Toggle Main Menu Toggle Search

Open Access padlockePrints

Accurate, Affordable, and Generalisable Machine Learning Simulations of Transition Metal X-ray Absorption Spectra using the XANESNET Deep Neural Network

Lookup NU author(s): Conor Rankine, Professor Thomas Penfold



This is the authors' accepted manuscript of an article that has been published in its final definitive form by AIP Publishing, 2022.

For re-use rights please refer to the publisher's terms and conditions.


The affordable, accurate, and generalisable prediction of spectroscopic observables plays a key role in the analysis of increasingly complex experiments. In this Article, we develop and deploy a deep neural network (DNN) – XANESNET – for predicting the lineshape of first-row transition metal K-edge X-ray absorption near-edge structure (XANES) spectra. XANESNET predicts the spectral intensities using only information about the local coordination geometry of the transition metal complexes encoded in a feature vector of weighted atom-centred symmetry functions (wACSF). We address in detail the calibration of the feature vector for the particularities of the problem at hand, and we explore the individual feature importances to reveal the physical insight that XANESNET obtains at the Fe K-edge. XANESNET relies on only a few judiciously-selected features – radial information on the first and second coordination shells suffices, along with angular information sufficient to separate satisfactorily key coordination geometries. The feature importance is found to reflect the XANES spectral window under consideration and is consistent with the expected underlying physics. We subsequently apply XANESNET at nine first-row transition metal (Ti–Zn) K-edges. It can be optimised in as little as a minute, predicts instantaneously, and provides K-edge XANES spectra with an average accuracy of ca. ± 2–4% in which the positions of prominent peaks are matched with a > 90% hit rate to sub-eV (ca. 0.8 eV) error.

Publication metadata

Author(s): Rankine CD, Penfold TJ

Publication type: Article

Publication status: Published

Journal: Journal of Chemical Physics

Year: 2022

Volume: 156

Print publication date: 28/04/2022

Online publication date: 25/03/2022

Acceptance date: 25/03/2022

Date deposited: 30/03/2022

ISSN (print): 0021-9606

ISSN (electronic): 1089-7690

Publisher: AIP Publishing


DOI: 10.1063/5.0087255

ePrints DOI: 10.57711/1r6n-4y97


Altmetrics provided by Altmetric