All news

Stochastic closure models learned without direct closure data

For reduced-order models of complex multiphysics systems, the authors propose a diffusion-based framework that recovers information lost where deterministic closures fall short. Training uses indirect offline data with online data assimilation, avoiding direct closure measurements. The authors cite applications to digital twins for additive manufacturing and world models for AI agents.

Why it matters

Lower data requirements for closure calibration broaden the use of fast surrogate models in industrial digital twins.

Relevant to DT products

Original headline
Score-Based Stochastic Closure Modeling via Offline Indirect Learning and Online Data Assimilation
Read the original: arXiv API — полнотекстовый поиск "digital twin"

Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.