Machine-Learning X-ray Absorption Spectra to Quantitative Accuracy

TL;DR

This paper demonstrates that graph-based neural networks can accurately predict X-ray absorption spectra of molecules, matching first-principles calculations at a fraction of the computational cost, thereby advancing data-driven discovery in spectroscopy.

Contribution

It introduces a machine learning approach using graph neural networks to predict X-ray absorption spectra with high accuracy, comparable to first-principles methods.

Findings

Predicted spectra reproduce nearly all prominent peaks.

90% of peak locations within 1 eV of ground truth.

Machine learning achieves similar accuracy to first-principles calculations.

Abstract

The advent of massive data repositories has propelled machine learning techniques to the front lines of many scientific fields, and exploring new frontiers by leveraging the predictive power of machine learning will greatly accelerate big data-assisted discovery. In this work, we show that graph-based neural networks can be used to predict the near edge x-ray absorption structure spectra of molecules with exceptional accuracy. The predicted spectra reproduce nearly all the prominent peaks, with 90% of the predicted peak locations within 1 eV of the ground truth. Our study demonstrates that machine learning models can achieve practically the same accuracy as first-principles calculations in predicting complex physical quantities, such as spectral functions, but at a fraction of the cost.