journal article·2024Open access

NestedAE: interpretable nested autoencoders for multi-scale materials characterization

Nikhil Thota, Maitreyee Sharma Priyadarshini, Rigoberto Hernandez

Materials Horizons· Volume 11· Issue 3

Abstract

We introduce an interpretable machine learning architecture, NestedAE, for multiscale materials using nested supervised autoencoders. We benchmarked the performance of NestedAE on two databases: (1) a synthetic dataset created from nested analytical functions whose dimensionality is therefore known a priori, and (2) a multiscale MHP dataset that is a combination of an open source dataset containing atomic and ionic properties, and a second dataset containing device characterization using current density-voltage (J-V) analysis. The NestedAE architecture was found to have higher noise robustness and lower reconstruction losses when compared to a vanilla autoencoder (AE). Its application on the MHP dataset revealed links between crystal scale properties and device performance in agreement with earlier experimental observations.
Source: europepmc · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Machine Learning in Materials Science · Thermography and Photoacoustic Techniques · Neural Networks and Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Chemical and Biomolecular Engineering Department, Johns Hopkins University, Baltimore, MD, USA

Chemistry Department, Johns Hopkins University, Baltimore, MD, USA

Materials Science and Engineering Department, Johns Hopkins University, Baltimore, MD, USA

Funding

Basic Energy Sciences · Division of Information and Intelligent Systems

References (36)

Show source-provided references
1. I. R. E. Agency, World Energy Transitions Outlook 2023: 1.5 Pathway, 2023, https://www.irena.org/Publications/2023/Jun/World-Energy-Transitions-Outlook-2023 , Accessed on September 13, 2023
2. Peng · Arch. Comput. Methods Eng. · 2021 · 28 · 101710.1007/s11831-020-09405-5 ↗
3. Clark · ACS Cent. Sci. · 2021 · 7 · 127110.1021/acscentsci.1c00685 ↗
4. Fish · Nat. Mater. · 2021 · 20 · 77410.1038/s41563-020-00913-0 ↗
5. Schmauder · Mater. Today · 2016 · 19 · 13010.1016/j.mattod.2016.01.013 ↗
6. Noid · J. Chem. Phys. · 2008 · 128 · 24411410.1063/1.2938860 ↗
7. Cipcigan · Rev. Mod. Phys. · 2019 · 91 · 02500310.1103/RevModPhys.91.025003 ↗
8. Jin · J. Chem. Theory Comput. · 2022 · 18 · 575910.1021/acs.jctc.2c00643 ↗
9. Marrink · J. Phys. Chem. B · 2007 · 11 · 781210.1021/jp071097f ↗
10. Periole · J. Chem. Theory Comput. · 2009 · 5 · 253110.1021/ct9002114 ↗
11. Tao · npj Comput. Mater. · 2021 · 7 · 2310.1038/s41524-021-00495-8 ↗
12. Hui · Comput. Mater. Sci. · 2023 · 226 · 11221510.1016/j.commatsci.2023.112215 ↗
13. Xu · Energy Adv. · 2023 · 2 · 89610.1039/D3YA00057E ↗
14. D. P.Kingma and M.Welling , arXiv , 2013 , preprint, arXiv:1312.6114 10.48550/arXiv.1312.611410.48550/arXiv.1312.6114 ↗
15. Gómez-Bombarelli · ACS Cent. Sci. · 2018 · 4 · 26810.1021/acscentsci.7b00572 ↗
16. Choubisa · Matter · 2020 · 3 · 43310.1016/j.matt.2020.04.016 ↗
17. Court · J. Chem. Inf. Model. · 2020 · 60 · 451810.1021/acs.jcim.0c00464 ↗
18. Z.Ren , F.Oviedo , H.Xue , M.Thway , K.Zhang , N.Li , J. D.Perea , M.Layurova , Y.Wang , S.Tian , T.Heumueller , E.Birgersson , F.Lin , A.Aberle , S.Sun , I. M.Peters , R.Stangl , C. J.Brabec and T.Buonassisi , 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC), 2019, pp. 3054–3058
19. Bengio · Adv. Neural Inf. Process Syst. · 2006 · 1096
20. P.Vincent , H.Larochelle , Y.Bengio and P.-A.Manzagol , Proceedings of the 25th International Conference on Machine Learning, 2008, pp. 1096–1103
21. D.Erhan , A.Courville , Y.Bengio and P.Vincent , Proceedings of the thirteenth international conference on artificial intelligence and statistics, 2010, pp. 201–208
22. M.Ranzato and M.Szummer , Proceedings of the 25th international conference on Machine learning, 2008, pp. 792–799
23. Green · Prog. Photovolt. Res. Appl. · 2023 · 31 · 65110.1002/pip.3726 ↗
24. Tu · Adv. Mater. · 2021 · 33 · 200654510.1002/adma.202006545 ↗
25. Hsiao · J. Mater. Chem. A · 2015 · 3 · 1537210.1039/C5TA01376C ↗
26. Bellman · J. Math. Mech. · 1957 · 679
27. X.Glorot , A.Bordes and Y.Bengio , Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011, pp. 315–323
28. G. E.Hinton , N.Srivastava , A.Krizhevsky , I.Sutskever and R. R.Salakhutdinov , arXiv, 2012, preprint, arXiv:1207.0580
29. Mannodi-Kanakkithodi · Energy Environ. Sci. · 2022 · 15 · 193010.1039/D1EE02971A ↗
30. Jacobsson · Nat. Energy · 2022 · 7 · 10710.1038/s41560-021-00941-3 ↗
31. Babayigit · Joule · 2018 · 2 · 120510.1016/j.joule.2018.06.009 ↗
32. Le · Adv. Neural Inf. Process Syst. · 2018 · 31 · 1
33. Li · Adv. Energy Mater. · 2019 · 9 · 190189110.1002/aenm.201901891 ↗
34. Yang · EcoMat · 2021 · 3 · e1212710.1002/eom2.12127 ↗
35. Zhao · Chem. Eng. J. · 2022 · 435 · 13514010.1016/j.cej.2022.135140 ↗
36. Rombach · Energy Environ. Sci. · 2021 · 14 · 516110.1039/D1EE02095A ↗