[G] Computational Materials Science and Data Science

9:30 AM - 9:45 AM JST(12:30 AM - 12:45 AM UTC)

[283] Data Assimilation of Multi-Phase-Field Model Based on Physics-Informed Neural-Networks

○Chang Liu¹, Meng Zhang², Satoshi Noguchi³, Junya Inoue² (1. EngUTokyo, 2. IIS UTokyo, 3. JAMSTEC)

Keywords:

grain growth,AI,microstructure prediction

A PINNs-based data assimilation framework is proposed for Multi-Phase-Field (MPF) simulations. The framework successfully performs grain growth prediction and inverse estimation of interface mobility. Stable simulations are achieved under enlarged time-step conditions where conventional finite-difference methods become unstable.