Parts of my academic research data are allowed to be open-sourced, as follows:

• EHML: Extended Hybrid Machine Learning: Implementation of several extensions, including physics-constrained data augmentation, on multi-fidelity surrogate modeling using TensorFlow and Abaqus.
• PSA: Pre-Stress Algorithm: This is a unified optimizer for large-scale pre-stressing analysis in articular cartilage models using Abaqus Fortran subroutines and Python scripts.
• HML: Hybrid Machine Learning: Implementation of a new hybrid machine learning technique for multi-fidelity surrogates of finite elements models with applications in multi-physics modeling of soft tissues.
• PMSE: Pointwise Mean Squared Error: Implementation of a simple pointwise metric for machine-learning-based surrogate modeling in Python using Keras and Abaqus.
• BioUMAT: Abaqus Fortran subroutine for cartilage multiphasic modeling: This code is the Fortran 77 version of the UMAT, FLOW, and SDVINI subroutines of the cartilage model, I firstly proposed in my Master's thesis. The model with minor modifications was used in several publications.