Borides as promising M₂AX phase materials with high elastic modulus using machine learning and optimization

Abstract

There is growing interest in novel MAX phase materials for various applications ranging from aircraft/spacecraft and defense to energy and electronics due to their unique combination of metallic and ceramic properties. Traditional materials discovery has mostly relied on human intuition coupled with rigorous experiments; however, this approach has been time-consuming and inefficient. Over the last few decades, advances in fundamental and data-driven approaches such as first-principles modeling, materials informatics, machine learning and optimization, coupled with an exponential rise in computational power, have enabled faster and more efficient materials discovery. Here, we present an exploration of high elastic modulus novel boride-based M₂AX phase materials using a combination of the aforementioned methods. Specifically, an ensemble of gradient boosted machine learning models was developed to predict the elastic modulus from informatics-based structural features by leveraging a dataset of Density Functional Theory (DFT)-predicted elastic moduli for 223 M₂AX phase materials (carbides and nitrides). Using Bayesian optimization, inverse modeling was carried out to maximize the model-predicted elastic modulus by identifying the optimal features. Finally, model predictions for 1,035 candidate M₂AX materials were generated to compare their features with the optimal features to identify potential novel promising materials. We found that Ta₂PB, Nb₂PB, and V₂PB have similar high elastic moduli (371.7, 351.5, and 347.4 GPa) to their carbide counterparts (364.7, 357.7, and 373.5 GPa), and our results support the possibility that borides can be a viable tertiary element for M₂AX phases.

Keywords

M₂AX phase / materials informatics / machine learning / ensemble / Bayesian optimization / borides

References

[1] Barsoum MW.MAX phases: properties of machinable ternary carbides and nitrides. 1^st ed. Wiley; 2013.

[2] Tzenov NV.Synthesis and characterization of Ti₃AlC₂.J Am Ceram Soc2000;83:825-32

[3] Dahlqvist M,Rosen J.MAX phases - Past, present, and future.Mater Today2024;72:1-24

[4] Gonzalez-Julian J,Sebold D,Vassen R.Cr₂AlC MAX phase as bond coat for thermal barrier coatings: processing, testing under thermal gradient loading, and future challenges.J Am Ceram Soc2020;103:2362-75

[5] Smialek JL.Oxidation of Al₂O₃ scale-forming MAX phases in turbine environments.Metall Mater Trans A2018;49:782-92

[6] Sun ZM.Progress in research and development on MAX phases: a family of layered ternary compounds.Int Mater Rev2011;56:143-66

[7] Guo L,Wang X.Ti₂AlC MAX phase for resistance against CMAS attack to thermal barrier coatings.Ceram Int2019;45:7627-34

[8] Lapauw T,Joris J.Interaction of M_n+1AX_n phases with oxygen-poor, static and fast-flowing liquid lead-bismuth eutectic.J Nucl Mater2019;520:258-72

[9] Chirica IM,Neaţu Ş,Barsoum MW.Applications of MAX phases and MXenes as catalysts.J Mater Chem A2021;9:19589-612

[10] Ward L,Faghaninia A.Matminer: an open source toolkit for materials data mining.Comput Mater Sci2018;152:60-9

[11] Sparks TD,Parry ME,Brgoch J.Machine learning for structural materials.Annu Rev Mater Res2020;50:27-48

[12] Mansouri Tehrani A,Parry M.Machine learning directed search for ultraincompressible, superhard materials.J Am Chem Soc2018;140:9844-53

[13] Sayeed HM,Baird SG.NLP meets materials science: quantifying the presentation of materials data in literature.Matter2024;7:723-7

[14] Seegmiller CC,Sayeed HM.Discovering chemically novel, high-temperature superconductors.Comput Mater Sci2023;228:112358

[15] Alverson M,Murdock R,Johnson J.Generative adversarial networks and diffusion models in material discovery.Digit Discov2024;3:62-80

[16] Wang AYT,Murdock RJ.Compositionally restricted attention-based network for materials property predictions.npj Comput Mater2021;7:545

[17] Merchant A,Schoenholz SS,Cheon G.Scaling deep learning for materials discovery.Nature2023;624:80-5 PMCID:PMC10700131

[18] Fuhr AS.Deep generative models for materials discovery and machine learning-accelerated innovation.Front Mater2022;9:865270

[19] Shetty P,Gupta S,Ramprasad R. Accelerating materials discovery for polymer solar cells: data-driven insights enabled by natural language processing. arXiv. [Preprint.] Jun 22, 2024 [accessed 2024 Aug 24]. Available from: https://arxiv.org/abs/2402.19462.

[20] Alghofaili YA,Alsaui AA,Alharbi FH.Accelerating materials discovery through machine learning: predicting crystallographic symmetry groups.J Phys Chem C2023;127:16645-53

[21] Ward L,Choudhary A.A general-purpose machine learning framework for predicting properties of inorganic materials.npj Comput Mater2016;2:16028

[22] Li H,Li Y.Machine learning assisted design of aluminum-lithium alloy with high specific modulus and specific strength.Mater Design2023;225:111483

[23] Mohanty T,Sparks TD.Machine learning guided optimal composition selection of niobium alloys for high temperature applications.APL Mach Learn2023;1:036102

[24] Cover MF,Bilek MMM.A comprehensive survey of M₂AX phase elastic properties.J Phys Condens Matter2009;21:305403

[25] Head T,Nahrstaedt H,Shcherbatyi I. Scikit-optimize/scikit-optimize. 2020. Available from: https://zenodo.org/records/4014775. [Last accessed on 24 Aug 2024]

[26] Ali MA,Uddin MM,Naqib SH.The rise of 212 MAX phase borides: DFT insights into the physical properties of Ti₂PB₂, Zr₂PbB₂, and Nb₂AB₂ [A = P, S] for thermomechanical applications.ACS Omega2023;8:954-68 PMCID:PMC9835788

[27] Zhang Q,San X.Zr₂SeB and Hf₂SeB: two new MAB phase compounds with the Cr₂AlC-type MAX phase (211 phase) crystal structures.J Adv Ceram2022;11:1764-76

[28] Rackl T.The MAX phase borides Zr₂SB and Hf₂SB.Solid State Sci2020;106:106316

[29] Rackl T,Niklaus R.Syntheses and physical properties of the MAX phase boride Nb₂SB and the solid solutions Nb₂SB_xC_1-x(x = 0-1).Phys Rev Mater2019;3:054001

[30] Ashton M,Broderick SR,Sinnott SB.Computational discovery of stable M₂AX phases.Phys Rev B2016;94:054116

[31] Ohmer D,Opahle I,Zhang H.High-throughput design of 211 - M₂AX compounds.Phys Rev Mater2019;3:053803

[32] Ohmer D,Singh HK.Stability predictions of magnetic M₂AX compounds.J Phys Condens Matter2019;31:405902