基于图神经网络的高性能二氧化碳还原高熵合金催化剂预测

doi:10.1016/S1872-2067(24)60264-0

摘要/Abstract

摘要：

本文针对铜基高熵合金(HEA)在CO₂还原反应中的催化性能, 探讨了其可调组成和表面结构对催化活性的提升作用. 由于HEA材料的表面复杂性及元素偏析倾向, 导致体相与表面组成不一致, 这为通过密度泛函理论进行直接研究带来了挑战. 本研究旨在克服这些困难, 探索如何通过模拟和机器学习方法优化HEA催化剂的设计.
为了模拟表面元素的分离行为, 本文采用了蒙特卡罗模拟与分子动力学相结合的方式, 涵盖了包括Cu, Ag, Au, Pt, Pd和Al在内的多个元素. 通过这一方法, 揭示了表面偏析倾向的规律: Ag > Au > Al > Cu > Pd > Pt. 为了解析表面位点特征与多齿CO₂还原中间体自由能之间的关系, 设计了一个基于图神经网络的模型, 其中吸附物被转化为位于其质心的伪原子. 该模型在C₂中间体自由能预测中取得了0.08-0.15 eV的平均绝对误差, 能够精准量化表面位点活性. 结果表明, 增加Cu, Ag和Al的浓度显著提高了CO和C₂的生成活性, 而Au, Pd和Pt则表现出抑制作用. 对于产氢(HER)反应, Al和Au是关键调节因子: 提高Au含量或降低Al含量有助于提升HER活性; 而Pd含量的增加或Au含量的减少则促进了甲酸的生成. 此外, 通过筛选稳定的组成空间, 研究还预测了比纯Cu催化剂更具催化活性的HEA体相组成, 适用于CO, HCOOH和C₂产品的生成.
综上, HEA通过其可调的组成和表面结构能够有效促进CO₂还原反应, 尽管表面组成和元素分离带来了挑战, 蒙特卡罗模拟与图神经网络的结合提供了一个高效的催化剂设计框架. 本文不仅为HEA催化剂的理性设计提供了理论依据, 还为高通量筛选具有优异催化性能的HEA电催化剂奠定了基础.

关键词: 密度泛函理论, 机器学习, CO₂还原, 高熵合金, 图神经网络

Abstract:

High-entropy alloy (HEA) offer tunable composition and surface structures, enabling the creation of novel active sites that enhance catalytic performance in renewable energy application. However, the inherent surface complexity and tendency for elemental segregation, which results in discrepancies between bulk and surface compositions, pose challenges for direct investigation via density functional theory. To address this, Monte Carlo simulations combined with molecular dynamics were employed to model surface segregation across a broad range of elements, including Cu, Ag, Au, Pt, Pd, and Al. The analysis revealed a trend in surface segregation propensity following the order Ag > Au > Al > Cu > Pd > Pt. To capture the correlation between surface site characteristics and the free energy of multi-dentate CO₂ reduction intermediates, a graph neural network was designed, where adsorbates were transformed into pseudo-atoms at their centers of mass. This model achieved mean absolute errors of 0.08-0.15 eV for the free energies of C₂ intermediates, enabling precise site activity quantification. Results indicated that increasing the concentration of Cu, Ag, and Al significantly boosts activity for CO and C₂ formation, whereas Au, Pd, and Pt exhibit negative effects. By screening stable composition space, promising HEA bulk compositions for CO, HCOOH, and C₂ products were predicted, offering superior catalytic activity compared to pure Cu catalysts.

Key words: Density functional theory, Machine learning, CO₂ reduction, High entropy alloys, Graph neural network

焦自浩, 张成翼, 刘亚, 郭烈锦, 王子运. 基于图神经网络的高性能二氧化碳还原高熵合金催化剂预测[J]. 催化学报, 2025, 71: 197-207.

Zihao Jiao, Chengyi Zhang, Ya Liu, Liejin Guo, Ziyun Wang. Graph neural network-driven prediction of high-performance CO₂ reduction catalysts based on Cu-based high-entropy alloys[J]. Chinese Journal of Catalysis, 2025, 71: 197-207.

×
扫码分享

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.cjcatal.com/CN/10.1016/S1872-2067(24)60264-0

https://www.cjcatal.com/CN/Y2025/V71/I4/197

图/表 5

Fig. 1. Stability analysis of HEAs. (a) Elements incorporated within the compositional space of HEAs. (b) Schematic representation of stability and phase formation criteria. (c) Distribution of stability parameters Ω and δ across all possible compositions, with varying colors indicating different VEC values. (d) Correlation between the metal proportion in stable phases and the averaged mixing enthalpy ΔH.

Fig. 2. A comparison between surface and bulk ratios of various elements after the segregation process. (a) The relationship between the surface ratio and bulk ratio for Ag and Au. Each point represents a possible HEA composition for a given bulk ratio of the specified element. The black points indicate the specified element has the highest concentration on the surface for that composition, indicating its dominance in surface segregation. (b) The relationship between the surface ratio and bulk ratio for element pairs.

Fig. 3. The reaction pathway and dataset generation. (a) Reaction pathways and key intermediates of CO2 reduction and HER. (b) Sample structures from the HEA dataset. (c) Multi-atom intermediates are represented as single pseudo-atoms, encoded through one-hot encoding. (d) Neighbor search for each node in the GNN using a 6 ? cutoff radius.

Fig. 4. Overview of GNN model performance. (a) Workflow of the GNN model. (b) Comparison of model performance using COM and COP. (c) Model predictions on the validation set, where the x-axis represents DFT-calculated free energies and the y-axis shows GNN-predicted free energies. (d) Model predictions on the test set. (e) Average adsorption heights of different intermediates, with error bars representing the standard deviation of adsorption heights.

Fig. 5. (a) Quartile analysis of surface activity in HEAs based on bulk elemental composition. (b) Analysis of dominant potential limiting steps for various products in the AQ3 (high-activity) and AQ1 (low-activity) regions. (c) Composition analysis of the 1000 most active adsorption sites in terms of nearest neighboring atoms. (d) Heatmap of the surface average limiting potential across the compositional space of HEAs. The color scale represents the average limiting potential for the C2 product, with lower values indicating more favorable catalytic activity. Specific HEA compositions with particularly low limiting potentials are highlighted.

参考文献

[1]	S. Nitopi, E. Bertheussen, S. B. Scott, X. Liu, A. K. Engstfeld, S. Horch, B. Seger, I. E. L. Stephens, K. Chan, C. Hahn, J. K. Nørskov, T. F. Jaramillo, I. Chorkendorff, Chem. Rev., 2019, 119, 7610-7672.
[2]	Y. Hori, H. Wakebe, T. Tsukamoto, O. Koga, Electrochim. Acta, 1994, 39, 1833-1839.
[3]	A. Vasileff, C. Xu, Y. Jiao, Y. Zheng, S.-Z. Qiao, Chem, 2018, 4, 1809-1831.
[4]	C. Choi, S. Kwon, T. Cheng, M. Xu, P. Tieu, C. Lee, J. Cai, H. M. Lee, X. Pan, X. Duan, W. A. Goddard, Y. Huang, Nat. Catal., 2020, 3, 804-812.
[5]	Y. Lum, J. W. Ager, Nat. Catal., 2019, 2, 86-93.
[6]	S. Nellaiappan, N. K. Katiyar, R. Kumar, A. Parui, K. D. Malviya, K. G. Pradeep, A. K. Singh, S. Sharma, C. S. Tiwary, K. Biswas, ACS Catal., 2020, 10, 3658-3663.
[7]	T. Ahmad, S. Liu, M. Sajid, K. Li, M. Ali, L. Liu, W. Chen, Nano Res. Energy, 2022, 1, 9120021.
[8]	X. Wang, W. Guo, Y. Fu, J. Mater. Chem. A, 2021, 9, 663-701.
[9]	K. Li, W. Chen, Mater. Today Energy, 2021, 20, 100638.
[10]	S. Liu, Y. Wang, T. Jiang, S. Jin, M. Sajid, Z. Zhang, J. Xu, Y. Fan, X. Wang, J. Chen, Z. Liu, X. Zheng, K. Zhang, Q. Nian, Z. Zhu, Q. Peng, T. Ahmad, K. Li, W. Chen, ACS Nano, 2024, 18, 4229-4240.
[11]	Y. Chida, T. Tomimori, T. Ebata, N. Taguchi, T. Ioroi, K. Hayashi, N. Todoroki, T. Wadayama, Nat. Commun., 2023, 14, 4492.
[12]	S. Li, X. Tang, H. Jia, H. Li, G. Xie, X. Liu, X. Lin, H.-J. Qiu, J. Catal., 2020, 383, 164-171.
[13]	Y. Mei, Y. Feng, C. Zhang, Y. Zhang, Q. Qi, J. Hu, ACS Catal., 2022, 12, 10808-10817.
[14]	Z. W. Chen, J. Li, P. Ou, J. E. Huang, Z. Wen, L. Chen, X. Yao, G. Cai, C. C. Yang, C. V. Singh, Q. Jiang, Nat. Commun., 2024, 15, 359.
[15]	P. Xie, Y. Yao, Z. Huang, Z. Liu, J. Zhang, T. Li, G. Wang, R. Shahbazian-Yassar, L. Hu, C. Wang, Nat. Commun., 2019, 10, 4011.
[16]	J. K. Pedersen, T. A. A. Batchelor, A. Bagger, J. Rossmeisl, ACS Catal., 2020, 10, 2169-2176.
[17]	H. Huang, J. Zhao, H. Guo, B. Weng, H. Zhang, R. A. Saha, M. Zhang, F. Lai, Y. Zhou, R.-Z. Juan, P.-C. Chen, S. Wang, J. A. Steele, F. Zhong, T. Liu, J. Hofkens, Y.-M. Zheng, J. Long, M. B. J. Roeffaers, Adv. Mater., 2024, 36, 2313209.
[18]	Z. W. Chen, Z. Gariepy, L. Chen, X. Yao, A. Anand, S.-J. Liu, C. G. Tetsassi Feugmo, I. Tamblyn, C. V. Singh, ACS Catal., 2022, 12, 14864-14871.
[19]	M. Zhong, K. Tran, Y. Min, C. Wang, Z. Wang, C.-T. Dinh, P. De Luna, Z. Yu, A. S. Rasouli, P. Brodersen, S. Sun, O. Voznyy, C.-S. Tan, M. Askerka, F. Che, M. Liu, A. Seifitokaldani, Y. Pang, S.-C. Lo, A. Ip, Z. Ulissi, E. H. Sargent, Nature, 2020, 581, 178-183.
[20]	F. Calle-Vallejo, J. I. Martínez, J. M. García-Lastra, P. Sautet, D. Loffreda, Angew. Chem. Int. Ed., 2014, 53, 8316-8319.
[21]	X. Ma, H. Xin, Phys. Rev. Lett., 2017, 118, 036101.
[22]	S. Wang, N. Omidvar, E. Marx, H. Xin, ACS Comb. Sci., 2018, 20, 567-572.
[23]	F. Abild-Pedersen, J. Greeley, F. Studt, J. Rossmeisl, T. R. Munter, P. G. Moses, E. Skúlason, T. Bligaard, J. K. Nørskov, Phys. Rev. Lett., 2007, 99, 016105.
[24]	T. Bligaard, J. K. Nørskov, S. Dahl, J. Matthiesen, C. H. Christensen, J. Sehested, J. Catal., 2004, 224, 206-217.
[25]	J. K. Pedersen, T. A. A. Batchelor, D. Yan, L. E. J. Skjegstad, J. Rossmeisl, Curr. Opin. Electrochem., 2021, 26, 100651.
[26]	J. Chen, Y. Ji, Chin. J. Catal., 2022, 43, 2889-2897.
[27]	P. Wynblatt, R. C. Ku, Surf. Sci., 1977, 65, 511-531.
[28]	C. Dahale, S. G. Srinivasan, S. Mishra, S. Maiti, B. Rai, Mol. Syst. Des. Eng., 2022, 7, 878-888.
[29]	D. Chatain, P. Wynblatt, Comput. Mater. Sci., 2021. 187, 110101.
[30]	J.-W. Yeh, S.-K. Chen, S.-J. Lin, J.-Y. Gan, T.-S. Chin, T.-T. Shun, C.-H. Tsau, S.-Y. Chang, Adv. Eng. Mater., 2004, 6, 299-303.
[31]	Y. Zou, S. Maiti, W. Steurer, R. Spolenak, Acta Mater., 2014, 65, 85-97.
[32]	X. Yang, Y. Zhang, Mater. Chem. Phys., 2012, 132, 233-238.
[33]	A. Takeuchi, A. Inoue, Mater. Trans., 2005, 46, 2817-2829.
[34]	S. Guo, C. Ng, J. Lu, C. T. Liu, J. Appl. Phys., 2011, 109, 103505.
[35]	A. P. Thompson, H. M. Aktulga, R. Berger, D. S. Bolintineanu, W. M. Brown, P. S. Crozier, P. J. in ’t Veld, A. Kohlmeyer, S. G. Moore, T. D. Nguyen, R. Shan, M. J. Stevens, J. Tranchida, C. Trott, S. J. Plimpton, Comput. Phys. Commun., 2022, 271, 108171.
[36]	X. W. Zhou, R. A. Johnson, H. N. G. Wadley, Phys. Rev. B, 2004, 69, 144113.
[37]	X. Yang, J. Zhang, S. Sagar, T. Dube, B.-G. Kim, Y.-G. Jung, D.D. Koo, A. Jones, J. Zhang,, Mater. Chem. Phys., 2021, 263, 124341.
[38]	Q.-X. Pei, W. Li, Z. H. Aitken, P. Liu, Y.-W. Zhang, J. Mater. Sci., 2023, 58, 18105-18119.
[39]	W. K. Hastings, Biometrika, 1970, 57, 97-109.
[40]	A. H. Larsen, J. J. Mortensen, J. Blomqvist, I. E. Castelli, R. Christensen, M. Dułak, J. Friis, M. N. Groves, B. Hammer, C. Hargus, E. D. Hermes, P. C. Jennings, P. B. Jensen, J. Kermode, J. R. Kitchin, E. L. Kolsbjerg, J. Kubal, K. Kaasbjerg, S. Lysgaard, J. B. Maronsson, T. Maxson, T. Olsen, L. Pastewka, A. Peterson, C. Rostgaard, J. Schiøtz, O. Schütt, M. Strange, K. S. Thygesen, T. Vegge, L. Vilhelmsen, M. Walter, Z. Zeng, K. W. Jacobsen, J. Phys.: Condens. Matter, 2017, 29, 273002.
[41]	G. Kresse, J. Furthmüller, Comput. Mater. Sci., 1996, 6, 15-50.
[42]	G. Kresse, J. Furthmüller, Phys. Rev. B, 1996, 54, 11169-11186.
[43]	B. Hammer, L. B. Hansen, J. K. Nørskov, Phys. Rev. B, 1999, 59, 7413-7421.
[44]	S. P. Ong, W. D. Richards, A. Jain, G. Hautier, M. Kocher, S. Cholia, D. Gunter, V. L. Chevrier, K. A. Persson, G. Ceder, Comput. Mater. Sci., 2013, 68, 314-319.
[45]	Y.-L. Liao, B. Wood, A. Das, T. Smidt, 2024, arXiv:2306.12059. https://doi.org/10.48550/arXiv.2306.12059.
[46]	D. Cheng, G. Zhang, L. Li, X. Shi, W. Zhu, X. Yuan, L. Moskaleva, P. Zhang, Z.-J. Zhao, J. Gong, Sci. China Chem., 2024, DOI: 10.1007/s11426-024-2292-3.
[47]	H. Li, K. Shin, G. Henkelman, J. Chem. Phys., 2018, 149, 174705.
[48]	Z. Jiao, M. Song, W. Jing, Y. Liu, L. Guo, J. Phys. Chem. Lett., 2023, 14, 6009-6017.
[49]	D. C. Peacock, Appl. Surf. Sci., 1986, 27, 58-70.
[50]	Y. Yu, K. Sagisaka, D. Fujita, Surf. Sci., 2009, 603, 723-726.
[51]	V. S. Sundaram, P. Wynblatt, Surf. Sci., 1975, 52, 569-587.
[52]	E. Christoffersen, P. Stoltze, J. K. Nørskov, Surf. Sci., 2002, 505, 200-214.
[53]	F. Cheng, X. He, Z.-X. Chen, Y.-G. Huang, J. Alloys Compd., 2015, 648, 1090-1096.
[54]	T. K. Todorova, M. W. Schreiber, M. Fontecave, ACS Catal., 2020, 10, 1754-1768.
[55]	M. T. Tang, H. Peng, P. S. Lamoureux, M. Bajdich, F. Abild-Pedersen, Appl. Catal. B, 2020, 279, 119384.
[56]	J. Han, J. Cen, L. Wu, Z. Li, X. Kong, R. Jiao, Z. Yu, T. Xu, F. Wu, Z. Wang, H. Xu, Z. Wei, Y. Liu, Y. Rong, W. Huang, 2024, arXiv:2403.00485. https://doi.org/10.48550/arXiv.2403.00485
[57]	A. Duval, S. V. Mathis, C. K. Joshi, V. Schmidt, S. Miret, F. D. Malliaros, T. Cohen, P. Liò, Y. Bengio, M. Bronstein, 2024, arXiv:2312.07511. https://doi.org/10.48550/arXiv.2312.07511.
[58]	O. T. Unke, S. Chmiela, H. E. Sauceda, M. Gastegger, I. Poltavsky, K.T. Schütt, A. Tkatchenko, K.-R. Müller, Chem. Rev., 2021, 121, 10142-10186.
[59]	L. Chanussot, A. Das, S. Goyal, T. Lavril, M. Shuaibi, M. Riviere, K. Tran, J. Heras-Domingo, C. Ho, W. Hu, A. Palizhati, A. Sriram, B. Wood, J. Yoon, D. Parikh, C. L. Zitnick, Z. Ulissi, ACS Catal., 2021, 11, 6059-6072.
[60]	L. Chen, Y. Tian, X. Hu, S. Yao, Z. Lu, S. Chen, X. Zhang, Z. Zhou, Adv. Funct. Mater., 2022, 32, 2208418.
[61]	J. Li, J. Hu, M. Zhang, W. Gou, S. Zhang, Z. Chen, Y. Qu, Y. Ma, Nat. Commun., 2021, 12, 3502.
[62]	L. R. L. Ting, O. Piqué, S. Y. Lim, M. Tanhaei, F. Calle-Vallejo, B.S. Yeo, ACS Catal., 2020, 10, 4059-4069.
[63]	J. Chen, M. Jia, Y. Mao, P. Hu, H. Wang, ACS Catal., 2023, 13, 2937-2947.
[64]	Q. Zhou, H. Shou, S. Qiao, Y. Cao, P. Zhang, S. Wei, S. Chen, X. Wu, L. Song, J. Am. Chem. Soc., 2024, 146, 15167-15175.
[65]	S. Back, J. Yoon, N. Tian, W. Zhong, K. Tran, Z. W. Ulissi, J. Phys. Chem. Lett., 2019, 10, 4401-4408.
[66]	S.-H. Wang, H. S. Pillai, S. Wang, L. E. K. Achenie, H. Xin, Nat. Commun., 2021, 12, 5288.
[67]	L. Zhang, X. Zhang, C. Chen, J. Zhang, W. Tan, Z. Xu, Z. Zhong, L. Du, H. Song, S. Liao, Y. Zhu, Z. Zhou, Z. Cui, Angew. Chem. Int. Ed., 2024, 63, e202411123.
[68]	T. Xie, J. C. Grossman, Phys. Rev. Lett., 2018, 120, 145301.
[69]	J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, G. E. Dahl, Proce. Machine Learning Res., 2017, 70, 1263-1272.
[70]	J. Zhang, C. Wang, S. Huang, X. Xiang, Y. Xiong, B. Xu, S. Ma, H. Fu, J. Kai, X. Kang, S. Zhao, Joule, 2023, 7, 1832-1851.
[71]	J. K. Nørskov, F. Studt, F. Abild-Pedersen, T. Bligaard, Fundamental Concepts in Heterogeneous Catalysis, John Wiley & Sons, 2014.
[72]	J. K. Nørskov, J. Rossmeisl, A. Logadottir, L. Lindqvist, J. R. Kitchin, T. Bligaard, H. Jónsson, J. Phys. Chem. B, 2004, 108, 17886-17892.
[73]	C. Liu, J. Qian, Y. Ye, H. Zhou, C.-J. Sun, C. Sheehan, Z. Zhang, G. Wan, Y.-S. Liu, J. Guo, S. Li, H. Shin, S. Hwang, T. B. Gunnoe, W. A. Goddard, S. Zhang, Nat. Catal., 2021, 4, 36-45.
[74]	A. John, A. M. Verma, M. Shaneeth, A. G. Rajan, ChemCatChem, 2023, 15, e202300188.
[75]	H. Lei, W. Zhang, J. Yang, J. Phys. Chem. Lett., 2024, 15, 5643-5653.
[76]	H. Xiao, T. Cheng, W. A. I. Goddard, R. Sundararaman, J. Am. Chem. Soc., 2016, 138, 483-486.
[77]	H. Liu, J. Liu, B. Yang, ACS Catal., 2021, 11, 12336-12343.
[78]	L. Liu, Z. Xia, Z. Wang, Y. Chen, H. Xiao, Sci. China Chem., 2025, 68, 21-25.
[79]	Z. Wang, W. A. Goddard, H. Xiao, Nat. Commun., 2023, 14, 4228.
[80]	L. Liu, H. Xiao, J. Am. Chem. Soc., 2023, 145, 14267-14275.
[81]	Z. Wang, H. Xiao, J. Am. Chem. Soc., 2024, 146, 29540-29550.