×

Recommended by

Indexed by

Efficient, interpretable graph neural network representation for angle-dependent properties and its application to optical spectroscopy

Tim Hsu1*, Tuan Anh Pham1*, Nathan Keilbart1, Stephen Weitzner1, James Chapman1, Penghao Xiao2, S. Roger Qiu1, Xiao Chen1, Brandon Wood1*

1 Lawrence Livermore National Laboratory, Livermore, CA, United States

2 Dalhousie University, Halifax, NS, Canada

* Corresponding authors emails: hsu16@llnl.gov, pham16@llnl.gov, wood37@llnl.gov
DOI10.24435/materialscloud:s7-8e [version v1]

Publication date: May 23, 2022

How to cite this record

Tim Hsu, Tuan Anh Pham, Nathan Keilbart, Stephen Weitzner, James Chapman, Penghao Xiao, S. Roger Qiu, Xiao Chen, Brandon Wood, Efficient, interpretable graph neural network representation for angle-dependent properties and its application to optical spectroscopy, Materials Cloud Archive 2022.66 (2022), doi: 10.24435/materialscloud:s7-8e.

Description

Graph neural networks are attractive for learning properties of atomic structures thanks to their intuitive graph encoding of atoms and bonds. However, conventional encoding does not include angular information, which is critical for describing atomic arrangements in disordered systems. In this work, we extend the recently proposed ALIGNN encoding, which incorporates bond angles, to also include dihedral angles (ALIGNN-d). This simple extension leads to a memory-efficient graph representation that captures the complete geometry of atomic structures. ALIGNN-d is applied to predict the infrared optical response of dynamically disordered Cu(II) aqua complexes, leveraging the intrinsic interpretability to elucidate the relative contributions of individual structural components. Bond and dihedral angles are found to be critical contributors to the fine structure of the absorption response, with distortions representing transitions between more common geometries exhibiting the strongest absorption intensity. Future directions for further development of ALIGNN-d are discussed.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.

Files

File name Size Description
for-reproducing-figures.tar.gz
MD5md5:cdb026366224747f6fee0b89c16cbc60
65.6 MiB Data for reproducing figures
for-reproducing-model-training.tar.gz
MD5md5:31bbff1d8be5a2a7a32ff0d5649a9a3b
88.6 MiB Data for reproducing model training

License

Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

Keywords

Graph neural network Spectroscopy Aqua complex

Version history:

2022.66 (version v1) [This version] May 23, 2022 DOI10.24435/materialscloud:s7-8e