Learning stable radiation boundaries for wave simulations via passive neural state-space models

Aotu Li, Xiaolong Wang, Yuchen Wang, Shaoqiang Wang · 2026

Read Learning stable radiation boundaries for wave simulations via passive neural state-space models by Aotu Li, Xiaolong Wang, Yuchen Wang, Shaoqiang Wang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13266139.txt.

Description

Aotu Li and the team propose a neural boundary method for wave simulations (2026). Simulations must cut endless space down to a finite grid without fake reflections. Standard absorbing layers need many grid rows and extra variables. A single-layer learned boundary could cut those costs.

The method uses a neural state-space model to predict boundary cell answers directly. Physical constraints keep it stable over long runs. Tests showed low reflection with substantially reduced computing overhead. No auxiliary fields need step-by-step evolution, unlike conventional matched layers. The authors plan extension to larger three-dimensional problems and complex boundary shapes.

Catalog record

CREATORAotu Li, Xiaolong Wang, Yuchen Wang, Shaoqiang Wang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE82 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13266139

Browse the full library · About the Tower of Babel