Machine Learning Based Electronic Structure Predictors in Single-Atom Alloys: A Model Study of CO Kink-Site Adsorption across Transition Metal Substrates
Source abstract
Abstract
This work reports on a comprehensive analysis of the predictive capacity and underlying physicochemical trends provided by d -band based electronic structure features as applied to single-atom alloys (SAAs). Taking CO adsorption energies at kink sites as a model framework, SAA adsorption trends are examined across a range of substrates with vastly differing intrinsic CO adsorption trends. Through this approach, it is demonstrated that SAA adsorption properties can be highly transferable, often displaying atom-like behavior independent of the host substrate, particularly in groups 6 through 12 of the periodic table. The predictability of such SAA behavior is found, however, to be highly qualitative for single d -band based electronic structure features. Nevertheless, it is shown that predictive capacity can be greatly improved through the creation of a feature space comprised of as few as 8 electronic structure features. Intriguingly, following the framework of Hammer and Nørskov, the machine learning accuracy of d -band based electronic structure features is shown to be sensitive to the atomic configuration diversity present in the training ensemble with model accuracy systematically improving through restrictions in the configurational space. More directly, it is shown that elements to the far left of the transition metal block such as Zr and Hf may exhibit CO binding properties comparable to Cu in the CO 2 reduction reaction. However, impurities from groups 6–10 are demonstrated to overbind in a highly transferable manner in line with established pure substrate trends and are likely to act as unwanted posing species concerning CO and the overall CO 2 reduction reaction. The results of this work broadly lay out the predictive capabilities of d -band features as applied to SAAs, as well as their propensity for exhibiting transferable binding properties among d -band substrates.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: CO2 Reduction Techniques and Catalysts · Machine Learning in Materials Science · Electrocatalysts for Energy Conversion
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Division of Materials Engineering, Faculty of Engineering, McGill University, Montréal, Québec H3A 0C5, Canada
Department of Chemistry, McGill University, Montréal, Québec H3A 0B8, Canada
Digital Technologies Research Centre, National Research Council Canada, Ottawa, Ontario K1A 0R6, Canada
Centre for the Physics of Materials, Department of Physics, McGill University, Montréal, Québec H3A 2T8, Canada
Funding
National Research Council Canada · Faculty of Engineering, McGill University
References (88)
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. 10.1038/s41467-021-23115-x10.1038/s41467-021-23115-x ↗
6. 10.1002/adma.20200184810.1002/adma.202001848 ↗
7. 10.1063/5.007362810.1063/5.0073628 ↗
8. 10.1016/0039-6028(96)80007-010.1016/0039-6028(96)80007-0 ↗
9. 10.1016/S0360-0564(02)45013-410.1016/S0360-0564(02)45013-4 ↗
10. 10.1038/srep3591610.1038/srep35916 ↗
11. 10.1063/1.474611710.1063/1.4746117 ↗
12. 10.1103/PhysRevB.89.11511410.1103/PhysRevB.89.115114 ↗
13. 10.1103/PhysRevB.82.04541410.1103/PhysRevB.82.045414 ↗
14. 10.1126/science.aad886810.1126/science.aad8868 ↗
15. 10.1038/s41557-018-0125-510.1038/s41557-018-0125-5 ↗
16. 10.1038/s41467-021-22048-910.1038/s41467-021-22048-9 ↗
17. 10.1021/acs.jcim.8b0065710.1021/acs.jcim.8b00657 ↗
18. 10.1021/acscatal.8b0447810.1021/acscatal.8b04478 ↗
19. 10.1021/acs.jpcc.0c0596410.1021/acs.jpcc.0c05964 ↗
20. 10.1038/s41467-020-14969-810.1038/s41467-020-14969-8 ↗
21. 10.1039/D1TA09184K10.1039/D1TA09184K ↗
22. 10.1039/C9TA07651D10.1039/C9TA07651D ↗
23. 10.1021/acs.jpcc.7b1267010.1021/acs.jpcc.7b12670 ↗
24. 10.1038/s41467-020-20342-610.1038/s41467-020-20342-6 ↗
25. 10.1021/acs.jpclett.5b0166010.1021/acs.jpclett.5b01660 ↗
26. 10.1021/cs200462f10.1021/cs200462f ↗
27. 10.1021/nl500567410.1021/nl5005674 ↗
28. 10.1016/j.cattod.2016.04.01310.1016/j.cattod.2016.04.013 ↗
29. 10.1021/acscatal.7b0164810.1021/acscatal.7b01648 ↗
30. 10.1007/s10562-019-02705-x10.1007/s10562-019-02705-x ↗
31. 10.1021/acs.jpcc.6b1280010.1021/acs.jpcc.6b12800 ↗
32. 10.1021/acs.jpcc.0c0149210.1021/acs.jpcc.0c01492 ↗
33. 10.1038/s41929-018-0063-z10.1038/s41929-018-0063-z ↗
34. 10.1126/sciadv.aax510110.1126/sciadv.aax5101 ↗
35. 10.1126/science.aab350110.1126/science.aab3501 ↗
36. 10.1016/j.joule.2018.12.01510.1016/j.joule.2018.12.015 ↗
37. 10.1038/nchem.222610.1038/nchem.2226 ↗
38. 10.1103/PhysRevB.74.15543910.1103/PhysRevB.74.155439 ↗
39. 10.1021/acs.jpclett.5b0072210.1021/acs.jpclett.5b00722 ↗
40. 10.1016/j.jelechem.2006.05.01310.1016/j.jelechem.2006.05.013 ↗
41. 10.1021/ja302668n10.1021/ja302668n ↗
42. 10.1002/ange.20130147010.1002/ange.201301470 ↗
43. 10.1021/acs.nanolett.0c0470310.1021/acs.nanolett.0c04703 ↗
44. 10.1021/acs.chemrev.8b0070510.1021/acs.chemrev.8b00705 ↗
45. 10.1002/anie.20201044910.1002/anie.202010449 ↗
46. 10.1007/s12678-016-0314-110.1007/s12678-016-0314-1 ↗
47. 10.1103/PhysRevB.60.614610.1103/PhysRevB.60.6146 ↗
48. 10.1103/PhysRevLett.81.281910.1103/PhysRevLett.81.2819 ↗
49. 10.1038/376238a010.1038/376238a0 ↗
50. 10.1103/PhysRevB.47.55810.1103/PhysRevB.47.558 ↗
51. 10.1016/0927-0256(96)00008-010.1016/0927-0256(96)00008-0 ↗
52. 10.1103/PhysRevB.49.1425110.1103/PhysRevB.49.14251 ↗
53. 10.1063/1.218700610.1063/1.2187006 ↗
54. 10.1103/PhysRevB.50.1795310.1103/PhysRevB.50.17953 ↗
55. 10.1103/PhysRevB.59.175810.1103/PhysRevB.59.1758 ↗
56. 10.1103/PhysRevLett.77.386510.1103/PhysRevLett.77.3865 ↗
57. 10.1088/1361-651X/ac13ca10.1088/1361-651X/ac13ca ↗
58. 10.1103/RevModPhys.60.60110.1103/RevModPhys.60.601 ↗
59. 10.1039/c3cp54822h10.1039/c3cp54822h ↗
60. 10.1021/ed067p30710.1021/ed067p307 ↗
61. 10.1063/1.172569710.1063/1.1725697 ↗
62. 10.1063/1.174249310.1063/1.1742493 ↗
63. 10.1063/1.32353910.1063/1.323539 ↗
64. 10.1136/oem.53.7.50410.1136/oem.53.7.504 ↗
65. Harrison W. A. · 2012
66. 10.1103/PhysRevB.35.248710.1103/PhysRevB.35.2487 ↗
67. 10.1093/bioinformatics/btz47010.1093/bioinformatics/btz470 ↗
68. Olson R. S. · 2016 · 12310.1007/978-3-319-31204-0_9 ↗
69. Olson R. S. · 2016 · 48510.1145/2908812.2908918 ↗
70. Pedregosa F. · J. Mach Learn Res. · 2011 · 12 · 2825
71. 10.1177/027836490404548110.1177/0278364904045481 ↗
72. Grus J. · 2019
73. 10.1016/j.jcat.2004.02.03410.1016/j.jcat.2004.02.034 ↗
74. 10.1016/j.eswa.2017.01.05110.1016/j.eswa.2017.01.051 ↗
75. Adali S. · J. Digit. Inf. Manag. · 2007 · 5 · 292
76. 10.18637/jss.v036.i1110.18637/jss.v036.i11 ↗
77. Biecek P. · J. Mach. Learn. Res. · 2018 · 19 · 1
78. Biecek P. · 202110.1201/9780429027192 ↗
79. 10.18637/jss.v028.i0510.18637/jss.v028.i05 ↗
80. Kuhn M. · 2016
81. Dwork C. · 2001 · 61310.1145/371920.372165 ↗
82. Copeland, A. A. Reasonable Social Welfare Function. Seminar on Applications of Mathematics to Social Sciences. University of Michigan, 1951.
83. 10.1002/wics.11110.1002/wics.111 ↗
84. Kittel C. · 2004
85. 10.3905/joi.2007.68182010.3905/joi.2007.681820 ↗
86. 10.1103/PhysRevB.79.07542210.1103/PhysRevB.79.075422 ↗
87. 10.1038/nmat339110.1038/nmat3391 ↗
88. 10.1016/S0013-4686(00)00559-410.1016/S0013-4686(00)00559-4 ↗