Residual-Compensated Ensemble Framework for High-Accuracy Interpretable Prediction of Binding Energies on Alloy Surfaces
Source abstract
Abstract
Highly accurate prediction models typically require high-dimensional structures, which would obscure the underlying physical mechanisms. Consequently, balancing prediction accuracy with model interpretability remains a fundamental challenge in binding energy prediction. Herein, we propose a residual-compensated SISSO-RFR framework for predicting binding energies of key atomic species (C, N, and O). First, an interpretable SISSO model incorporating five descriptors is developed, and the descriptors further demonstrate the significant contribution of surface elements exhibiting strong affinity to the adsorbate. Subsequently, a Random Forest Regression (RFR) model compensates for residual errors between the calculated values and the SISSO predictions. The resulting SISSO-RFR framework demonstrates a significantly higher accuracy than both conventional ensemble models and dual SISSO approaches. This synergistic integration strikes an optimal balance between model transparency inherent in white-box SISSO approaches and predictive accuracy achieved through RFR's error compensation mechanisms. The framework effectively balances accuracy with interpretability, offering a streamlined approach to deepen understanding of the structure-performance relationship and accelerate catalyst discovery.
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
Zhongyuan Critical Metals Laboratory and School of Material Science and Engineering
Zhengzhou University
National Key Laboratory of Special Rare Metal Materials
Zhongyuan Critical Metals Laboratory
School of Chemical Engineering
School of Materials Science and Technology
Huazhong University of Science and Technology
Funding
National Key Research and Development Program of China · Key Research Projects Plan of Higher Education Institutions in Henan Province · Zhongyuan Critical Metals Laboratory, Zhengzhou University
References (41)
Show source-provided references
1. 10.1063/1.494689410.1063/1.4946894 ↗
2. 10.1126/science.aad499810.1126/science.aad4998 ↗
3. 10.1016/j.chempr.2024.06.02210.1016/j.chempr.2024.06.022 ↗
4. 10.1038/s41929-018-0142-110.1038/s41929-018-0142-1 ↗
5. 10.1039/D4EY00023D10.1039/D4EY00023D ↗
6. 10.1021/acscatal.0c0208910.1021/acscatal.0c02089 ↗
7. 10.1002/cnl2.7001710.1002/cnl2.70017 ↗
8. 10.1016/j.pnsc.2024.04.01410.1016/j.pnsc.2024.04.014 ↗
9. 10.1039/D3SC06990G10.1039/D3SC06990G ↗
10. 10.1126/science.aan541210.1126/science.aan5412 ↗
11. 10.1038/s41467-019-11848-910.1038/s41467-019-11848-9 ↗
12. 10.1038/s41467-024-55688-810.1038/s41467-024-55688-8 ↗
13. 10.1038/s41467-025-59709-y10.1038/s41467-025-59709-y ↗
14. 10.1021/acscatal.0c0491110.1021/acscatal.0c04911 ↗
15. 10.1002/cnl2.19310.1002/cnl2.193 ↗
16. 10.1103/PhysRevLett.99.01610510.1103/PhysRevLett.99.016105 ↗
17. 10.1016/j.comptc.2024.11492310.1016/j.comptc.2024.114923 ↗
18. 10.1016/j.pnsc.2024.08.00310.1016/j.pnsc.2024.08.003 ↗
19. 10.1021/acscatal.2c0064810.1021/acscatal.2c00648 ↗
20. 10.1039/D2TA07216E10.1039/D2TA07216E ↗
21. 10.1021/jacs.3c1298410.1021/jacs.3c12984 ↗
22. 10.1126/science.116589310.1126/science.1165893 ↗
23. 10.1016/j.chempr.2020.09.00110.1016/j.chempr.2020.09.001 ↗
24. 10.1038/s41929-022-00744-z10.1038/s41929-022-00744-z ↗
25. 10.1038/s41524-022-00884-710.1038/s41524-022-00884-7 ↗
26. Lundberg S. M. · 2017
27. 10.1016/j.jcat.2025.11609810.1016/j.jcat.2025.116098 ↗
28. 10.1103/PhysRevMaterials.2.08380210.1103/PhysRevMaterials.2.083802 ↗
29. 10.1016/j.jcat.2024.11558610.1016/j.jcat.2024.115586 ↗
30. 10.1016/j.jcat.2024.11561010.1016/j.jcat.2024.115610 ↗
31. 10.1016/j.jcat.2024.11565610.1016/j.jcat.2024.115656 ↗
32. 10.1021/acscatal.8b0447810.1021/acscatal.8b04478 ↗
33. 10.1021/acscatal.3c0061110.1021/acscatal.3c00611 ↗
34. 10.1021/jacs.4c1637710.1021/jacs.4c16377 ↗
35. 10.1039/D2TA02326A10.1039/D2TA02326A ↗
36. 10.1016/j.cej.2024.15230010.1016/j.cej.2024.152300 ↗
37. 10.1016/j.jcat.2019.01.04010.1016/j.jcat.2019.01.040 ↗
38. 10.1016/j.jcat.2018.04.02510.1016/j.jcat.2018.04.025 ↗
39. 10.1016/j.jcat.2025.11597110.1016/j.jcat.2025.115971 ↗
40. 10.1038/s41524-022-00896-310.1038/s41524-022-00896-3 ↗
41. 10.1016/j.cej.2022.13718610.1016/j.cej.2022.137186 ↗