Application of machine learning to spectrum and image data
Source abstract
Abstract
Machine learning is a useful tool when extracting hidden information from complex measurement data obtained via surface analysis, as in secondary ion mass spectrometry. Flexible learning methods often require significant effort to adjust parameters, as these parameters may have a significant effect on results. However, machine learning methods enable the extraction of new information that cannot be found by manual analysis. This paper presents some examples of complex data analyses using conventional multivariate analysis methods based on linear combinations (principal component analysis and multivariate curve resolution), an unsupervised learning method based on artificial neural networks (sparse autoencoder), and a supervised learning method based on decision trees (random forest). To obtain reproducible and useful results from machine learning applications to surface analysis data, the preparation of data sets—including the selection of variables and the raw data conversion process—is crucial. Moreover, sufficient information representing analytical purposes, such as the chemical structures of unknown samples, material types, and physical or chemical properties of particular materials, must be contained in the data set for supervised learning.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ion-surface interactions and analysis · Geochemistry and Geologic Mapping · Machine Learning in Materials Science
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Science and Technology, Seikei University , 3-3-1 Kichijoji-Kitamachi, Musashino-shi, Tokyo 180-8633 Japan
References (49)
Show source-provided references
1. Langmuir · 2001 · 17 · 464910.1021/la001209t ↗
2. Appl. Surf. Sci. · 2006 · 252 · 657510.1016/j.apsusc.2006.02.073 ↗
3. Anal. Chem. · 2008 · 80 · 13510.1021/ac071560k ↗
4. Anal. Chem. · 2008 · 80 · 194210.1021/ac701921e ↗
5. Surf. Interface Anal. · 2008 · 40 · 110.1002/sia.2713 ↗
6. Surf. Interface Anal. · 2009 · 41 · 8810.1002/sia.2973 ↗
7. Surf. Interface Anal. · 2009 · 41 · 65310.1002/sia.3070 ↗
8. Surf. Interface Anal. · 2009 · 41 · 66610.1002/sia.3084 ↗
9. Biointerphases · 2012 · 7 · 4910.1007/s13758-012-0049-3 ↗
10. Surf. Interface Anal. · 2015 · 47 · 43910.1002/sia.5731 ↗
11. Biointerphases · 2020 · 15 · 03101310.1116/6.0000017 ↗
12. Surf. Interface Anal. · 2002 · 33 · 71510.1002/sia.1438 ↗
13. Sci. Rep. · 2017 · 7 · 352110.1038/s41598-017-03780-z ↗
14. Biointerphases · 2020 · 15 · 02101310.1116/6.0000044 ↗
15. Rapid Commun. Mass Spectrom. · 2023 · 37 · e944510.1002/rcm.9445 ↗
16. J. Vac. Sci. Technol. A · 2013 · 31 · 05081910.1116/1.4816935 ↗
17. Ultramicroscopy · 2010 · 110 · 13410.1016/j.ultramic.2009.10.011 ↗
18. e-J. Surf. Sci. Nanotechnol. · 2023 · 21 · 12810.1380/ejssnt.2023-023 ↗
19. EPJ Tech. Instrum. · 2015 · 2 · 810.1140/epjti/s40485-015-0018-6 ↗
20. Carbohydr. Polym. · 2020 · 230 · 11556110.1016/j.carbpol.2019.115561 ↗
21. Analyst · 2020 · 145 · 757110.1039/D0AN01244K ↗
22. Appl. Surf. Sci. · 2010 · 256 · 320410.1016/j.apsusc.2009.12.006 ↗
23. Mass Spectrom. Rev. · 2020 · 39 · 24510.1002/mas.21602 ↗
24. Langmuir · 2002 · 18 · 409010.1021/la020022u ↗
25. Surf. Interface Anal. · 2011 · 43 · 28510.1002/sia.3440 ↗
26. Langmuir · 2004 · 20 · 187710.1021/la035376f ↗
27. Anal. Chem. · 2010 · 82 · 294710.1021/ac902964q ↗
28. Adv. Funct. Mater. · 2009 · 19 · 304610.1002/adfm.200900809 ↗
29. Langmuir · 2007 · 23 · 5010.1021/la062330o ↗
30. Surf. Interface Anal. · 2006 · 38 · 138610.1002/sia.2382 ↗
31. e-J. Surf. Sci. Nanotechnol. · 2006 · 4 · 61410.1380/ejssnt.2006.614 ↗
32. Anal. Chem. · 2007 · 79 · 137710.1021/ac0616005 ↗
33. Anal. Bioanal. Chem. · 2013 · 405 · 662110.1007/s00216-013-7139-z ↗
34. Rapid Commun. Mass Spectrom. · 2015 · 29 · 168710.1002/rcm.7266 ↗
35. Anal. Chem. · 2016 · 88 · 359210.1021/acs.analchem.5b04133 ↗
36. Anal. Chem. · 2010 · 82 · 266110.1021/ac902280h ↗
37. Anal. Chem. · 2010 · 82 · 433710.1021/ac100837n ↗
38. Surf. Interface Anal. · 2010 · 42 · 91110.1002/sia.3244 ↗
39. 2016 · 110.1109/SSCI.2016.7849863 ↗
40. Biointerphases · 2020 · 15 · 02101010.1116/6.0000010 ↗
41. Anal. Chem · 2021 · 93 · 419110.1021/acs.analchem.0c04577 ↗
42. Anal. Chem. · 2020 · 92 · 658710.1021/acs.analchem.0c00349 ↗
43. Biointerphases · 2020 · 15 · 06100410.1116/6.0000614 ↗
44. Analyst · 2021 · 146 · 588010.1039/D0AN02155E ↗
45. Biointerphases · 2022 · 17 · 02080210.1116/6.0001590 ↗
46. Anal. Chem. · 2022 · 94 · 780410.1021/acs.analchem.1c05453 ↗
47. Anal. Chem. · 2020 · 92 · 1045010.1021/acs.analchem.0c00986 ↗
48. Anal. Bioanal. Chem. · 2022 · 414 · 117710.1007/s00216-021-03744-3 ↗
49. See the supplementary material online for PCA loadings (the highest or the lowest ten), MCR spectrum matrix (the highest ten), and decoder weights (the highest ten).