paper-with-me

홈 › Papers

Machine learning moment closure models for the radiative transfer equation I: directly learning a gradient based closure

2021-05-12 · Juntao Huang, Yingda Cheng, Andrew J. Christlieb, Luke F. Roberts

In this paper, we take a data-driven approach and apply machine learning to the moment closure problem for radiative transfer equation in slab geometry. Instead of learning the unclosed high order moment, we propose to directly learn the gradient of the high order moment using neural networks. This new approach is consistent with the exact closure we derive for the free streaming limit and also provides a natural output normalization. A variety of benchmark tests, including the variable scattering problem, the Gaussian source problem with both periodic and reflecting boundaries, and the two-material problem, show both good accuracy and generalizability of our machine learning closure model.

📄 PDF Abstract BibTeX arXiv:2105.05690

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Machine learning moment closure models for the radiative transfer equation II: enforcing global hyperbolicity in gradient based closures

2021-05-30 · Juntao Huang, Yingda Cheng, Andrew J. Christlieb, Luke F. Roberts 외

This is the second paper in a series in which we develop machine learning (ML) moment closure models for the radiative transfer equation (RTE). In our previous work \cite{huang2021gradient}, we proposed an approach to di…

RTE

Machine learning moment closure models for the radiative transfer equation III: enforcing hyperbolicity and physical characteristic speeds

2021-09-02 · Juntao Huang, Yingda Cheng, Andrew J. Christlieb, Luke F. Roberts

This is the third paper in a series in which we develop machine learning (ML) moment closure models for the radiative transfer equation (RTE). In our previous work \cite{huang2021gradient}, we proposed an approach to lea…

RTE

A Hyperbolic Neural Closure for M1 Radiation Transfer

2026-07-11 · Bongseok Kim, Jiahao Zhang, Johannes Krotz, Dinshaw Balsara 외 arxiv

In radiation transfer simulations, an M1 method achieves substantial computational savings by replacing the full angular transport equation with a low-order moment system. Because this reduced system is not closed, a clo…

Machine learning moment closure models for the radiative transfer equation IV: enforcing symmetrizable hyperbolicity in two dimensions

2026-04-22 · Juntao Huang arxiv

This is our fourth work in the series on machine learning (ML) moment closure models for the radiative transfer equation (RTE). In the first three papers of this series, we considered the RTE in slab geometry in 1D1V (i.…

Physics Informed Neural Networks for Simulating Radiative Transfer

2020-09-25 · Siddhartha Mishra, Roberto Molinaro

We propose a novel machine learning algorithm for simulating radiative transfer. Our algorithm is based on physics informed neural networks (PINNs), which are trained by minimizing the residual of the underlying radiativ…

BIG-bench Machine Learning