journal article·2024-09Open access

Interpretable Machine Learning‐Assisted High‐Throughput Screening for Understanding NRR Electrocatalyst Performance Modulation between Active Center and C‐N Coordination

Jinxin Sun, Anjie Chen, Junming Guan, Ying Han, Yongjun Liu, Xianghong Niu, Maoshuai He, Li Shi, Jinlan Wang, Xiuyun Zhang

Abstract

Understanding the correlation between the fundamental descriptors and catalytic performance is meaningful to guide the design of high‐performance electrochemical catalysts. However, exploring key factors that affect catalytic performance in the vast catalyst space remains challenging for people. Herein, to accurately identify the factors that affect the performance of N2 reduction, we apply interpretable machine learning (ML) to analyze high‐throughput screening results, which is also suited to other surface reactions in catalysis. To expound on the paradigm, 33 promising catalysts are screened from 168 carbon‐supported candidates, specifically single‐atom catalysts (SACs) supported by a BC3 monolayer (TM@VB/C‐Nn = 0–3‐BC3) via high‐throughput screening. Subsequently, the hybrid sampling method and XGBoost model are selected to classify eligible and non‐eligible catalysts. Through feature interpretation using Shapley Additive Explanations (SHAP) analysis, two crucial features, that is, the number of valence electrons (Nv) and nitrogen substitution (Nn), are screened out. Combining SHAP analysis and electronic structure calculations, the synergistic effect between an active center with low valence electron numbers and reasonable C‐N coordination (a medium fraction of nitrogen substitution) can exhibit high catalytic performance. Finally, six superior catalysts with a limiting potential lower than −0.4 V are predicted. Our workflow offers a rational approach to obtaining key information on catalytic performance from high‐throughput screening results to design efficient catalysts that can be applied to other materials and reactions.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Ammonia Synthesis and Nitrogen Reduction · Machine Learning in Materials Science · Electrocatalysts for Energy Conversion

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

Affiliations

College of Physics Science and Technology Yangzhou University Yangzhou 225002 China

State Key Laboratory of Organic Electronics and Information Displays (KLOEID) & Institute of Advanced Materials (IAM), School of Science Nanjing University of Posts and Telecommunications Nanjing 210023 China

College of Chemistry and Molecular Engineering Qingdao University of Science and Technology Qingdao 266042 China

School of Physics & Key Laboratory of Quantum Materials and Devices, Ministry of Education Southeast University Nanjing 20089 China

Funding

National Natural Science Foundation of China

References (55)

Show source-provided references
1. 10.1126/science.aaq168410.1126/science.aaq1684 ↗
2. 10.1038/ngeo32510.1038/ngeo325 ↗
3. 10.1021/jacs.7b0439310.1021/jacs.7b04393 ↗
4. 10.1021/jacs.2c0189910.1021/jacs.2c01899 ↗
5. 10.1021/acscentsci.0c0055210.1021/acscentsci.0c00552 ↗
6. 10.1126/science.110643510.1126/science.1106435 ↗
7. 10.1016/j.apsusc.2022.15333810.1016/j.apsusc.2022.153338 ↗
8. 10.1021/acscatal.9b0224510.1021/acscatal.9b02245 ↗
9. 10.1002/adfm.20200805610.1002/adfm.202008056 ↗
10. 10.1039/D2NH00451H10.1039/D2NH00451H ↗
11. 10.1039/C9TA01410A10.1039/C9TA01410A ↗
12. 10.1039/C1CP22271F10.1039/C1CP22271F ↗
13. 10.1021/jacs.7b0521310.1021/jacs.7b05213 ↗
14. 10.1002/cssc.20150032210.1002/cssc.201500322 ↗
15. 10.1016/j.nanoen.2020.10552710.1016/j.nanoen.2020.105527 ↗
16. 10.1021/acsami.0c1847210.1021/acsami.0c18472 ↗
17. 10.1007/s12274-021-4009-410.1007/s12274-021-4009-4 ↗
18. 10.1039/D1NR02883A10.1039/D1NR02883A ↗
19. 10.1038/s41746-020-0249-z10.1038/s41746-020-0249-z ↗
20. 10.1016/j.artint.2021.10352510.1016/j.artint.2021.103525 ↗
21. 10.1002/advs.20220263810.1002/advs.202202638 ↗
22. 10.1002/adma.20230084810.1002/adma.202300848 ↗
23. 10.1038/s41929-022-00744-z10.1038/s41929-022-00744-z ↗
24. 10.1038/s42254-022-00456-010.1038/s42254-022-00456-0 ↗
25. 10.1038/s42256-019-0138-910.1038/s42256-019-0138-9 ↗
26. 10.1016/j.future.2019.07.05910.1016/j.future.2019.07.059 ↗
27. 10.1016/j.ins.2021.11.01010.1016/j.ins.2021.11.010 ↗
28. 10.1038/s41524-022-00826-310.1038/s41524-022-00826-3 ↗
29. 10.1016/j.scs.2022.10425510.1016/j.scs.2022.104255 ↗
30. 10.1016/j.patcog.2022.10900810.1016/j.patcog.2022.109008 ↗
31. 10.1016/j.media.2021.10229510.1016/j.media.2021.102295 ↗
32. 10.1103/PhysRevB.50.1836010.1103/PhysRevB.50.18360 ↗
33. 10.1039/D0NR07580A10.1039/D0NR07580A ↗
34. 10.1002/adma.20180369410.1002/adma.201803694 ↗
35. 10.1039/D0TA01565B10.1039/D0TA01565B ↗
36. 10.1002/anie.20190020310.1002/anie.201900203 ↗
37. Lee S. A. · Exp. Dermatol. · 2021 · 1
38. Kim J. · Exp. Dermatol. · 2022 · 2
39. 10.1021/acsami.1c0641410.1021/acsami.1c06414 ↗
40. 10.1021/acs.jpcc.2c0589410.1021/acs.jpcc.2c05894 ↗
41. 10.1021/acsnano.2c1060710.1021/acsnano.2c10607 ↗
42. 10.1021/acscatal.8b0090510.1021/acscatal.8b00905 ↗
43. 10.1039/C9NR08969A10.1039/C9NR08969A ↗
44. 10.1021/jacs.2c0454010.1021/jacs.2c04540 ↗
45. 10.1016/j.scs.2022.10367710.1016/j.scs.2022.103677 ↗
46. 10.1016/j.ajp.2022.10331610.1016/j.ajp.2022.103316 ↗
47. 10.1002/jmv.2739310.1002/jmv.27393 ↗
48. 10.1016/j.chempr.2021.11.00910.1016/j.chempr.2021.11.009 ↗
49. 10.1103/PhysRevB.50.1795310.1103/PhysRevB.50.17953 ↗
50. 10.1103/PhysRevLett.77.386510.1103/PhysRevLett.77.3865 ↗
51. 10.1007/s00214005003110.1007/s002140050031 ↗
52. 10.1103/PhysRevB.54.1116910.1103/PhysRevB.54.11169 ↗
53. 10.1103/PhysRevB.39.316810.1103/PhysRevB.39.3168 ↗
54. 10.1016/j.apsusc.2021.14913110.1016/j.apsusc.2021.149131 ↗
55. 10.1016/j.jechem.2020.04.01410.1016/j.jechem.2020.04.014 ↗