Tim Hsu^1*, Tuan Anh Pham^1*, Nathan Keilbart¹, Stephen Weitzner¹, James Chapman¹, Penghao Xiao², S. Roger Qiu¹, Xiao Chen¹, Brandon Wood^1*

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), https://doi.org/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

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.

External references

Keywords

Graph neural network Spectroscopy Aqua complex