Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914045890658304 |
|---|---|
| author | Razavi, Hamidreza Moelans, Nele |
| author_facet | Razavi, Hamidreza Moelans, Nele |
| contents | This paper presents a physics-informed framework that integrates graph convolutional networks (GCN) with long short-term memory (LSTM) architecture to forecast microstructure evolution over long time horizons in both 2D and 3D with remarkable performance across varied metrics. The proposed framework is composition-aware, trained jointly on datasets with different compositions, and operates in latent graph space, which enables the model to capture compositions and morphological dynamics while remaining computationally efficient. Compressing and encoding phase-field simulation data with convolutional autoencoders and operating in Latent graph space facilitates efficient modeling of microstructural evolution across composition, dimensions, and long-term horizons. The framework captures the spatial and temporal patterns of evolving microstructures while enabling long-range forecasting at reduced computational cost after training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15029 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution Razavi, Hamidreza Moelans, Nele Materials Science Computational Engineering, Finance, and Science Machine Learning Computational Physics This paper presents a physics-informed framework that integrates graph convolutional networks (GCN) with long short-term memory (LSTM) architecture to forecast microstructure evolution over long time horizons in both 2D and 3D with remarkable performance across varied metrics. The proposed framework is composition-aware, trained jointly on datasets with different compositions, and operates in latent graph space, which enables the model to capture compositions and morphological dynamics while remaining computationally efficient. Compressing and encoding phase-field simulation data with convolutional autoencoders and operating in Latent graph space facilitates efficient modeling of microstructural evolution across composition, dimensions, and long-term horizons. The framework captures the spatial and temporal patterns of evolving microstructures while enabling long-range forecasting at reduced computational cost after training. |
| title | Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution |
| topic | Materials Science Computational Engineering, Finance, and Science Machine Learning Computational Physics |
| url | https://arxiv.org/abs/2509.15029 |