Multilevel Learning of Activity and Selectivity Descriptors for CO2 Conversion Catalysts

Machine learning offers an efficient strategy for identifying catalyst candidates, but simultaneous prediction of activity and selectivity remains challenging. In this study, a multilevel machine-learning framework was developed using a dataset of 1,260 catalyst entries and 8,740 calculated adsorption and reaction descriptors collected from transition-metal, oxide, and supported catalytic systems. Random forest, gradient boosting, graph neural network, and multilayer perceptron models were compared for predicting CO2 conversion, methanol selectivity, methane selectivity, and olefin selectivity. The best ensemble model achieved an R² value of 0.87 for activity prediction and a classification accuracy of 84.3% for dominant product selectivity. Feature-importance analysis identified CO2 adsorption energy, hydrogen affinity, oxygen-vacancy formation energy, and metal–oxygen coordination number as the most influential descriptors. The framework provides a scalable route for screening catalysts across thermochemical and photocatalytic CO2 conversion systems.

1. Liang, S., Zhang, X., Du, Y., & Chen, W. (2026). Supply Network Restructuring and Capacity Ramp-Up Limits in the Localized Expansion of High-Performance Computing Equipment Production. Available at SSRN 7339738.
2. Ghangrekar, O. M., & Balakotaiah, V. (2026). Optimization of CO2 hydrogenation for enhanced methanol selectivity: A combined thermodynamic and kinetic assessment. AIChE Journal, e70401.
3. Bao, Y., & Wang, H. (2026). Edge-to-Cloud Infrastructure Continuum: A Unified Framework for Optimizing Industrial IoT Systems. Available at SSRN 7185578.
4. Yang, Z., Alexandrova, A. N., & Sautet, P. (2026). Modeling CO2 Hydrogenation to Methanol on an Ensemble of Inverse ZrO2 on Cu Catalytic Sites: Mechanism, Reactivity, and Deactivation. Angewandte Chemie, e5448247.
5. Jeong, D. J., Wang, X., Park, N., Lee, D., Lee, Y., Bae, J. W., ... & Kang, J. H. (2026). Linking zeolite structures to reactivity in the carbonylation of dimethyl ether. Industrial Chemistry & Materials.
6. Chen, F., Liang, H., Li, S., Yue, L., & Xu, P. (2025). Design of Domestic Chip Scheduling Architecture for Smart Grid Based on Edge Collaboration.
7. Bozal-Ginesta, C., Pablo-García, S., Choi, C., Tarancón, A., & Aspuru-Guzik, A. (2025). Machine learning for the experimental and computational development of heterogeneous catalysis.
8. Liang, R., Feifan, F. N. U., Liang, Y., & Ye, Z. (2025). Emotion-Aware Interface Adaptation in Mobile Applications Based on Color Psychology and Multimodal User State Recognition. Frontiers in Artificial Intelligence Research, 2(1), 51-57.
9. Mondal, T., & Exner, K. S. (2026). Descriptor-Based Insights into Hydrazine Selectivity in Electrochemical Ammonia Oxidation on Single-Atom Centers of MXenes. ACS Physical Chemistry Au.
10. Du, Y. (2025). Research on Digital Quality Traceability System for Temperature-Controlled Supply Chain of Foreign Trade Wine Driven by Blockchain and IoT. Business and Social Sciences Proceedings, 4, 57-65.
11. Chenebuah, E. T., Nganbe, M., Liu, L., & Tchagang, A. B. (2026). A partially quantum‑informed crystal graph network for direct adsorption energy prediction in catalysis. Scientific Reports.
12. Serrano-Diez, E., Pita-Milleiro, A., Rangel-Garcia, J., Moreno, J. J., Rosello-Merino, M., & Campos, J. (2025). Reversible bimetallic inhibition to modulate selectivity during catalysis. Journal of the American Chemical Society, 147(1), 1271-1281.
13. Bao, Y., Qiu, Y., & Wang, H. (2026, May). Unified Identity Layer for Hyperscale Ecosystems: A Framework for Cross-Platform User Attribution and Experimentation. In 2026 6th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) (pp. 540-543). IEEE.
14. Hossain, M. N., Zhang, L., Neagu, R., & Sun, S. (2025). Exploring the properties, types, and performance of atomic site catalysts in electrochemical hydrogen evolution reactions. Chemical Society Reviews, 54(7), 3323-3386.
15. Gu, X. (2026). Identifying Causal Effects and Analyzing Heterogeneity of User Growth Interventions on Digital Platforms: Evidence from Large-Scale Behavioral Data. Available at SSRN 6809181.
16. Bozal-Ginesta, C., Pablo-García, S., Choi, C., Tarancón, A., & Aspuru-Guzik, A. (2025). Developing machine learning for heterogeneous catalysis with experimental and computational data. Nature Reviews Chemistry, 9(9), 601-616.
17. You, S. (2026). Verifiable Audit Mechanisms in AI Compliance Automation: Scalability. Available at SSRN 6547458.
18. Jiao, Y., Shi, T., Zhao, B., & Wang, A. (2026). The Impact of VR Sketching Simulations on the Assessment of Scale and Site Suitability in Public Art Spaces.
19. Toney, J. W., St. Michel, R. G., Garrison, A. G., Kevlishvili, I., & Kulik, H. J. (2025). Graph neural networks for predicting metal–ligand coordination of transition metal complexes. Proceedings of the National Academy of Sciences, 122(41), e2415658122.
20. Jiao, Y., Zhao, B., Wang, A., & Shi, T. (2026). Construction and Empirical Study of a Modularized Teaching System for Art Courses Based on a Unified Training Pathway.
21. Yang, J. (2026). Stage‐Coupled Computational Framework for Stratified Accessibility and Equity Analysis in Community‐Based Elderly Care Services.
22. Bozal-Ginesta, C., Pablo-García, S., Choi, C., Tarancón, A., & Aspuru-Guzik, A. (2025). Developing machine learning for heterogeneous catalysis with experimental and computational data. Nature Reviews Chemistry, 9(9), 601-616.
23. Wu, J., Wu, D., Zhang, J., & Peng, Y. (2026). Generative AI Feedback in Junior High School Artistic Creation Evaluation. Available at SSRN 7244838.
24. Azancot, L., Tarifa, P., Cazaña, F., Romeo, E., & Monzón, A. (2026). Citrate-mediated structure and enthalpy-entropy trade-off in Ni-CeO2 catalysts for low-temperature CO2 methanation. Chemical Engineering Journal, 546, 179789.