diffhydro: Inverse Multiphysics Modeling and Embedded Machine Learning in Astrophysical Flows
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911319785996288 |
|---|---|
| author | Horowitz, Benjamin Lukić, Zarija Nagamine, Kentaro Oku, Yuri |
| author_facet | Horowitz, Benjamin Lukić, Zarija Nagamine, Kentaro Oku, Yuri |
| contents | We present the extension of the differentiable hydrodynamics code, diffhydro, enabling scalable PDE-constrained inference and integrated hybrid physics-ML models for a wide range of astrophysical applications. New physics additions include radiative heating/cooling, OU-driven turbulence, and self-gravity via multigrid Poisson. We demonstrate good agreement with the Athena++ code on standard validation tests such as Sedov-Taylor, Kelvin-Helmholtz, and driven/decaying turbulence. We further introduce a solver-in-the-loop neural corrector that reduces coarse-grid errors during time integration while preserving stability. The addition of custom adjoints facilitates efficient end-to-end gradients and multi-device scaling. We present simulations up to 1024^3 elements, run on distributed GPU systems, and we show gradient-based reconstructions of complex initial conditions in turbulent, self-gravitating, radiatively cooling flows. The code is written in JAX, and the solver's modular finite-volume components are compiled by XLA into fused accelerator kernels, delivering high-throughput forward runs and tractable differentiation through long integrations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13403 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | diffhydro: Inverse Multiphysics Modeling and Embedded Machine Learning in Astrophysical Flows Horowitz, Benjamin Lukić, Zarija Nagamine, Kentaro Oku, Yuri Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies We present the extension of the differentiable hydrodynamics code, diffhydro, enabling scalable PDE-constrained inference and integrated hybrid physics-ML models for a wide range of astrophysical applications. New physics additions include radiative heating/cooling, OU-driven turbulence, and self-gravity via multigrid Poisson. We demonstrate good agreement with the Athena++ code on standard validation tests such as Sedov-Taylor, Kelvin-Helmholtz, and driven/decaying turbulence. We further introduce a solver-in-the-loop neural corrector that reduces coarse-grid errors during time integration while preserving stability. The addition of custom adjoints facilitates efficient end-to-end gradients and multi-device scaling. We present simulations up to 1024^3 elements, run on distributed GPU systems, and we show gradient-based reconstructions of complex initial conditions in turbulent, self-gravitating, radiatively cooling flows. The code is written in JAX, and the solver's modular finite-volume components are compiled by XLA into fused accelerator kernels, delivering high-throughput forward runs and tractable differentiation through long integrations. |
| title | diffhydro: Inverse Multiphysics Modeling and Embedded Machine Learning in Astrophysical Flows |
| topic | Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies |
| url | https://arxiv.org/abs/2512.13403 |