Adsorbate-Dependent Electronic Structure Descriptors for Machine Learning-Driven Binding Energy Predictions in Diverse Single Atom Alloys: A Reductionist Approach
Source abstract
Abstract
A long-standing challenge in the design of single atom alloys (SAAs), for catalytic applications, is the determination of a feature space that maximally correlates to molecular binding energies per the Sabatier principle. The more representative a feature space is of the underlying binding properties, the greater the predictive capability of a given machine learning (ML) algorithm. Moreover, the greater the diversity and range of SAA impurities/sites examined, the greater the difficulty in arriving at such a predictive feature. In this work, we undertake to examine the degree to which adsorbate electronic structure properties might address this challenge, in a distinct departure from the traditional substrate electronic structure feature construction found in the catalysis literature. Specifically, as a model system, we explore the predictive capacity of the p-orbital projected density of states (PDOS) pertaining to the adsorption of CO molecules on a wide range of SAA substrates, impurity embeddings, and vicinal cuts. This analysis is executed in two parts. First, we explore the degree to which the entire PDOS distribution, in the form of an energy-dependent vector, can predict binding energies. Subsequently, guided by a rigorous intrinsic dimensionality analysis, uniform manifold approximation and projection visualization, and chemical intuition, we are able to reduce the predictive feature space to just three physical quantities based on semicore level properties and charge filling of the adsorbate–as embedded with the PDOS distribution. This near-intrinsic feature space and the PDOS distribution are both shown to provide significant improvements in predictive accuracy when coupled with regression-based ML methods, even when tackling highly diverse chemical datasets. The results of this analysis both further substantiate the transferability characteristics of SAAs and indicate that adsorbate-based electronic structure features (from either relaxed or unrelaxed chemical datasets) are powerful tools in the prediction of catalytic binding energies in such systems. They also underscore the predictive benefit of finding a feature space with a dimension equal to the intrinsic dimensionality of the data that can maximally correlate with the physical property under investigation when employing ML methods in catalysis studies.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Electrocatalysts for Energy Conversion · CO2 Reduction Techniques and Catalysts
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Division of Materials Engineering, Faculty of Engineering
McGill University
Institute for Information Technology
National Research Council Canada
Canada & Centre for the Physics of Materials, Department of Physics
Funding
National Research Council Canada · Faculty of Engineering, McGill University
References (78)
Show source-provided references
1. 10.1021/acs.accounts.8b0049010.1021/acs.accounts.8b00490 ↗
2. 10.1126/science.121586410.1126/science.1215864 ↗
3. 10.1021/acs.chemrev.0c0057610.1021/acs.chemrev.0c00576 ↗
4. 10.1021/acs.chemrev.0c0007810.1021/acs.chemrev.0c00078 ↗
5. 10.1021/acscatal.8b0088110.1021/acscatal.8b00881 ↗
6. 10.1039/f1989850230910.1039/f19898502309 ↗
7. 10.1021/ja00250a04410.1021/ja00250a044 ↗
8. 10.1021/jp970284i10.1021/jp970284i ↗
9. 10.1016/0022-0728(88)80071-810.1016/0022-0728(88)80071-8 ↗
10. 10.1149/1.209699310.1149/1.2096993 ↗
11. 10.1021/acsenergylett.8b0009210.1021/acsenergylett.8b00092 ↗
12. 10.1021/acs.chemrev.8b0070510.1021/acs.chemrev.8b00705 ↗
13. 10.1021/acs.jpcc.3c0270510.1021/acs.jpcc.3c02705 ↗
14. 10.1002/aic.1619810.1002/aic.16198 ↗
15. 10.1038/nmat122310.1038/nmat1223 ↗
16. 10.1038/s41467-021-22048-910.1038/s41467-021-22048-9 ↗
17. 10.1021/acs.jpclett.5b0166010.1021/acs.jpclett.5b01660 ↗
18. 10.1038/s41467-020-20342-610.1038/s41467-020-20342-6 ↗
19. 10.1016/0039-6028(96)80007-010.1016/0039-6028(96)80007-0 ↗
20. Hammer, B.; Nørskov, J. K. Advances in Catalysis; Elsevier, 2000; Vol. 45, pp 71–129.10.1016/S0360-0564(02)45013-4 ↗
21. 10.1038/srep3591610.1038/srep35916 ↗
22. 10.1103/PhysRevB.82.04541410.1103/PhysRevB.82.045414 ↗
23. 10.1021/acs.jpcc.0c0596410.1021/acs.jpcc.0c05964 ↗
24. 10.1038/s41467-020-14969-810.1038/s41467-020-14969-8 ↗
25. 10.1039/D1TA09184K10.1039/D1TA09184K ↗
26. 10.1103/PhysRevB.89.11511410.1103/PhysRevB.89.115114 ↗
27. 10.1021/acscatal.8b0447810.1021/acscatal.8b04478 ↗
28. 10.1021/cs200462f10.1021/cs200462f ↗
29. 10.1021/nl500567410.1021/nl5005674 ↗
30. 10.1016/j.cattod.2016.04.01310.1016/j.cattod.2016.04.013 ↗
31. 10.1021/acscatal.7b0164810.1021/acscatal.7b01648 ↗
32. 10.1021/acs.jcim.8b0065710.1021/acs.jcim.8b00657 ↗
33. 10.1007/s10562-019-02705-x10.1007/s10562-019-02705-x ↗
34. 10.1021/acs.jpcc.6b1280010.1021/acs.jpcc.6b12800 ↗
35. 10.1021/acs.jpcc.0c0149210.1021/acs.jpcc.0c01492 ↗
36. 10.1021/acs.jpcc.7b1267010.1021/acs.jpcc.7b12670 ↗
37. 10.1038/s41929-018-0063-z10.1038/s41929-018-0063-z ↗
38. 10.1016/j.joule.2018.12.01510.1016/j.joule.2018.12.015 ↗
39. 10.1103/PhysRevB.47.55810.1103/PhysRevB.47.558 ↗
40. 10.1016/0927-0256(96)00008-010.1016/0927-0256(96)00008-0 ↗
41. 10.1103/PhysRevB.49.1425110.1103/PhysRevB.49.14251 ↗
42. 10.1063/1.218700610.1063/1.2187006 ↗
43. 10.1103/PhysRevB.50.1795310.1103/PhysRevB.50.17953 ↗
44. 10.1103/PhysRevB.59.175810.1103/PhysRevB.59.1758 ↗
45. 10.1103/PhysRevLett.77.386510.1103/PhysRevLett.77.3865 ↗
46. 10.1093/bioinformatics/btz47010.1093/bioinformatics/btz470 ↗
47. Olson, R. S.; Urbanowicz, R. J.; Andrews, P. C.; Lavender, N. A.; Kidd, L. C.; Moore, J. H. Applications of Evolutionary Computation: 19th European Conference, EvoApplications 2016, Porto, Portugal, March 30─April 1, 2016, Proceedings, Part I; Squillero, G.; Burelli, P., Eds. Springer International Publishing, 2016; pp 123–137, Chapter Automating Biomedical Data Science Through Tree-Based Pipeline Optimization.10.1007/978-3-319-31204-0_9 ↗
48. Olson, R. S.; Bartley, N.; Urbanowicz, R. J.; Moore, J. H. Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science. Proceedings of the Genetic and Evolutionary Computation Conference 2016: New York, NY, USA, 2016; pp 485–492.10.1145/2908812.2908918 ↗
49. 10.1103/PhysRevB.60.614610.1103/PhysRevB.60.6146 ↗
50. 10.1103/PhysRevLett.81.281910.1103/PhysRevLett.81.2819 ↗
51. 10.1038/376238a010.1038/376238a0 ↗
52. 10.1103/PhysRev.124.4110.1103/PhysRev.124.41 ↗
53. 10.1103/PhysRev.178.112310.1103/PhysRev.178.1123 ↗
54. 10.1007/s11244-013-0159-210.1007/s11244-013-0159-2 ↗
55. 10.1038/s41557-018-0125-510.1038/s41557-018-0125-5 ↗
56. 10.1016/j.susc.2018.11.01910.1016/j.susc.2018.11.019 ↗
57. 10.1007/s10994-012-5294-710.1007/s10994-012-5294-7 ↗
58. 10.1186/1745-6150-2-210.1186/1745-6150-2-2 ↗
59. 10.48550/arXiv.1002.205010.48550/arXiv.1002.2050 ↗
60. 10.1109/t-c.1971.22320810.1109/t-c.1971.223208 ↗
61. 10.1007/s10618-018-0578-610.1007/s10618-018-0578-6 ↗
62. 10.48550/arXiv.2209.1447510.48550/arXiv.2209.14475 ↗
63. 10.1038/s41598-017-11873-y10.1038/s41598-017-11873-y ↗
64. 10.1016/0167-2789(83)90298-110.1016/0167-2789(83)90298-1 ↗
65. 10.1007/s11263-008-0144-610.1007/s11263-008-0144-6 ↗
66. 10.1214/aos/117634324710.1214/aos/1176343247 ↗
67. Levina, E.; Bickel, P. Maximum likelihood estimation of intrinsic dimension. Adv. Neural Inf. Process., 2004; Vol. 17.
68. 10.1109/TSP.2009.203172210.1109/TSP.2009.2031722 ↗
69. Farahmand, A. M.; Szepesvári, C.; Audibert, J.Y. Manifold-adaptive dimension estimation. Proceedings of the 24th International Conference on Machine Learning, 2007; pp 265–272.10.1145/1273496.1273530 ↗
70. Albergante, L.; Bac, J.; Zinovyev, A. Estimating the effective dimension of large biological datasets using Fisher separability analysis. International Joint Conference on Neural Networks (IJCNN) 2019, 2019; pp 1–8.10.1109/IJCNN.2019.8852450 ↗
71. 10.3390/e2310136810.3390/e23101368 ↗
72. 10.1162/neco_a_0143410.1162/neco_a_01434 ↗
73. 10.1177/027836490404548110.1177/0278364904045481 ↗
74. 10.1103/RevModPhys.60.60110.1103/RevModPhys.60.601 ↗
75. Nørskov J. K. · 201410.1002/9781118892114 ↗
76. 10.1016/j.commatsci.2017.07.03010.1016/j.commatsci.2017.07.030 ↗
77. 10.1021/acs.chemrev.0c0111110.1021/acs.chemrev.0c01111 ↗
78. https://opencatalystproject.org.