Machine-learning-enhanced time-of-flight mass spectrometry analysis

Ye Wei; Rama Srinivas Varanasi; Torsten Schwarz; Leonie Gomell; Huan Zhao; David J Larson; Binhan Sun; Geng Liu; Hao Chen; Dierk Raabe; Baptiste Gault

doi:10.1016/j.patter.2020.100192

Machine-learning-enhanced time-of-flight mass spectrometry analysis

Patterns (N Y). 2021 Jan 21;2(2):100192. doi: 10.1016/j.patter.2020.100192. eCollection 2021 Feb 12.

Authors

Affiliations

¹ Max-Planck-Institut für Eisenforschung, Max-Planck-Strasse 1, 40237 Düsseldorf, Germany.
² CAMECA Instruments, 5470 Nobel Drive, Madison, WI 53711, USA.
³ Key Laboratory for Advanced Materials of Ministry of Education, School of Materials Science and Engineering, Tsinghua University, Beijing 100084, China.
⁴ Department of Materials, Royal School of Mines, Imperial College, London SW7 2AZ, UK.

Abstract

Mass spectrometry is a widespread approach used to work out what the constituents of a material are. Atoms and molecules are removed from the material and collected, and subsequently, a critical step is to infer their correct identities based on patterns formed in their mass-to-charge ratios and relative isotopic abundances. However, this identification step still mainly relies on individual users' expertise, making its standardization challenging, and hindering efficient data processing. Here, we introduce an approach that leverages modern machine learning technique to identify peak patterns in time-of-flight mass spectra within microseconds, outperforming human users without loss of accuracy. Our approach is cross-validated on mass spectra generated from different time-of-flight mass spectrometry (ToF-MS) techniques, offering the ToF-MS community an open-source, intelligent mass spectra analysis.

Keywords: atom probe tomography; machine learning; pattern recognition; secondary ion mass spectrometry; time-of-flight mass spectrometry.