Manuel Ricardo Guevara

p-div-gnn. This work proposes P-DivGNN, a divergence regularized physics-informed graph neural network tailored for accurately reconstructing mechanical fields in materials undergoing large deformations using elastic and hyperelastic constitutive models.

StressLSTM. Minimal implementation in PyTorch of the LSTM-based approach for stress prediction described in the paper: FE-LSTM: A hybrid approach to accelerate multiscale simulations of architectured materials using Recurrent Neural Networks and Finite Element Analysis

cnn3d_tpms_csma2024. The github repository for the article "Classification et estimation de densité de microstructures triplement périodiques avec des réseaux de neurones à convolution 3D" presented at CSMA 2024