Volume 3 Issue 2
June  2024
Turn off MathJax
Article Contents
Daniel Wines, Kamal Choudhary. Data-driven design of high pressure hydride superconductors using DFT and deep learning[J]. Materials Futures, 2024, 3(2): 025602. doi: 10.1088/2752-5724/ad4a94
Citation: Daniel Wines, Kamal Choudhary. Data-driven design of high pressure hydride superconductors using DFT and deep learning[J]. Materials Futures, 2024, 3(2): 025602. doi: 10.1088/2752-5724/ad4a94
Paper •
OPEN ACCESS

Data-driven design of high pressure hydride superconductors using DFT and deep learning

© 2024 The Author(s). Published by IOP Publishing Ltd on behalf of the Songshan Lake Materials Laboratory
Materials Futures, Volume 3, Number 2
  • Received Date: 2024-02-23
  • Accepted Date: 2024-05-12
  • Rev Recd Date: 2024-05-01
  • Publish Date: 2024-05-31
  • AbstractThe observation of superconductivity in hydride-based materials under ultrahigh pressures (for example, H3S and LaH10) has fueled the interest in a more data-driven approach to discovering new high-pressure hydride superconductors. In this work, we performed density functional theory (DFT) calculations to predict the critical temperature (Tc) of over 900 hydride materials under a pressure range of (0-500) GPa, where we found 122 dynamically stable structures with a Tc above MgB2 (39 K). To accelerate screening, we trained a graph neural network (GNN) model to predict Tc and demonstrated that a universal machine learned force-field can be used to relax hydride structures under arbitrary pressures, with significantly reduced cost. By combining DFT and GNNs, we can establish a more complete map of hydrides under pressure.
  • loading
  • [1]
    Bardeen J, Cooper L N, Schrieffer J R 1957 Microscopic theory of superconductivity Phys. Rev. 106 162-4 doi: 10.1103/PhysRev.106.162
    [2]
    Bardeen J, Cooper L N, Schrieffer J R 1957 Theory of superconductivity Phys. Rev. 108 1175-204 doi: 10.1103/PhysRev.108.1175
    [3]
    Nagamatsu J, Nakagawa N, Muranaka T, Zenitani Y, Akimitsu J 2001 Superconductivity at 39 K in magnesium diboride Nature 410 63-64 doi: 10.1038/35065039
    [4]
    Eremets M I, et al 2022 High-temperature superconductivity in hydrides: experimental evidence and details J. Supercond. Nov. Magn. 35 965-77 doi: 10.1007/s10948-022-06148-1
    [5]
    Zhang S, Zhang M, Liu H 2021 Superconductive hydrogen-rich compounds under high pressure Appl. Phys. A 127 684 doi: 10.1007/s00339-021-04802-4
    [6]
    Ashcroft N W 1968 Metallic hydrogen: a high-temperature superconductor? Phys. Rev. Lett. 21 1748-9 doi: 10.1103/PhysRevLett.21.1748
    [7]
    Ashcroft N W 2004 Hydrogen dominant metallic alloys: high temperature superconductors? Phys. Rev. Lett. 92 187002 doi: 10.1103/PhysRevLett.92.187002
    [8]
    Drozdov A P, Eremets M I, Troyan I A, Ksenofontov V, Shylin S I 2015 Conventional superconductivity at 203 kelvin at high pressures in the sulfur hydride system Nature 525 73-76 doi: 10.1038/nature14964
    [9]
    Drozdov A P, et al 2019 Superconductivity at 250 K in lanthanum hydride under high pressures Nature 569 528-31 doi: 10.1038/s41586-019-1201-8
    [10]
    Geballe Z M, Liu H, Mishra A K, Ahart M, Somayazulu M, Meng Y, Baldini M, Hemley R J 2018 Synthesis and stability of lanthanum superhydrides Angew. Chem., Int. Ed. 57 688-92 doi: 10.1002/anie.201709970
    [11]
    Somayazulu M, Ahart M, Mishra A K, Geballe Z M, Baldini M, Meng Y, Struzhkin V V, Hemley R J 2019 Evidence for superconductivity above 260 K in lanthanum superhydride at megabar pressures Phys. Rev. Lett. 122 027001 doi: 10.1103/PhysRevLett.122.027001
    [12]
    Liu H, Naumov I I, Hoffmann R, Ashcroft N W, Hemley R J 2017 Potential high-TC superconducting lanthanum and yttrium hydrides at high pressure Proc. Natl Acad. Sci. 114 6990-5 doi: 10.1073/pnas.1704505114
    [13]
    Liu H, Naumov I I, Geballe Z M, Somayazulu M, Tse J S, Hemley R J 2018 Dynamics and superconductivity in compressed lanthanum superhydride Phys. Rev. B 98 100102 doi: 10.1103/PhysRevB.98.100102
    [14]
    Kruglov I A, et al 2020 Superconductivity of LaH10 and LaH16 polyhydrides Phys. Rev. B 101 024508 doi: 10.1103/PhysRevB.101.024508
    [15]
    Kong P, et al 2021 Superconductivity up to 243 K in the yttrium-hydrogen system under high pressure Nat. Commun. 12 5075 doi: 10.1038/s41467-021-25372-2
    [16]
    Semenok D V, Kvashnin A G, Ivanova A G, Svitlyk V, Fominski V Y, Sadakov A V, Sobolevskiy O A, Pudalov V M, Troyan I A, Oganov A R 2020 Superconductivity at 161 K in thorium hydride ThH10: synthesis and properties Mater. Today 33 36-44 doi: 10.1016/j.mattod.2019.10.005
    [17]
    Shao M, Chen W, Zhang K, Huang X, Cui T 2021 High-pressure synthesis of superconducting clathratelike YH4 Phys. Rev. B 104 174509 doi: 10.1103/PhysRevB.104.174509
    [18]
    Shao M, Chen S, Chen W, Zhang K, Huang X, Cui T 2021 Superconducting ScH3 and LuH3 at megabar pressures Inorg. Chem. 60 15330-5 doi: 10.1021/acs.inorgchem.1c01960
    [19]
    Zhang C, He X, Li Z, Zhang S, Feng S, Wang X, Yu R, Jin C 2022 Superconductivity in zirconium polyhydrides with Tc above 70 K Sci. Bull. 67 907-9 doi: 10.1016/j.scib.2022.03.001
    [20]
    Hong F, et al 2022 Possible superconductivity at 70 K in tin hydride SnHx under high pressure Mater. Today Phys. 22 100596 doi: 10.1016/j.mtphys.2021.100596
    [21]
    Li Z, et al 2022 Superconductivity above 200 K discovered in superhydrides of calcium Nat. Commun. 13 2863 doi: 10.1038/s41467-022-30454-w
    [22]
    Denchfield A, Park H, Hemley R J 2024 Electronic structure of nitrogen-doped lutetium hydrides Phys. Rev. Materials 8 L021801 doi: 10.1103/PhysRevMaterials.8.L021801
    [23]
    Ge Y, Zhang F, Hemley R J 2021 Room-temperature superconductivity in boron-and nitrogen-doped lanthanum superhydride Phys. Rev. B 104 214505 doi: 10.1103/PhysRevB.104.214505
    [24]
    Ge Y, Zhang F, Dias R P, Hemley R J, Yao Y 2020 Hole-doped room-temperature superconductivity in H3S1−xZx (Z = C, Si) Mater. Today Phys. 15 100330 doi: 10.1016/j.mtphys.2020.100330
    [25]
    Fan F, Papaconstantopoulos D, Mehl M, Klein B 2016 High-temperature superconductivity at high pressures for H3SixP1−x, H3PxS1−x and H3Cl−xS1−x J. Phys. Chem. Solids 99 105-10 doi: 10.1016/j.jpcs.2016.08.007
    [26]
    Snider E, Dasenbrock-Gammon N, McBride R, Debessai M, Vindana H, Vencatasamy K, Lawler K V, Salamat A, Dias R P 2020 RETRACTED ARTICLE: room-temperature superconductivity in a carbonaceous sulfur hydride Nature 586 373-7 doi: 10.1038/s41586-020-2801-z
    [27]
    Dasenbrock-Gammon N, et al 2023 RETRACTED ARTICLE: evidence of near-ambient superconductivity in a N-doped lutetium hydride Nature 615 244-50 doi: 10.1038/s41586-023-05742-0
    [28]
    Jain A, et al 2013 Commentary: the materials project: a materials genome approach to accelerating materials innovation APL Mater. 1 011002 doi: 10.1063/1.4812323
    [29]
    Saal J E, Kirklin S, Aykol M, Meredig B, Wolverton C 2013 Materials design and discovery with high-throughput density functional theory: the Open Quantum Materials Database (OQMD) JOM 65 1501-9 doi: 10.1007/s11837-013-0755-4
    [30]
    Kirklin S, Saal J E, Meredig B, Thompson A, Doak J W, Aykol M, Rühl S, Wolverton C 2015 The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies npj Comput. Mater. 1 15010 doi: 10.1038/npjcompumats.2015.10
    [31]
    Haastrup S, et al 2018 The computational 2D materials database: high-throughput modeling and discovery of atomically thin crystals 2D Mater. 5 042002 doi: 10.1088/2053-1583/aacfc1
    [32]
    Gjerding M N, et al 2021 Recent progress of the computational 2D materials database (C2DB) 2D Mater. 8 044002 doi: 10.1088/2053-1583/ac1059
    [33]
    Choudhary K, et al 2020 The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design npj Comput. Mater. 6 1-13 doi: 10.1038/s41524-020-00440-1
    [34]
    Ong S P, Richards W D, Jain A, Hautier G, Kocher M, Cholia S, Gunter D, Chevrier V L, Persson K A, Ceder G 2013 Python materials genomics (pymatgen): a robust, open- source python library for materials analysis Comput. Mater. Sci. 68 314-9 doi: 10.1016/j.commatsci.2012.10.028
    [35]
    Wines D, Gurunathan R, Garrity K F, DeCost B, Biacchi A J, Tavazza F, Choudhary K 2023 Recent progress in the JARVIS infrastructure for next-generation data-driven materials design Appl. Phys. Rev. 10 041302 doi: 10.1063/5.0159299
    [36]
    Choudhary K, Garrity K 2022 Designing high-TC superconductors with BCS-inspired screening, density functional theory and deep-learning npj Comput. Mater. 8 244 doi: 10.1038/s41524-022-00933-1
    [37]
    Wines D, Choudhary K, Biacchi A J, Garrity K F, Tavazza F 2023 High-throughput DFT-based discovery of next generation two-dimensional (2D) superconductors Nano Lett. 23 969-78 doi: 10.1021/acs.nanolett.2c04420
    [38]
    García-Nieto P J, García-Gonzalo E, Paredes-Sánchez J 2021 Prediction of the critical temperature of a superconductor by using the WOA/MARS, Ridge, Lasso and Elastic-net machine learning techniques Neural Comput. Appl. 33 17131-45 doi: 10.1007/s00521-021-06304-z
    [39]
    Stanev V, Oses C, Kusne A G, Rodriguez E, Paglione J, Curtarolo S, Takeuchi I 2018 Machine learning modeling of superconducting critical temperature npj Comput. Mater. 4 29 doi: 10.1038/s41524-018-0085-8
    [40]
    Zhang J, Zhu Z, Xiang X D, Zhang K, Huang S, Zhong C, Qiu H-J, Hu K, Lin X 2022 Machine learning prediction of superconducting critical temperature through the structural descriptor J. Phys. Chem. C 126 8922-7 doi: 10.1021/acs.jpcc.2c01904
    [41]
    Meredig B, et al 2018 Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery Mol. Syst. Des. Eng. 3 819-25 doi: 10.1039/C8ME00012C
    [42]
    Roter B, Dordevic S 2020 Predicting new superconductors and their critical temperatures using machine learning Physica C 575 1353689 doi: 10.1016/j.physc.2020.1353689
    [43]
    Menon D, Ranganathan R 2022 A generative approach to materials discovery, design and optimization ACS Omega 7 25958-73 doi: 10.1021/acsomega.2c03264
    [44]
    Seegmiller C C, Baird S G, Sayeed H M, Sparks T D 2023 Discovering chemically novel, high-temperature superconductors Comput. Mater. Sci. 228 112358 doi: 10.1016/j.commatsci.2023.112358
    [45]
    Wines D, Xie T, Choudhary K 2023 Inverse design of next-generation superconductors using data-driven deep generative models J. Phys. Chem. Lett. 14 6630-8 doi: 10.1021/acs.jpclett.3c01260
    [46]
    Shipley A M, Hutcheon M J, Needs R J, Pickard C J 2021 High-throughput discovery of high-temperature conventional superconductors Phys. Rev. B 104 054501 doi: 10.1103/PhysRevB.104.054501
    [47]
    Sommer T, Willa R, Schmalian J, Friederich P 2023 3DSC - a dataset of superconductors including crystal structures Sci. Data 10 816 doi: 10.1038/s41597-023-02721-y
    [48]
    Cerqueira T F, Sanna A, Marques M A 2024 Sampling the materials space for conventional superconducting compounds Adv. Mater. 36 2307085 doi: 10.1002/adma.202307085
    [49]
    Saha S, Di Cataldo S, Giannessi F, Cucciari A, von der Linden W, Boeri L 2023 Mapping superconductivity in high-pressure hydrides: the Superhydra project Phys. Rev. Mater. 7 054806 doi: 10.1103/PhysRevMaterials.7.054806
    [50]
    Belli F, Novoa T, Contreras-García J, Errea I 2021 Strong correlation between electronic bonding network and critical temperature in hydrogen-based superconductors Nat. Commun. 12 5381 doi: 10.1038/s41467-021-25687-0
    [51]
    Choudhary K, et al 2022 Recent advances and applications of deep learning methods in materials science npj Comput. Mater. 8 59 doi: 10.1038/s41524-022-00734-6
    [52]
    Choudhary K 2024 AtomGPT: atomistic generative pre-trained transformer for forward and inverse materials design (arXiv:2405.03680)
    [53]
    Burdine C, Blair E 2023 Discovery of novel superconducting materials with deep learning 2023 IEEE Int. Conf. on Quantum Computing and Engineering (QCE) pp 1335-4110.1109/QCE57702.2023.00151
    [54]
    Baroni S, Giannozzi P, Testa A 1987 Green’s-function approach to linear response in solids Phys. Rev. Lett. 58 1861 doi: 10.1103/PhysRevLett.58.1861
    [55]
    Gonze X 1995 Perturbation expansion of variational principles at arbitrary order Phys. Rev. A 52 1086 doi: 10.1103/PhysRevA.52.1086
    [56]
    Wierzbowska M, de Gironcoli S, Giannozzi P 2005 Origins of low-and high-pressure discontinuities of Tc in niobium (arXiv:cond-mat/0504077)
    [57]
    Giannozzi P, et al 2020 Quantum ESPRESSO toward the exascale J. Chem. Phys. 152 154105 doi: 10.1063/5.0005082
    [58]
    Garrity K F, Bennett J W, Rabe K M, Vanderbilt D 2014 Pseudopotentials for high-throughput DFT calculations Comput. Mater. Sci. 81 446-52 doi: 10.1016/j.commatsci.2013.08.053
    [59]
    Perdew J P, Ruzsinszky A, Csonka G I, Vydrov O A, Scuseria G E, Constantin L A, Zhou X, Burke K 2008 Restoring the density-gradient expansion for exchange in solids and surfaces Phys. Rev. Lett. 100 136406 doi: 10.1103/PhysRevLett.100.136406
    [60]
    Topsakal M, Wentzcovitch R 2014 Accurate projected augmented wave (PAW) datasets for rare-earth elements (RE = La-Lu) Comput. Mater. Sci. 95 263-70 doi: 10.1016/j.commatsci.2014.07.030
    [61]
    Choudhary K, Tavazza F 2019 Convergence and machine learning predictions of Monkhorst-Pack k-points and plane-wave cut-off in high-throughput DFT calculations Comput. Mater. Sci. 161 300-8 doi: 10.1016/j.commatsci.2019.02.006
    [62]
    Marsiglio F 2020 Eliashberg theory: a short review Ann. Phys., NY 417 168102 doi: 10.1016/j.aop.2020.168102
    [63]
    McMillan W 1968 Transition temperature of strong-coupled superconductors Phys. Rev. 167 331 doi: 10.1103/PhysRev.167.331
    [64]
    Choudhary K, DeCost B 2021 Atomistic line graph neural network for improved materials property predictions npj Comput. Mater. 7 1-8 doi: 10.1038/s41524-021-00650-1
    [65]
    Paszke A, et al 2019 PyTorch: an imperative style, high-performance deep learning library Advances in Neural Information Processing Systemsvol 32 8026-3710.5555/3454287.3455008
    [66]
    Wang M, et al 2019 Deep graph library: towards efficient and scalable deep learning on graphs (arXiv:1909.01315)
    [67]
    Klimeš J, Bowler D R, Michaelides A 2009 Chemical accuracy for the van der Waals density functional J. Phys.: Condens. Matter 22 022201 doi: 10.1088/0953-8984/22/2/022201
    [68]
    Eliashberg G M 1960 Interactions between electrons and lattice vibrations in a superconductor Sov. Phys. -JETP 11 3(Engl. transl.)
    [69]
    Sanna A, Pellegrini C, Liebhaber E, Rossnagel K, Franke K J, Gross E K U 2022 Real-space anisotropy of the superconducting gap in the charge-density wave material 2H-NbSe2 npj Quantum Mater. 7 6 doi: 10.1038/s41535-021-00412-8
    [70]
    Marques M A L, Lüders M, Lathiotakis N N, Profeta G, Floris A, Fast L, Continenza A, Gross E K U, Massidda S 2005 Ab initio theory of superconductivity. II. Application to elemental metals Phys. Rev. B 72 024546 doi: 10.1103/PhysRevB.72.024546
    [71]
    Lüders M, Marques M A L, Lathiotakis N N, Floris A, Profeta G, Fast L, Continenza A, Massidda S, Gross E K U 2005 Ab initio theory of superconductivity. I. Density functional formalism and approximate functionals Phys. Rev. B 72 024545 doi: 10.1103/PhysRevB.72.024545
    [72]
    Ong S P, Jain A, Hautier G, Kang B, Ceder G 2010 Thermal stabilities of delithiated olivine MPO4 (M = Fe, Mn) cathodes investigated using first principles calculations Electrochem. Commun. 12 427-30 doi: 10.1016/j.elecom.2010.01.010
    [73]
    Ong S P, Wang L, Kang B, Ceder G 2008 Li-Fe-P-O2 phase diagram from first principles calculations Chem. Mater. 20 1798-807 doi: 10.1021/cm702327g
    [74]
    Kim D Y, Scheicher R H, kwang Mao H, Kang T W, Ahuja R 2010 General trend for pressurized superconducting hydrogen-dense materials Proc. Natl Acad. Sci. 107 2793-6 doi: 10.1073/pnas.0914462107
    [75]
    Lonie D C, Hooper J, Altintas B, Zurek E 2013 Metallization of magnesium polyhydrides under pressure Phys. Rev. B 87 054107 doi: 10.1103/PhysRevB.87.054107
    [76]
    El-Eskandarany M S, Banyan M, Al-Ajmi F 2018 Discovering a new MgH2 metastable phase RSC Adv. 8 32003-8 doi: 10.1039/C8RA07068G
    [77]
    Boonchot C, Tsuppayakorn-Aek P, Pinsook U, Bovornratanaraks T 2021 Stability and electronic structure of magnesium hydride and magnesium deuteride under high pressure J. Phys.: Conf. Ser. 2145 012026 doi: 10.1088/1742-6596/2145/1/012026
    [78]
    Pickard C J, Needs R J 2006 High-pressure phases of silane Phys. Rev. Lett. 97 045504 doi: 10.1103/PhysRevLett.97.045504
    [79]
    Strobel T A, Goncharov A F, Seagle C T, Liu Z, Somayazulu M, Struzhkin V V, Hemley R J 2011 High-pressure study of silane to 150 GPa Phys. Rev. B 83 144102 doi: 10.1103/PhysRevB.83.144102
    [80]
    Chen X-J, Wang J-L, Struzhkin V V, Mao H-K, Hemley R J, Lin H-Q 2008 Superconducting behavior in compressed solid SiH4 with a layered structure Phys. Rev. Lett. 101 077002 doi: 10.1103/PhysRevLett.101.077002
    [81]
    Zhang H, Jin X, Lv Y, Zhuang Q, Liu Y, Lv Q, Bao K, Li D, Liu B, Cui T 2015 High-temperature superconductivity in compressed solid silane Sci. Rep. 5 8845 doi: 10.1038/srep08845
    [82]
    Kim D Y, Scheicher R H, Lebègue S, Prasongkit J, Arnaud B, Alouani M, Ahuja R 2008 Crystal structure of the pressure-induced metallic phase of SiH4 from ab initio theory Proc. Natl Acad. Sci. 105 16454-9 doi: 10.1073/pnas.0804148105
    [83]
    Strobel T A, Somayazulu M, Hemley R J 2009 Novel pressure-induced interactions in silane-hydrogen Phys. Rev. Lett. 103 065701 doi: 10.1103/PhysRevLett.103.065701
    [84]
    Degtyareva O, Canales M M, Bergara A, Chen X-J, Song Y, Struzhkin V V, Mao H-K, Hemley R J 2007 Crystal structure of SiH4 at high pressure Phys. Rev. B 76 064123 doi: 10.1103/PhysRevB.76.064123
    [85]
    Howie R T, Narygina O, Guillaume C L, Evans S, Gregoryanz E 2012 High-pressure synthesis of lithium hydride Phys. Rev. B 86 064108 doi: 10.1103/PhysRevB.86.064108
    [86]
    Pépin C, Loubeyre P, Occelli F, Dumas P 2015 Synthesis of lithium polyhydrides above 130 GPa at 300 K Proc. Natl Acad. Sci. 112 7673-6 doi: 10.1073/pnas.1507508112
    [87]
    Smith J S, Desgreniers S, Klug D D, Tse J S 2009 High-density strontium hydride: an experimental and theoretical study Solid State Commun. 149 830-4 doi: 10.1016/j.ssc.2009.03.021
    [88]
    Struzhkin V V, Kim D Y, Stavrou E, Muramatsu T, Mao H-K, Pickard C J, Needs R J, Prakapenka V B, Goncharov A F 2016 Synthesis of sodium polyhydrides at high pressures Nat. Commun. 7 12267 doi: 10.1038/ncomms12267
    [89]
    Choudhary K, DeCost B, Major L, Butler K, Thiyagalingam J, Tavazza F 2023 Unified graph neural network force-field for the periodic table: solid state applications Digit. Discovery 2 346-55 doi: 10.1039/D2DD00096B
    [90]
    Chen C, Ong S P 2022 A universal graph deep learning interatomic potential for the periodic table Nat. Comput. Sci. 2 718-28 doi: 10.1038/s43588-022-00349-3
    [91]
    Gasteiger J, Shuaibi M, Sriram A, Günnemann S, Ulissi Z, Zitnick C L, Das A 2022 GemNet-OC: developing graph neural networks for large and diverse molecular simulation datasets (arXiv:2204.02782)
    [92]
    Larsen A H, et al 2017 The atomic simulation environment—a Python library for working with atoms J. Phys.: Condens. Matter 29 273002 doi: 10.1088/1361-648X/aa680e
    [93]
    Bitzek E, Koskinen P, Gähler F, Moseler M, Gumbsch P 2006 Structural relaxation made simple Phys. Rev. Lett. 97 170201 doi: 10.1103/PhysRevLett.97.170201
    [94]
    Choudhary K, et al 2024 JARVIS-Leaderboard: a large scale benchmark of materials design methods npj Comput. Mater. 10 93 doi: 10.1038/s41524-024-01259-w
    [95]
    Evans M, et al 2024 Developments and applications of the OPTIMADE API for materials discovery, design and data exchange Digit. Discovery doi: 10.1039/D4DD00039K
  • 加载中

Catalog

    Figures(7)  / Tables(1)

    Article Metrics

    Article Views(208) PDF downloads(29)
    Article Statistics
    Related articles from

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return