS Journals

Caption: Figure 18.

Performance of the Kelvin–Helmholtz flux corrector network is compared over time compared to the uncorrected network on a test set. While the network was only trained until t = 1.0 (∼1000 time steps), we find significant improvement over the baseline until t ∼ 3.0, which is far into the nonlinear regime.

Other Images in This Article
Image in this article
Image in this article
Image in this article
Image in this article
Image in this article
Image in this article
Image in this article
Image in this article
Image in this article

Show More

Copyright and Terms & Conditions

Additional terms of reuse