Supporting files for "DFT and machine learning identify standard atomization enthalpy as a descriptor of Al/Al4C3 adhesion"
This repository contains Python analysis scripts and atomic interface models accompanying the study “DFT and machine learning uncover standard atomization enthalpy as a descriptor of Al/Al₄C₃ adhesion”. The scripts implement regression-model comparison, Lasso-based feature selection, SHAP analysis, cross-validation and composite-descriptor construction for interfacial adhesion prediction. The structural collection comprises 352 Al(111)/Al4C3(0001) interface models spanning 44 dopant elements, two termination types and four doping sites. These resources support the analysis of elemental thermochemistry and configuration-dependent interfacial bonding.
Authors
- Herbert M. Urbassek (ORCID: https://orcid.org/0000-0002-7739-4453)
- Junzhe Zhao
- Nina Merkert
- Da Li
- Shuangquan Guo
- wei shao
- zhibo zhang
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.5281/zenodo.24347485
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00