Author(s)

Emma Bucher, Christopher Rau, Quan Phuong^*

Affiliation(s)

School of Environmental and Life Sciences, The University of Newcastle, Australia.

Corresponding Author

Quan Phuong

ABSTRACT

The escalating levels of carbon dioxide (CO2) in the atmosphere, primarily due to human activities, pose significant challenges to global climate stability. CO2 hydrogenation emerges as a promising technology to mitigate these emissions by converting CO2 into valuable hydrocarbons and fuels, thus providing a sustainable energy pathway. Catalysts are essential for enhancing the efficiency and selectivity of this process; however, the discovery of effective catalysts is complicated by the vast array of potential materials and the intricate interactions that influence catalytic performance. Traditional methods of catalyst screening are often laborious and resource-intensive, necessitating innovative approaches to expedite the discovery process. This paper explores the integration of machine learning (ML) techniques into high-throughput screening (HTS) methodologies to facilitate the rapid evaluation of thousands of catalyst candidates for CO2 hydrogenation. By leveraging ML algorithms, we can analyze extensive datasets, identify performance patterns, and prioritize promising candidates for experimental validation. The findings demonstrate that ML-driven HTS not only accelerates catalyst discovery but also optimizes resource utilization, paving the way for more efficient solutions to combat CO2 emissions.

KEYWORDS

Machine learning; High-throughput screening; CO2 hydrogenation

CITE THIS PAPER

Emma Bucher, Christopher Rau, Quan Phuong. Machine learning-driven high-throughput screening of catalyst candidates for CO2 hydrogenation. Academic Journal of Earth Sciences. 2024, 2(2): 34-41. DOI: 10.61784/ajes3002.

REFERENCES

[1] Zhang Y, Xu Z, Wang T, et al. Reinforcement learning-enabled autonomous optimization for CO2 hydrogenation. Nat Commun, 2020, 11(1): 5812.

[2] Tran K, Ulissi ZW. Active learning across intermetallics to guide discovery of electrocatalysts for CO2 reduction and H2 evolution. Nat Catal, 2018, 1(9): 696-703.

[3] Gao W, Chen Y, Li Y, et al. Automated catalyst design for CO2 electroreduction. Nature, 2022, 610(7931): 287-293.

[4] Sun T, Yang J, Li J, et al. Enhancing Auto Insurance Risk Evaluation with Transformer and SHAP. IEEE Access, 2024.

[5] Lin Y, Fu H, Zhong Q, et al. The influencing mechanism of the communities’ built environment on residents’ subjective well-being: A case study of Beijing. Land, 2024, 13(6):793.

[6] Li J, Fan L, Wang X, et al. Product Demand Prediction with Spatial Graph Neural Networks. Applied Sciences, 2024, 14(16): 6989.

[7] Liu M, Ma Z, Li J, et al. Deep-Learning-Based Pre-training and Refined Tuning for Web Summarization Software. IEEE Access, 2024.

[8] Chen X, Liu M, Niu Y, et al. Deep-Learning-Based Lithium Battery Defect Detection via Cross-Domain Generalization. IEEE Access, 2024.

[9] Wang X, Wu YC, Ji X, et al. Algorithmic discrimination: examining its types and regulatory measures with emphasis on US legal practices. Frontiers in Artificial Intelligence, 2024, 7: 1320277.

[10] Wang X, Wu YC, Ma Z. Blockchain in the courtroom: exploring its evidentiary significance and procedural implications in US judicial processes. Frontiers in Blockchain, 2024, 7:1306058.

[11] Ma Z, Chen X, Sun T, et al. Blockchain-Based Zero-Trust Supply Chain Security Integrated with Deep Reinforcement Learning for Inventory Optimization. Future Internet, 2024, 16(5): 163.

[12] Wang X, Wu YC, Zhou M, et al. Beyond surveillance: privacy, ethics, and regulations in face recognition technology. Frontiers in big data, 2024, 7: 1337465.

[13] Wang X, Wu YC. Balancing innovation and Regulation in the age of generative artificial intelligence. Journal of Information Policy, 2024, 14.

[14] Zuo Z, Niu Y, Li J, et al. Machine Learning for Advanced Emission Monitoring and Reduction Strategies in Fossil Fuel Power Plants. Applied Sciences, 2024, 14(18): 8442.

[15] Toyao T, Maeno Z, Takakusagi S, et al. Machine Learning for Catalysis Informatics: Recent Applications and Prospects. ACS Catal, 2020, 10(3): 2260-2297.

[16] Zhong M, Tran K, Min Y, et al. Accelerated discovery of CO2 electrocatalysts using active machine learning. Nature, 2020, 581(7807): 178-183.

[17] Schlexer Lamoureux P, Winther KT, Garrido Torres JA, et al. Machine Learning for Computational Heterogeneous Catalysis. ChemCatChem, 2019, 11(16): 3581-3601.

[18] Li Z, Wang S, Chin WS, et al. Machine learning-guided discovery and optimization of catalysts for CO2 electroreduction. Nat Catal, 2022, 5(10): 858-868.

[19] Gu GH, Noh J, Kim S, et al. Practical deep-learning representation for fast heterogeneous catalyst screening. NPJ Comput Mater, 2019, 5(1): 47.

[20] Jia X, Lynch A, Huang Y, et al. Anthropogenic CO2 reduction: from materials design to flow reactors. Mater Today, 2019, 24: 15-47.

[21] Medford AJ, Kunz MR, Ewing SM, et al. Extracting knowledge from data through catalysis informatics. ACS Catal, 2018, 8(8): 7403-7429.

[22] Xie T, Grossman JC. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. Phys Rev Lett, 2018, 120(14): 145301.

[23] Grajciar L, Heard CJ, Bondarenko AA, et al. Towards operando computational modeling in heterogeneous catalysis. Chem Soc Rev, 2018, 47(22): 8307-8348.

[24] Ulissi ZW, Tang MT, Xiao J, et al. Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO2 Reduction. ACS Catal, 2017, 7(10): 6600-6608.

[25] Boes JR, Mamun O, Winther K, et al. Graph Theory Approach to High-Throughput Surface Adsorption Structure Generation. J Phys Chem A, 2019, 123(11): 2281-2285.

[26] Back S, Tran K, Ulissi ZW. Toward a Design of Active Oxygen Evolution Catalysts: Insights from Automated Density Functional Theory Calculations and Machine Learning. ACS Catal, 2019, 9(9): 7651-7659.

[27] Jinnouchi R, Asahi R. Predicting Catalytic Activity of Nanoparticles by a DFT-Aided Machine-Learning Algorithm. J Phys Chem Lett, 2017, 8(17): 4279-4283.

[28] Li Z, Ma X, Xin H. Feature engineering of machine-learning chemisorption models for catalyst design. Catal Today, 2017, 280: 232-238.

[29] Gu GH, Choi C, Lee Y, et al. Progress in computational and machine-learning methods for heterogeneous small-molecule activation. Nat Rev Mater, 2020, 5(8): 605-621.

[30] Gusarov S, Stoyanov SR, Siahrostami S, et al. Deep Learning for Molecular Design and Discovery: From Chemical Reactions to Materials. ACS Cent Sci, 2021, 7(6): 902-915.

[31] Gasper R, Shi H, Ramasubramaniam A. Adsorption of CO2 on Pt-Cu Nanoalloys: Density Functional Theory and Machine Learning Approaches. J Phys Chem C, 2017, 121(10): 5612-5619.

[32] Kitchin JR. Machine learning in catalysis. Nat Catal, 2018, 1(4): 230-232.

[33] Wan Y, Zhang Z, Xu X, et al. Engineering active sites of polyoxometalate-based metal-organic frameworks for boosting CO2 electroreduction. Nat Commun, 2021, 12(1): 2870.

[34] Gómez-Bombarelli R, Wei JN, Duvenaud D, et al. Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules. ACS Cent Sci, 2018, 4(2): 268-276.

[35] Andersen M, Levchenko SV, Scheffler M, et al. Beyond Scaling Relations for the Description of Catalytic Materials. ACS Catal, 2019, 9(4): 2752-2759.

[36] Rosen AS, Iyer SM, Ray D, et al. Machine learning the quantum-chemical properties of metal–organic frameworks for accelerated materials discovery. Matter, 2021, 4(5): 1578-1597.

[37] Artrith N, Butler KT, Coudert FX, et al. Best practices in machine learning for chemistry. Nat Chem, 2021, 13(6): 505-508.

[38] Schleder GR, Padilha ACM, Acosta CM, et al. From DFT to machine learning: recent approaches to materials science–a review. J Phys Mater, 2019, 2(3): 032001.

[39] Melander M, Kuisma MJ, Christensen TE, et al. Grand-canonical approach to density functional theory of electrocatalytic systems: Thermodynamics of solid-liquid interfaces at constant ion and electrode potentials. J Chem Phys, 2019, 150(4): 041706.

[40] Janet JP, Kulik HJ. Machine Learning in Inorganic Chemistry. J Phys Chem A, 2021, 125(39): 8561-8568.

[41] Asif M, Yao C, Zuo Z, et al. Machine learning-driven catalyst design, synthesis and performance prediction for CO2 hydrogenation. Journal of Industrial and Engineering Chemistry, 2024.

[42] Xiong Z, Wang Y, Cheng T, et al. Revealing the active phase of copper during the electroreduction of CO2 in aqueous electrolyte by correlating in situ X-ray spectroscopy and in situ electron microscopy. Nat Catal, 2020, 3(8): 636-642.

[43] Palkovits R, Palkovits S. Efficient catalyst discovery for sustainable chemical synthesis via high-throughput experimentation and machine learning. Nat Commun, 2022, 13(1): 3675.

[44] Chen C, Zhu X, Wen X, et al. Coupling N2 and CO2 in H2O to synthesize urea under ambient conditions. Nat Chem, 2020,12(8): 717-724.

[45] Norskov JK, Bligaard T, Rossmeisl J, et al. Towards the computational design of solid catalysts. Nat Chem, 2009, 1(1): 37-46.

[46] Wang Y, Liu J, Wang Y, et al. Synergy of electron-phonon coupling and lattice distortion in crystal structure-dependent CO2 activation. Nat Commun, 2021, 12(1): 1013.

[47] Tao H, Stach EA, Goodman ED, et al. Accelerating Catalysts Discovery through Machine Learning and High-Throughput Experimentation. ACS Catal, 2022, 12(5): 2962-2968.