Enhanced accuracy through machine learning-based simultaneous evaluation: a case study of RBS analysis of multinary materials.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
08 Apr 2024
08 Apr 2024
Historique:
received:
01
12
2023
accepted:
27
03
2024
medline:
9
4
2024
pubmed:
9
4
2024
entrez:
8
4
2024
Statut:
epublish
Résumé
We address the high accuracy and precision demands for analyzing large in situ or in operando spectral data sets. A dual-input artificial neural network (ANN) algorithm enables the compositional and depth-sensitive analysis of multinary materials by simultaneously evaluating spectra collected under multiple experimental conditions. To validate the developed algorithm, a case study was conducted analyzing complex Rutherford backscattering spectrometry (RBS) spectra collected in two scattering geometries. The dual-input ANN analysis excelled in providing a systematic analysis and precise results, showcasing its robustness in handling complex data and minimizing user bias. A comprehensive comparison with human supervision analysis and conventional single-input ANN analysis revealed a reduced susceptibility of the dual-input ANN analysis to inaccurately known setup parameters, a common challenge in material characterization. The developed multi-input approach can be extended to a wide range of analytical techniques, in which the combined analysis of measurements performed under different experimental conditions is beneficial for disentangling details of the material properties.
Identifiants
pubmed: 38589457
doi: 10.1038/s41598-024-58265-7
pii: 10.1038/s41598-024-58265-7
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
8186Subventions
Organisme : EU infrastructure network RADIATE
ID : 824096
Informations de copyright
© 2024. The Author(s).
Références
IEEE. International roadmap for devices and systems: metrology (2022).
Schleunitz, A. et al. Novel 3D micro-and nanofabrication method using thermally activated selective topography equilibration (taste) of polymers. Nano Converg. 1, 1–8 (2014).
doi: 10.1186/s40580-014-0007-5
Gira, M. J., Tkacz, K. P. & Hampton, J. R. Physical and electrochemical area determination of electrodeposited Ni Co, and NiCo thin films. Nano Converg. 3, 6 (2016).
pubmed: 28191416
pmcid: 5271141
doi: 10.1186/s40580-016-0063-0
Bauer, S., Rodrigues, A. & Baumbach, T. Real time in situ x-ray diffraction study of the crystalline structure modification of Ba
pubmed: 30097626
pmcid: 6086881
doi: 10.1038/s41598-018-30392-y
Schmidt, J., Marques, M. R., Botti, S. & Marques, M. A. Recent advances and applications of machine learning in solid-state materials science. npj Comput. Mater. 5, 83 (2019).
doi: 10.1038/s41524-019-0221-0
Bedolla, E., Padierna, L. C. & Castaneda-Priego, R. Machine learning for condensed matter physics. J. Condens. Matter Phys. 33, 053001 (2020).
doi: 10.1088/1361-648X/abb895
Oviedo, F. et al. Fast and interpretable classification of small x-ray diffraction datasets using data augmentation and deep neural networks. npj Comput. Mater. 5, 60 (2019).
doi: 10.1038/s41524-019-0196-x
Bridger, A., David, W. I., Wood, T. J., Danaie, M. & Butler, K. T. Versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders. npj Comput. Mater. 9, 14 (2023).
doi: 10.1038/s41524-022-00960-y
Munshi, J. et al. Disentangling multiple scattering with deep learning: Application to strain mapping from electron diffraction patterns. npj Comput. Mater. 8, 254 (2022).
doi: 10.1038/s41524-022-00939-9
Taherimakhsousi, N. et al. Quantifying defects in thin films using machine vision. npj Comput. Mater. 6, 111 (2020).
doi: 10.1038/s41524-020-00380-w
Griffin, L. A., Gaponenko, I., Zhang, S. & Bassiri-Gharb, N. Smart machine learning or discovering meaningful physical and chemical contributions through dimensional stacking. npj Comput. Mater. 5, 85 (2019).
doi: 10.1038/s41524-019-0222-z
Demeulemeester, J. et al. Artificial neural networks for instantaneous analysis of real-time Rutherford backscattering spectra. Nucl. Instrum. Methods Phys. Res. B 268, 1676–1681 (2010).
doi: 10.1016/j.nimb.2010.02.127
Planckaert, N. et al. Artificial neural networks applied to the analysis of synchrotron nuclear resonant scattering data. J. Synchrotron Radiat. 17, 86–92 (2010).
pubmed: 20029116
doi: 10.1107/S0909049509042824
Kim, H. J. et al. Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth. Nano Converg. 10, 10 (2023).
pubmed: 36806667
pmcid: 9941396
doi: 10.1186/s40580-023-00359-5
Venderley, J. et al. Harnessing interpretable and unsupervised machine learning to address big data from modern x-ray diffraction. PNAS 119, e2109665119 (2022).
pubmed: 35679347
pmcid: 9214512
doi: 10.1073/pnas.2109665119
Banko, L., Maffettone, P. M., Naujoks, D., Olds, D. & Ludwig, A. Deep learning for visualization and novelty detection in large x-ray diffraction datasets. npj Comput. Mater. 7, 104 (2021).
doi: 10.1038/s41524-021-00575-9
Suzuki, Y. et al. Symmetry prediction and knowledge discovery from x-ray diffraction patterns using an interpretable machine learning approach. Sci. Rep. 10, 21790 (2020).
pubmed: 33311555
pmcid: 7732852
doi: 10.1038/s41598-020-77474-4
Wu, L. et al. Resolution-enhanced x-ray fluorescence microscopy via deep residual networks. npj Comput. Mater. 9, 43 (2023).
doi: 10.1038/s41524-023-00995-9
Theron, C., Lombaard, J. & Pretorius, R. Real-time RBS of solid-state reaction in thin films. Nucl. Instrum. Methods Phys. Res. B 161, 48–55 (2000).
doi: 10.1016/S0168-583X(99)00882-4
Smeets, D. et al. Simultaneous real-time x-ray diffraction spectroscopy, Rutherford backscattering spectrometry, and sheet resistance measurements to study thin film growth kinetics by Kissinger plots. J. Appl. Phys 104, 103538 (2008).
doi: 10.1063/1.3021110
Demeulemeester, J. et al. Pt redistribution during Ni (Pt) silicide formation. Appl. Phys. Lett. 93, 261912 (2008).
doi: 10.1063/1.3058719
Comrie, C. et al. Determination of the dominant diffusing species during nickel and palladium germanide formation. Thin Solid Films 526, 261–268 (2012).
doi: 10.1016/j.tsf.2012.10.113
Schrauwen, A. et al. On the nucleation of PdSi and NiSi[Formula: see text] during the ternary Ni (Pd)/Si (100) reaction. J. Appl. Phys 114, 063518 (2013).
doi: 10.1063/1.4818333
van Stiphout, K. et al. Ion beam modification of the Ni-Si solid-phase reaction: The influence of substrate damage and nitrogen impurities introduced by ion implantation. J. Phys. D Appl. Phys. 54, 015307 (2020).
doi: 10.1088/1361-6463/abb046
Barradas, N. et al. International Atomic Energy Agency intercomparison of ion beam analysis software. Nucl. Instrum. Methods Phys. Res. B 262, 281–303 (2007).
doi: 10.1016/j.nimb.2007.05.018
Heller, R., Klingner, N., Claessens, N., Merckling, C. & Meersschaut, J. Differential evolution optimization of Rutherford backscattering spectra. J. Appl. Phys 132, 165302 (2022).
doi: 10.1063/5.0096497
Butler, J. Criteria for validity of Rutherford scatter analyses. Nucl. Instrum. Methods Phys. Res. B 45, 160–165 (1990).
doi: 10.1016/0168-583X(90)90808-8
Silva, T. F. et al. Self-consistent ion beam analysis: An approach by multi-objective optimization. Nucl. Instrum. Methods Phys. Res. B 506, 32–40 (2021).
doi: 10.1016/j.nimb.2021.09.007
Barradas, N. P. & Vieira, A. Artificial neural network algorithm for analysis of Rutherford backscattering data. Phys. Rev. E 62, 5818 (2000).
doi: 10.1103/PhysRevE.62.5818
Guimarães, R. D. S. et al. Processing of massive Rutherford back-scattering spectrometry data by artificial neural networks. Nucl. Instrum. Methods Phys. Res. B 493, 28–34 (2021).
doi: 10.1016/j.nimb.2021.02.010
Pinho, H., Vieira, A., Nené, N. & Barradas, N. Artificial neural network analysis of multiple IBA spectra. Nucl. Instrum. Methods Phys. Res. B 228, 383–387 (2005).
doi: 10.1016/j.nimb.2004.10.075
Demeulemeester, J. et al. Sn diffusion during Ni germanide growth on Ge[Formula: see text]Sn[Formula: see text]. Appl. Phys. Lett. 99, 211905 (2011).
doi: 10.1063/1.3662925
Huang, Z.-M. et al. Emission of direct-gap band in germanium with Ge-GeSn layers on one-dimensional structure. Sci. Rep. 6, 24802 (2016).
pubmed: 27097990
pmcid: 4838848
doi: 10.1038/srep24802
Vincent, B. et al. Characterization of GeSn materials for future Ge pMOSFETs source/drain stressors. Microelectron. Eng. 88, 342–346 (2011).
doi: 10.1016/j.mee.2010.10.025
Liu, Z. et al. Defect-free high Sn-content GeSn on insulator grown by rapid melting growth. Sci. Rep. 6, 38386 (2016).
pubmed: 27941825
pmcid: 5150248
doi: 10.1038/srep38386
Gaudet, S., Detavernier, C., Kellock, A., Desjardins, P. & Lavoie, C. Thin film reaction of transition metals with germanium. J. Vacuum Sci. Technol. A 24, 474–485 (2006).
doi: 10.1116/1.2191861
Vieira, A., Barradas, N. & Jeynes, C. Error performance analysis of artificial neural networks applied to Rutherford backscattering. Surf. Interface Anal. 31, 35–38 (2001).
doi: 10.1002/sia.949
Barradas, N. P., Vieira, A. & Patricio, R. Artificial neural networks for automation of Rutherford backscattering spectroscopy experiments and data analysis. Phys. Rev. E 65, 066703 (2002).
doi: 10.1103/PhysRevE.65.066703
Mayer, M. Improved physics in SIMNRA 7. Nucl. Instrum. Methods Phys. Res. B 332, 176–180 (2014).
doi: 10.1016/j.nimb.2014.02.056
Healy, M. Minimising carbon contamination during ion beam analysis. Nucl. Instrum. Methods Phys. Res. B 129, 130–136 (1997).
doi: 10.1016/S0168-583X(97)00127-4
Garson, G. D. Interpreting neural-network connection weights. AI Expert 6, 46–51 (1991).
Oliveira, V. & Silva, T. What do artificial neural networks learn? A study for analysis of RBS spectra. J. Phys. Conf. Ser. 2340, 012003 (2022).
doi: 10.1088/1742-6596/2340/1/012003
Chroneos, A. & Bracht, H. Diffusion of n-type dopants in germanium. Appl. Phys. Rev. 1, 011301 (2014).
doi: 10.1063/1.4838215
Sjöland, K., Munnik, F. & Wätjen, U. Uncertainty budget for ion beam analysis. Nucl. Instrum. Methods Phys. Res. B 161, 275–280 (2000).
doi: 10.1016/S0168-583X(99)00911-8
Jeynes, C. et al. “Total IBA’’-Where are we?. Nucl. Instrum. Methods Phys. Res. B 271, 107–118 (2012).
doi: 10.1016/j.nimb.2011.09.020
Claessens, N. et al. Quantification of area-selective deposition on nanometer-scale patterns using Rutherford backscattering spectrometry. Sci. Rep. 12, 17770 (2022).
pubmed: 36272993
pmcid: 9587986
doi: 10.1038/s41598-022-22645-8
Claessens, N. et al. Ensemble RBS: Probing the compositional profile of 3D microscale structures. Surf. Interfaces 32, 102101 (2022).
doi: 10.1016/j.surfin.2022.102101
Dubey, S. R., Singh, S. K. & Chaudhuri, B. B. Activation functions in deep learning: A comprehensive survey and benchmark. Neurocomputing 503, 92–108 (2022).
doi: 10.1016/j.neucom.2022.06.111
Mayer, M. Ion beam analysis of rough thin films. Nucl. Instrum. Methods Phys. Res. B 194, 177–186 (2002).
doi: 10.1016/S0168-583X(02)00689-4
Barradas, N., Jeynes, C. & Webb, R. Simulated annealing analysis of Rutherford backscattering data. Appl. Phys. Lett. 71, 291–293 (1997).
doi: 10.1063/1.119524
Ziegler, J. F. Srim-2003. Nucl. Instrum. Methods Phys. Res. B 219, 1027–1036 (2004).
doi: 10.1016/j.nimb.2004.01.208