Coupled LSTM-GNN Framework Accelerates Stress Field Reconstruction in Complex Materials
Researchers have proposed a coupled Long Short-Term Memory and Graph Neural Network (LSTM-GNN) framework that reconstructs local stress fields in heterogeneous microstructures under non-linear, history-dependent loading. The model is trained on 10,000 non-proportional loading paths and achieves three orders of magnitude speedup over traditional finite element simulations. This matters because it could significantly reduce the computational cost of multi-scale materials simulations while maintaining high accuracy and generalizing across different mesh types and resolutions.
A new machine learning framework combining Long Short-Term Memory (LSTM) networks with physics-informed Graph Neural Networks (GNNs) has been developed to reconstruct spatially-resolved stress fields in heterogeneous microstructures. The LSTM component encodes macroscopic stress-strain sequences to capture path-dependent material behavior, while the GNN reconstructs the spatial stress distribution at each time step. A key innovation is a relative weighting strategy with linear warm-up that balances data-driven and physics-based loss terms, resolving convergence issues in the elasto-plastic regime that plagued fixed-weight approaches. Trained on a periodic plate-with-a-hole microstructure with von Mises elasto-plasticity, the model generalizes to loading sequences twice the training length with only 1.9% cumulative error. Notably, because the GNN operates on mesh connectivity rather than specific element types, the trained model transfers directly to meshes of different element types and resolutions without retraining. Analysis of the LSTM hidden states also reveals a low-dimensional structure linked to the internal state variables of the underlying constitutive model, suggesting the network has learned physically meaningful representations.
What's missing
The study is limited to a single microstructure geometry (periodic plate-with-a-hole) and one plasticity model (von Mises elasto-plasticity); generalization to more complex microstructures, damage mechanics, or other constitutive models has not been demonstrated. The paper does not report performance on fully three-dimensional geometries, and it is unclear how the framework scales with increasing microstructural complexity or larger mesh sizes. No comparison against other surrogate modeling approaches (e.g., convolutional neural networks or Fourier neural operators) is provided.
What different sources said
- arXiv cs.LGCenter
Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.