Derivative neural operators with physics-guided diffusion refinement for predicting two-phase flow dynamics
Physics of Fluids · 01.07.2026 · 38 (7)
DOI: 10.1063/5.0344207 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 14.07.2026. Verfasst von Zhixian Lv und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Foundation of State Key Laboratory of Aerodynamics, Tianyuan Fund for Mathemetics of National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Time-dependent partial differential equations play a central role in modeling two-phase flow systems, but high-resolution long-term simulations remain computationally demanding. Although data-driven surrogate models provide efficient alternatives, they often suffer from temporal error accumulation and the loss of fine-scale physical structures. In this work, we propose a framework based on derivative neural operators with physics-guided diffusion refinement for fast high-resolution prediction of two-phase flow dynamics. A derivative neural operator is trained on coarse grids to learn the instantaneous temporal dynamics of the physical fields, and the predicted derivatives are advanced using a fourth-order Runge–Kutta scheme for stable and efficient time integration. During the refinement process, the gradient of the governing-equation residual is incorporated as conditional physical guidance, encouraging the refined fields to satisfy the underlying two-phase flow dynamics. In this framework, the coarse-grid derivative operator captures the dominant temporal dynamics, whereas the diffusion refinement recovers interfacial morphology and vortical details that are lost during coarse-grid prediction. Numerical results on several representative systems demonstrate that the proposed framework improves predictive accuracy and spatial resolution.
Förderung
- Foundation of State Key Laboratory of Aerodynamics
- Tianyuan Fund for Mathemetics of National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Lv, Z., Li, C., Wang, Y., & Li, Y. (2026). Derivative neural operators with physics-guided diffusion refinement for predicting two-phase flow dynamics. Physics of Fluids, 38(7). https://doi.org/10.1063/5.0344207
Vancouver
Lv Z, Li C, Wang Y, Li Y. Derivative neural operators with physics-guided diffusion refinement for predicting two-phase flow dynamics. Physics of Fluids. 2026;38(7). doi:10.1063/5.0344207
BibTeX
@article{Lv2026,
author = {Lv, Zhixian and Li, Chen and Wang, Yating and Li, Yibao},
title = {Derivative neural operators with physics-guided diffusion refinement for predicting two-phase flow dynamics},
journal = {Physics of Fluids},
year = {2026},
volume = {38},
number = {7},
doi = {10.1063/5.0344207}
}
EUVIMED