ePrints

Uncertainty Quantification of Spectral Predictions Using Deep Neural Networks

Lookup NU author(s): Dr Sneha Verma, Kathryn Garside, Professor Thomas Penfold

Downloads

• Accepted version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

We investigate the performance of uncertainty quantification methods, namely deep ensembles and bootstrap resampling, for deep neural network (DNN) predictions of transition metal K-edge X-ray absorption near-edge structure (XANES) spectra. Bootstrap resampling combined with our multi-layer perceptron (MLP) model provides an accurate assessment of uncertainty with >90% of all predicted spectral intensities falling within ±3σ of the true values for held-out data across the nine first-row transition metal K-edge XANES spectra.

Publication metadata

Author(s): Verma S, Aznan N, Garside K, Penfold TJ

Publication type: Article

Publication status: Published

Journal: Chemical Communications

Year: 2023

Volume: 46

Issue: 59

Pages: 7100-7103

Print publication date: 16/05/2023

Online publication date: 16/05/2023

Acceptance date: 16/05/2023

Date deposited: 16/05/2023

ISSN (print): 1359-7345

ISSN (electronic): 1364-548X

Publisher: Royal Society of Chemistry

URL: https://doi.org/10.1039/D3CC01988H

DOI: 10.1039/D3CC01988H

Altmetrics

Funding

Share