GASCAP: Accelerating Adsorption Evaluation Using Graph Voronoi Diagram and Machine Learning Method

Abstract

Adsorption on a solid surface is a significant chemical process in the fields of gas sensors, solid catalysts, hydrogen storage materials, and ion batteries. Here, we develop a high-throughput computing package, termed as gas sensors and catalysts automatically screening package (GASCAP), to accelerate the evaluation of adsorption on solid surfaces using integrated computational materials engineering. The aims of GASCAP are to detect unequal adsorption sites, construct coadsorption structures, analyze adsorption energies, calculate work functions, and clarify charge interaction in high-throughput ways. The regulation of CO adsorption on the Pt (111) surface is used as a benchmark to demonstrate the effectiveness of GASCAP. Additionally, the GASCAP is interfaced with the machine learning interatomic potentials (MILP), to accelerate the adsorption energy computations. The calculated results reveal that the MILP can effectively accelerate the adsorption energy screening at 220 times when the calculation accuracy is reliable. To expand the application, a database is built with 5914 adsorbates and substrates. Considering the fast development of high-throughput calculations, the GASCAP will be a promising simulation platform for the future development in solid surface science.

Keywords

adsorption evaluation / high-throughput computation / integrated computational materials engineering / machine learning interatomic potentials

References

[1] Q. M. Bing, W. Liu, W. C. Yi, and J. Y. Liu, “Ni Anchored CN Monolayers as Low-Cost and Efficient Catalysts for Hydrogen Production From Formic Acid,” Journal of Power Sources 413 (2019): 399–407, https://doi.org/10.1016/j.jpowsour.2018.12.063.

[2] W. C. Yi, X. Chen, Z. X. Wang, Y. C. Ding, B. C. Yang, and X. B. Liu, “A Novel Two-Dimensional δ-InP₃ Monolayer With High Stability, Tunable Bandgap, High Carrier Mobility, and Gas Sensing of NO₂,” Journal of Materials Chemistry C: Materials for Optical and Electronic Devices 7, no. 24 (2019): 7352–7359, https://doi.org/10.1039/c9tc02030f.

[3] X. Y. Song, Y. H. Li, M. Yin, et al., “Two-Orders-of-Magnitude Enhancement of SERS Activity via a Simple Surface Engineering of Quasi-Metal Single-Crystal Frameworks,” Nano Letters 37 (2024): 11683–11689, https://doi.org/10.1021/acs.nanolett.4c03309.

[4] T. Yang, X. G. Jiang, W. C. Yi, X. M. Cheng, and T. X. Cheng, “Enhanced Fast Response to Hg⁰ by Adsorption-Induced Electronic Structure Evolution of TiC Nanosheet,” Applied Surface Science 544 (2021): 148925, https://doi.org/10.1016/j.apsusc.2021.148925.

[5] X. Y. Cai, W. C. Yi, J. Chen, et al., “A Novel 2D Porous CN Framework as a Promising Anode Material With Ultra-High Specific Capacity for Lithium-Ion Batteries,” Journal of Materials Chemistry A 10, no. 12 (2022): 6551–6559, https://doi.org/10.1039/d1ta10877h.

[6] X. G. Jiang, G. H. Zhang, W. C. Yi, T. Yang, and X. B. Liu, “Penta-BeP₂ Monolayer: A Superior Sensor for Detecting Toxic Gases in the Air With Excellent Sensitivity, Selectivity, and Reversibility,” ACS Applied Materials and Interfaces 14, no. 30 (2022): 35229–35236, https://doi.org/10.1021/acsami.2c07482.

[7] H. Y. Du, W. Yang, W. C. Yi, Y. H. Sun, N. S. Yu, and J. Wang, “Oxygen-Plasma-Assisted Enhanced Acetone-Sensing Properties of ZnO Nanofibers by Electrospinning,” ACS Applied Materials and Interfaces 12, no. 20 (2020): 23084–23093, https://doi.org/10.1021/acsami.0c03498.

[8] W. J. Li, Y. P. Zhang, Y. H. Wang, et al., “Graphdiyne Facilitates Photocatalytic CO₂ Hydrogenation Into C²⁺ Hydrocarbons,” Applied Catalysis B: Environmental 340 (2024): 123267, https://doi.org/10.1016/j.apcatb.2023.123267.

[9] J. Klimeš, D. R. Bowler, and A. Michaelides, “Van der Waals Density Functionals Applied to Solids,” Physical Review B: Condensed Matter 83, no. 19 (2011): 195131, https://doi.org/10.1103/physrevb.83.195131.

[10] H. Y. Du, Z. R. Zhang, X. G. Jiang, et al., “Enhancement of NO₂ Gas Sensing Properties of Polypyrrole by Polarization Doping With DBS: Experimental and DFT Studies,” ACS Applied Materials and Interfaces 15, no. 45 (2023): 52961–52970, https://doi.org/10.1021/acsami.3c12154.

[11] C. Zhu, J. P. Cao, Z. Yang, et al., “Study on Hydrodeoxygenation Mechanism of Anisole Over Ni (111) by First-Principles Calculation,” Molecular Catalysis 523 (2022): 111402, https://doi.org/10.1016/j.mcat.2021.111402.

[12] C. Zhan, G. Wang, X. G. Zhang, et al., “Single-Molecule Measurement of Adsorption Free Energy at the Solid–Liquid Interface,” Angewandte Chemie International Edition 58, no. 41 (2019): 14534–14538, https://doi.org/10.1002/anie.201907966.

[13] D. W. Hatchett, R. H. Uibel, K. J. Stevenson, J. M. Harris, and H. S. White, “Electrochemical Measurement of the Free Energy of Adsorption of n-Alkanethiolates at Ag(111),” Journal of the American Chemical Society 120, no. 5 (1998): 1062–1069, https://doi.org/10.1021/ja972617v.

[14] H. Xiong, Q. Sun, K. Chen, et al., “Correlating the Experimentally Determined CO Adsorption Enthalpy With the Electrochemical CO Reduction Performance on Cu Surfaces,” Angewandte Chemie International Edition 62, no. 10 (2023): e202218447, https://doi.org/10.1002/ange.202218447.

[15] Z. X. Wang, J. Zhang, and H. Y. Du, “Achieving the Sensing Property of Hg⁰ Molecules on Black Phosphorene Nanosheets Using Anisotropy as a Response Signal,” ACS Applied Nano Materials 8, no. 16 (2025): 8417–8423, https://doi.org/10.1021/acsanm.5c01065.

[16] L. Kou, T. Frauenheim, and C. Chen, “Phosphorene as a Superior Gas Sensor: Selective Adsorption and Distinct I-V Response,” Journal of Physical Chemistry Letters 5, no. 15 (2014): 2675–2681, https://doi.org/10.1021/jz501188k.

[17] H. Sun and J. Y. Liu, “A Pulsed Tandem Electrocatalysis Strategy for CO₂ Reduction,” Journal of the American Chemical Society 147, no. 17 (2025): 14388–14400, https://doi.org/10.1021/jacs.5c00633.

[18] J. R. Boes, O. Mamun, K. Winther, and T. Bligaard, “Graph Theory Approach to High-Throughput Surface Adsorption Structure Generation,” Journal of Physical Chemistry A 123, no. 11 (2019): 2281–2285, https://doi.org/10.1021/acs.jpca.9b00311.

[19] A. H. Larsen, J. J. Mortensen, J. Blomqvist, et al., “The Atomic Simulation Environment—A Python Library for Working With Atoms,” Journal of Physics: Condensed Matter 29, no. 27 (2017): 273002, https://doi.org/10.1088/1361-648X/aa680e.

[20] J. H. Montoya and K. A. Persson, “A High-Throughput Framework for Determining Adsorption Energies on Solid Surfaces,” Npj Computational Materials 3, no. 1 (2017): 14, https://doi.org/10.1038/s41524-017-0017-z.

[21] D. P. Kovács, I. Batatia, E. S. Arany, and G. Csányi, “Evaluation of the MACE Force Field Architecture: From Medicinal Chemistry to Materials Science,” Journal of Chemical Physics 159, no. 4 (2023): 044118, https://doi.org/10.1063/5.0155322.

[22] B. Deng, P. Zhong, K. Jun, et al., “CHGNet as a Pretrained Universal Neural Network Potential for Charge-Informed Atomistic Modelling,” Nature Machine Intelligence 5, no. 9 (2023): 1031–1041, https://doi.org/10.1038/s42256-023-00716-3.

[23] Y. Park, J. Kim, S. Hwang, and S. Han, “Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations,” Journal of Chemical Theory and Computation 20, no. 11 (2024): 4857–4868, https://doi.org/10.1021/acs.jctc.4c00190.

[24] J. Gasteiger, M. Shuaibi, A. Sriram, et al., “GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets,” arXiv 2204 (2022): 02782, https://doi.org/10.48550/arXiv.2204.02782.

[25] W. Xu, K. Reuter, and M. Andersen, “Predicting Binding Motifs of Complex Adsorbates Using Machine Learning With a Physics-Inspired Graph Representation,” Nature Computational Science 2, no. 7 (2022): 443–450, https://doi.org/10.1038/s43588-022-00280-7.

[26] T. Y. Zhang and X. J. Liu, “Informatics Is Fueling New Materials Discovery,” Journal of Materials Informatics 1, no. 1 (2021): 1, https://doi.org/10.20517/jmi.2021.09.

[27] W. Y. Wang, J. Yin, Z. Chai, et al., “Big Data-Assisted Digital Twins for the Smart Design and Manufacturing of Advanced Materials: From Atoms to Products,” Journal of Materials Informatics 2, no. 1 (2022): 1–27, https://doi.org/10.20517/jmi.2021.11.

[28] G. Kresse and J. Furthmüller, “Efficiency of Ab-Initio Total Energy Calculations for Metals and Semiconductors Using a Plane-Wave Basis Set,” Computational Materials Science 6, no. 1 (1996): 15–50, https://doi.org/10.1016/0927-0256(96)00008-0.

[29] G. Kresse and J. Furthmüller, “Efficient Iterative Schemes Forab Initiototal-Energy Calculations Using a Plane-Wave Basis Set,” Physical Review B: Condensed Matter 54, no. 16 (1996): 11169–11186, https://doi.org/10.1103/physrevb.54.11169.

[30] H. J. Monkhorst and J. D. Pack, “Special Points for Brillouin-Zone Integrations,” Physical Review B: Condensed Matter 13, no. 12 (1976): 5188–5192, https://doi.org/10.1103/physrevb.13.5188.

[31] J. P. Perdew, K. Burke, and M. Ernzerhof, “Generalized Gradient Approximation Made Simple,” Physical Review Letters 77, no. 18 (1996): 3865–3868, https://doi.org/10.1103/physrevlett.77.3865.

[32] G. Kresse and D. Joubert, “From Ultrasoft Pseudopotentials to the Projector Augmented-Wave Method,” Physical Review B: Condensed Matter 59, no. 3 (1999): 1758–1775, https://doi.org/10.1103/physrevb.59.1758.

[33] H. Yu, M. Giantomassi, G. Materzanini, J. Wang, and G. M. Rignanese, “Systematic Assessment of Various Universal Machine-Learning Interatomic Potentials,” Materials Genome Engineering Advances 2, no. 3 (2024): e58, https://doi.org/10.1002/mgea.58.

[34] B. Focassio, M. F. Lp, and G. R. Schleder, “Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces,” ACS Applied Materials and Interfaces 17, no. 9 (2025): 13111–13121, https://doi.org/10.1021/acsami.4c03815.

[35] D. P. Kovacs, J. H. Moore, N. J. Browning, et al., “MACE-OFF: Short-Range Transferable Machine Learning Force Fields for Organic Molecules,” Journal of the American Chemical Society 147, no. 21 (2025): 17598–17611, https://doi.org/10.1021/jacs.4c07099.

[36] D. Marx and M. Pilipczuk, “Optimal Parameterized Algorithms for Planar Facility Location Problems Using Voronoi Diagrams,” ACM Transactions on Algorithms 18, no. 2 (2022): 1–64, https://doi.org/10.1145/3483425.

[37] K. Nakada and A. Ishii, “Migration of Adatom Adsorption on Graphene Using DFT Calculation,” Solid State Communications 151, no. 1 (2011): 13–16, https://doi.org/10.1016/j.ssc.2010.10.036.

[38] V. V. Kulish, O. I. Malyi, C. Persson, and P. Wu, “Adsorption of Metal Adatoms on Single-Layer Phosphorene,” Physical Chemistry Chemical Physics 17, no. 2 (2015): 992–1000, https://doi.org/10.1039/c4cp03890h.

[39] T. Hu and J. Hong, “First-Principles Study of Metal Adatom Adsorption on Black Phosphorene,” Journal of Physical Chemistry C 119, no. 15 (2015): 8199–8207, https://doi.org/10.1021/acs.jpcc.5b01300.

[40] S. Gautier, S. N. Steinmann, C. Michel, P. Fleurat-Lessard, and P. Sautet, “Molecular Adsorption at Pt(111). How Accurate Are DFT Functionals?,” Physical Chemistry Chemical Physics 17, no. 43 (2015): 28921–28930, https://doi.org/10.1039/c5cp04534g.

[41] W. T. Cahyanto, A. A. B. Padama, M. C. S. Escaño, and H. Kasai, “Preferential Sites for Adsorption of Methanol and Methoxy on Pt and Pt-Alloy Surfaces,” Physica Scripta 85, no. 1 (2012): 015605, https://doi.org/10.1088/0031-8949/85/01/015605.

[42] E. M. Karp, T. L. Silbaugh, M. C. Crowe, and C. T. Campbell, “Energetics of Adsorbed Methanol and Methoxy on Pt(111) by Microcalorimetry,” Journal of the American Chemical Society 134, no. 50 (2012): 20388–20395, https://doi.org/10.1021/ja307465u.

[43] J. Greeley and M. Mavrikakis, “Competitive Paths for Methanol Decomposition on Pt(111),” Journal of the American Chemical Society 126, no. 12 (2004): 3910–3919, https://doi.org/10.1021/ja037700z.

[44] B. Hammer and J. K. Nørskov, “Electronic Factors Determining the Reactivity of Metal Surfaces,” Surface Science 343, no. 3 (1995): 211–220, https://doi.org/10.1016/0039-6028(96)80007-0.

[45] E. Bosoni, L. Beal, M. Bercx, et al., “How to Verify the Precision of Density-Functional-Theory Implementations via Reproducible and Universal Workflows,” Nature Reviews Physics 6, no. 1 (2023): 45–58, https://doi.org/10.1038/s42254-023-00655-3.

[46] L. Cao, “Recent Advances in the Application of Machine-Learning Algorithms to Predict Adsorption Energies,” Trends in Chemistry 4, no. 4 (2022): 347–360, https://doi.org/10.1016/j.trechm.2022.01.012.

[47] Y. Zhou and X. Zu, “Mn₂C Sheet as an Electrode Material for Lithium-Ion Battery: A First-Principles Prediction,” Electrochimica Acta 235 (2017): 167–174, https://doi.org/10.1016/j.electacta.2017.03.111.

[48] S. J. Ray, “First-Principles Study of MoS₂, Phosphorene and Graphene Based Single Electron Transistor for Gas Sensing Applications,” Sensors and Actuators B: Chemical 222 (2016): 492–498, https://doi.org/10.1016/j.snb.2015.08.039.

[49] J. Chen, S. Lin, M. Xu, et al., “Metal-Decoration-Free Li₃C₂ Monolayer With Heptacoordinate Carbons as a Promising Hydrogen Storage Medium,” ACS Materials Letters 4, no. 8 (2022): 1402–1410, https://doi.org/10.1021/acsmaterialslett.2c00254.

[50] W. Pei, W. Zhang, X. Yu, et al., “ZhaoJ. Computational Design of Spatially Confined Triatomic Catalysts for Nitrogen Reduction Reaction,” Journal of Materials Informatics 3, no. 4 (2023): 26, http://dx.doi.org/10.20517/jmi.2023.35.

[51] X. Jin, L. Y. Huai, H. Wen, W. C. Yi, and J. Y. Liu, “Reduction of NO With CO on the Co₃O₄(110)-B and CoO(110) Surfaces: A First-Principles Study,” Journal of Physical Chemistry C 123, no. 3 (2018): 1770–1778, https://doi.org/10.1021/acs.jpcc.8b09345.

[52] X. Ye, S. Ma, X. Jiang, Z. Yang, W. Jiang, and H. Wang, “The Adsorption of Acidic Gaseous Pollutants on Metal and Nonmetallic Surface Studied by First-Principles Calculation: A Review,” Chinese Chemical Letters 30, no. 12 (2019): 2123–2131, https://doi.org/10.1016/j.cclet.2019.09.043.

[53] M. Calatayud, A. Markovits, M. Menetrey, B. Mguig, and C. Minot, “Adsorption on Perfect and Reduced Surfaces of Metal Oxides,” Catalysis Today 85, no. 2–4 (2003): 125–143, https://doi.org/10.1016/s0920-5861(03)00381-x.

[54] Z. Fang, J. Wang, X. Yang, et al., “Adsorption of Arginine, Glycine and Aspartic Acid on Mg and Mg-Based Alloy Surfaces: A First-Principles Study,” Applied Surface Science 409 (2017): 149–155, https://doi.org/10.1016/j.apsusc.2017.02.241.

[55] Z. K. Han, D. Sarker, R. Ouyang, A. Mazheika, Y. Gao, and S. V. Levchenko, “Single-Atom Alloy Catalysts Designed by First-Principles Calculations and Artificial Intelligence,” Nature Communications 12, no. 1 (2021): 1833, https://doi.org/10.1038/s41467-021-22048-9.

[56] J. Hulva, M. Meier, R. Bliem, et al., “Unraveling CO Adsorption on Model Single-Atom Catalysts,” Science 371, no. 6527 (2021): 375–379, https://doi.org/10.1126/science.abe5757.

[57] N. Salami, “First-Principles Realistic Prediction of Gas Adsorption on Two-Dimensional Vanadium Carbide (MXene),” Applied Surface Science 581 (2022): 152105, https://doi.org/10.1016/j.apsusc.2021.152105.

RIGHTS & PERMISSIONS

2026 The Author(s). Materials Genome Engineering Advances published by Wiley-VCH GmbH on behalf of University of Science and Technology Beijing.