---
title: "Surrogate Models for Stochastic Al-Cu Phase-Field Solidification"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04695v1"
permalink: "https://feed.astralor.com/items/itm_d646985e2455c49dc91d838b"
published: "2026-11-03T11:18:38.000Z"
score: 57
channel: "tech"
tags: ["推理效率","Surrogate Models","Stochastic Al-Cu Phase-Field","Solidification Phase-field","Phase-field","VP-DDBM","Al-Cu","Given"]
---

# Surrogate Models for Stochastic Al-Cu Phase-Field Solidification

## 速览

Phase-field models resolve microstructural evolution during rapid alloy solidification, but their computational cost limits long trajectories, stochastic ensembles, and studies across process conditions. We present a va…

## 关键点

- Phase-field models resolve microstructural evolution during rapid alloy solidification, but their computational cost limits long trajectories, stochastic ensembles, and studies across process conditions.
- We present a variance-preserving denoising diffusion bridge model (VP-DDBM) for state-conditioned prediction of two-dimensional Al-Cu solidification.
- Given the current phase, concentration, and prescribed temperature fields, the model predicts the subsequent state and is applied autoregressively.

## 全文

Phase-field models resolve microstructural evolution during rapid alloy solidification, but their computational cost limits long trajectories, stochastic ensembles, and studies across process conditions. We present a variance-preserving denoising diffusion bridge model (VP-DDBM) for state-conditioned prediction of two-dimensional Al-Cu solidification. Given the current phase, concentration, and prescribed temperature fields, the model predicts the subsequent state and is applied autoregressively. Across two held-out thermal gradients, VP-DDBM produces lower long-horizon errors than deterministic U-Net and SI-ConvNeXt baselines in domain-mean phase, domain-mean Cu concentration, and leading-tip position. It also retains fine dendritic structure over long rollouts, whereas the deterministic U-Net progressively smooths the morphology. VP-DDBM predicts the phase and concentration evolution approximately $73\times$ faster than the phase-field solver, showing potential for faster process-condition screening and ensemble-based microstructure studies.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d646985e2455c49dc91d838b