Derivative-informed Graph Convolutional Autoencoder with Phase Classification for the Lifshitz-Petrich Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yanlai, Ji, Yajie, Xu, Zhenli
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911153707286528
author Chen, Yanlai
Ji, Yajie
Xu, Zhenli
author_facet Chen, Yanlai
Ji, Yajie
Xu, Zhenli
contents The Lifshitz-Petrich (LP) model is a classical model for describing complex spatial patterns such as quasicrystals and multiphase structures. Solving and classifying the solutions of the LP model is challenging due to the presence of high-order gradient terms and the long-range orientational order characteristic of the quasicrystals. To address these challenges, we propose a Derivative-informed Graph Convolutional Autoencoder (DiGCA) to classify the multi-component multi-state solutions of the LP model. The classifier consists of two stages. In the offline stage, the DiGCA phase classifier innovatively incorporates both solutions and their derivatives for training a graph convolutional autoencoder which effectively captures intricate spatial dependencies while significantly reducing the dimensionality of the solution space. In the online phase, the framework employs a neural network classifier to efficiently categorize encoded solutions into distinct phase diagrams. The numerical results demonstrate that the DiGCA phase classifier accurately solves the LP model, classifies its solutions, and rapidly generates detailed phase diagrams in a robust manner, offering significant improvements in both efficiency and accuracy over traditional methods.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11293
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Derivative-informed Graph Convolutional Autoencoder with Phase Classification for the Lifshitz-Petrich Model
Chen, Yanlai
Ji, Yajie
Xu, Zhenli
Numerical Analysis
Machine Learning
The Lifshitz-Petrich (LP) model is a classical model for describing complex spatial patterns such as quasicrystals and multiphase structures. Solving and classifying the solutions of the LP model is challenging due to the presence of high-order gradient terms and the long-range orientational order characteristic of the quasicrystals. To address these challenges, we propose a Derivative-informed Graph Convolutional Autoencoder (DiGCA) to classify the multi-component multi-state solutions of the LP model. The classifier consists of two stages. In the offline stage, the DiGCA phase classifier innovatively incorporates both solutions and their derivatives for training a graph convolutional autoencoder which effectively captures intricate spatial dependencies while significantly reducing the dimensionality of the solution space. In the online phase, the framework employs a neural network classifier to efficiently categorize encoded solutions into distinct phase diagrams. The numerical results demonstrate that the DiGCA phase classifier accurately solves the LP model, classifies its solutions, and rapidly generates detailed phase diagrams in a robust manner, offering significant improvements in both efficiency and accuracy over traditional methods.
title Derivative-informed Graph Convolutional Autoencoder with Phase Classification for the Lifshitz-Petrich Model
topic Numerical Analysis
Machine Learning
url https://arxiv.org/abs/2509.11293