Machine Learning and High-Throughput Approaches to Magnetism

  • S. Sanvito
  • M. Žic
  • J. Nelson
  • T. Archer
  • C. Oses
  • S. Curtarolo
Living reference work entry


Magnetic materials have underpinned human civilization for at least one millennium and now find applications in the most diverse technologies, ranging from data storage, to energy production and delivery, to sensing. Such great diversity, associated to the fact that only a limited number of elements can sustain a magnetic order, makes magnetism rare and fascinating. The discovery of a new high-performance magnet is often a complex process, where serendipity plays an important role. Here we present a range of novel approaches to the discovery and design of new magnetic materials, which is rooted in high-throughput electronic structure theory and machine learning models. Such combination of methods has already demonstrated the ability of discovering ferromagnets with high Curie temperature at an unprecedented speed.



This work is supported by Science Foundation Ireland (Grants No. 14/IA/2624). JN thank the Irish Research Council for financial support. SC and CO acknowledge support by DOD-ONR (N00014-13-1-0635, N00014-15-1-2863, N00014-16-1-2326) and the consortium – Duke University – for computational assistance. SC acknowledges the Alexander von Humboldt Foundation for financial support.


  1. Archer T, Pemmaraju C, Sanvito S, Franchini C, He J, Filippetti A, Delugas P, Puggioni D, Fiorentini V, Tiwari R, Majumdar P (2011) Exchange interactions and magnetic phases of transition metal oxides: benchmarking advanced ab initio methods. Phys Rev B 84:115114ADSCrossRefGoogle Scholar
  2. Bloński P, Hafner J (2009) Density-functional theory of the magnetic anisotropy of nanostructures: an assessment of different approximations. J Phys Condens Matter 21:426001ADSCrossRefGoogle Scholar
  3. Calderon C, Plata J, Toher C, Oses C, Levy O, Fornari M, Natan A, Mehl M, Hart G, Nardelli M, Curtarolo S (2015) The AFLOW standard for high-throughput materials science calculations diagrams. Comput Mat Sci 108:233–238CrossRefGoogle Scholar
  4. Carrete J, Li W, Mingo N, Wang S, Curtarolo S (2014) Finding unprecedentedly low-thermal-conductivity half-heusler semiconductors via high-throughput materials modeling. Phys Rev X 4:011019Google Scholar
  5. Castelliz L (1955) Beitrag zum ferromagnetismus von legierungen der ubergangsmetalle mit elementen der b-gruppe. Z Metallk 46:198–203Google Scholar
  6. Coey J (2009) Magnetism and magnetic materials. Oxford University Press, OxfordGoogle Scholar
  7. Coey J, Sanvito S (2004) Magnetic semiconductors and half-metals. J Phys D Appl Phys 37: 988–993ADSCrossRefGoogle Scholar
  8. Curtarolo S, Setyawan W, Hart G, Jahnatek M, Chepulskii R, Taylor R, Wang S, Xue J, Yang K, Levy O, Mehl M, Morgan D (2012a) AFLOW: an automatic framework for high-throughput materials discovery. Comput Mat Sci 58:218–226CrossRefGoogle Scholar
  9. Curtarolo S, Setyawan W, Wang S, Xue J, Yang K, Taylor R, Nelson L, Hart G, Sanvito S, Nardelli M, Mingo N, Levy O (2012b) AFLOWLIB.ORG: a distributed materials properties repository from high-throughput ab initio calculations. Comput Mat Sci 58:227–235CrossRefGoogle Scholar
  10. Curtarolo S, Hart G, Nardelli M, Mingo N, Sanvito S, Levy O (2013) The high-throughput highway to computational materials design. Nat Mater 12:191–201ADSCrossRefGoogle Scholar
  11. Dam HC, Nguyen VC, Pham TL, Nguyen AT, Kino H, Terakura K, Miyake T (2017) A regression-based feature selection study of the curie temperature of transition-metal rare-earth compounds: prediction and understanding. arXiV:cond-matGoogle Scholar
  12. d’Avezac M, Luo JW, Chanier T, Zunger A (2012) Genetic-algorithm discovery of a direct-gap and optically allowed superstructure from indirect-gap Si and Ge semiconductors. Phys Rev Lett 108:027401ADSCrossRefGoogle Scholar
  13. Dunn TM (1961) Spin-orbit coupling in the first and second transition series. Trans Farad Soc 57:1441CrossRefGoogle Scholar
  14. Faleev SV, Ferrante Y, Jeong J, Samant MG, Jones B, Parkin SS (2017) Origin of the tetragonal ground state of Heusler compounds. Phys Rev Appl 7:034022ADSCrossRefGoogle Scholar
  15. Franchini C, Archer T, He J, Chen XQ, Filippetti A, Sanvito S (2011) Exceptionally strong magnetism in the 4d perovskites RTcO3 (R = Ca, Sr, Ba). Phys Rev B 83:220402Google Scholar
  16. Ghiringhelli L, Vybiral J, Levchenko S, Draxl C, Scheffler M (2015) Big data of materials science: critical role of the descriptor. Phys Rev Lett 114:105503ADSCrossRefGoogle Scholar
  17. Ghiringhelli L, Carbogno C, Levchenko S, Mohamed F, Huhs G, Lueders M, Oliveira M, Scheffler M (2017) Towards efficient data exchange and sharing for big-data driven materials science: metadata and data formats. NPJ Comput Mater 3:46ADSCrossRefGoogle Scholar
  18. Graf T, Felser C, Parkin S (2011) Simple rules for the understanding of Heusler compounds. Prog Solid State Chem 39:1–50CrossRefGoogle Scholar
  19. Grazulis S, Chateigner D, Downs RT, Yokochi AT, Quiros M, Lutterotti L, Manakova E, Butkus J, Moeck P, Le Bail A (2009) Crystallography open database – an open-access collection of crystal structures. J Appl Crystallogr 42:726–729CrossRefGoogle Scholar
  20. Hachmann J, Olivares-Amaya R, Atahan-Evrenk S, Amador-Bedolla C, Snchez-Carrera RS, Gold-Parker A, Vogt L, Brockway AM, Aspuru-Guzik A (2011) The Harvard clean energy project: large-scale computational screening and design of organic photovoltaics on the world community grid. J Phys Chem Lett 2(17):2241–2251CrossRefGoogle Scholar
  21. Hart G, Curtarolo S, Massalski T, Levy O (2013) Comprehensive search for new phases and compounds in binary alloy systems based on platinum-group metals, using a computational first-principles approach. Phys Rev X 3:041035Google Scholar
  22. Hastie T, Tibshirani R, Friedman J (2013) The elements of statistical learning: data mining, inference, and prediction. Springer, New YorkzbMATHGoogle Scholar
  23. ICSD (2018) FIZ Karlsruhe and NIST, inorganic crystal structure database. http://icsdfiz-karlsruhede/icsd/
  24. Isayev O, Oses C, Toher C, Gossett E, Curtarolo S, Tropsha A (2017) Universal fragment descriptors for predicting properties of inorganic crystals. Nat Comm 8:15679ADSCrossRefGoogle Scholar
  25. Jain A, Ong SP, Hautier G, Chen W, Richards WD, Dacek S, Cholia S, Gunter D, Skinner D, Ceder G, Persson KA (2013) Commentary: the materials project: a materials genome approach to accelerating materials innovation. APL Mater 1(1):011002ADSCrossRefGoogle Scholar
  26. Janak J (1977) Uniform susceptibilities of metallic elements. Phys Rev B 16:255–262ADSCrossRefGoogle Scholar
  27. Kanomata T, Shirakawa K, Kaneko T (1987) Effect of hydrostatic pressure on the curie temperature of the Heusler alloys Ni2MnZ (Z = Al, Ga, In, Sn and Sb). J Magn Magn Mater 65:76ADSCrossRefGoogle Scholar
  28. Kirklin S, Saal JE, Meredig B, Thompson A, Doak JW, Aykol M, Rühl S, Wolverton C (2015) The open quantum materials database (OQMD): assessing the accuracy of DFT formation energies. npj Comput Mat 1:15010Google Scholar
  29. Kresse G, Furthmuller J (1996) Efficiency of ab initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput Mater Sci 6:15–50CrossRefGoogle Scholar
  30. Kusne AG, Gao T, Mehta A, Ke L, Nguyen MC, Ho KM, Antropov V, Wang CZ, Kramer MJ, Long C, Takeuchi I (2014) On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets. Sci Rep 4:6367CrossRefGoogle Scholar
  31. Lukas H, Fries S, Sundman B (2007) Computational thermodynamics, the Calphad method. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  32. Magda G, Jin X, Hagymási I, Vancsó P, Osváth Z, Nemes-Incze P, Hwang C, Biró L, Tapasztó L (2014) Room-temperature magnetic order on zigzag edges of narrow graphene nanoribbons. Nature 514:608–611ADSCrossRefGoogle Scholar
  33. Mazin I (1999) How to define and calculate the degree of spin polarization in ferromagnets. Phys Rev Lett 83:1427–1430ADSCrossRefGoogle Scholar
  34. Moruzzi VL, Marcus PM (1989) Magnetism in FCC rhodium and palladium. Phys Rev B 39: 471–474ADSCrossRefGoogle Scholar
  35. Oganov A, Glass C (2006) Crystal structure prediction using ab initio evolutionary techniques: principles and applications. J Chem Phys 124:244704ADSCrossRefGoogle Scholar
  36. Oliynyk AO, Mar A (2018) Discovery of intermetallic compounds from traditional to machine- learning approaches. Acc Chem Res 51:59–68CrossRefGoogle Scholar
  37. Oswald A, Zeller R, Braspenning P, Dederichs P (1985) Interaction of magnetic impurities in Cu and Ag. J Phys F 15:193ADSCrossRefGoogle Scholar
  38. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825MathSciNetzbMATHGoogle Scholar
  39. Perdew J, Burke K, Ernzerhof M (1996) Generalized gradient approximation made simple. Phys Rev Lett 77:3865–3868ADSCrossRefGoogle Scholar
  40. Pickard CJ, Needs R (2011) Ab initio random structure searching. J Phys Condens Matter 23:053201ADSCrossRefGoogle Scholar
  41. Pizzi G, Cepellotti A, Sabatini R, Marzari N, Kozinsky B (2016) Aiida: automated interactive infrastructure and database for computational science. Comput Mat Sci 111:218–230CrossRefGoogle Scholar
  42. Rasmussen FA, Thygesen KS (2015) Computational 2D materials database: electronic structure of transition-metal dichalcogenides and oxides. J Phys Chem C 119(23):13169–13183CrossRefGoogle Scholar
  43. Requist R, Baruselli P, Smogunov A, Fabrizio M, Modesti S, Tosatti E (2016) Metallic, magnetic and molecular nanocontacts. Nat Nanotech 11:499–508ADSCrossRefGoogle Scholar
  44. Rode K, Baadji N, Betto D, Lau YC, Kurt H, Venkatesan M, Stamenov P, Sanvito S, Coey J, Fonda E, Otero E, Choueikani F, Ohresser P, Porcher F, André G (2013) Site-specific order and magnetism in tetragonal Mn3Ga thin films. Phys Rev B 87:184429ADSCrossRefGoogle Scholar
  45. Rodriguez E, Poineau F, Llobet A, Kennedy B, Avdeev M, Thorogood G, Carter M, Seshadri R, Singh D, Cheetham A (2011) High temperature magnetic ordering in the 4d perovskite SrTcO3. Phys Rev Lett 106:067201ADSCrossRefGoogle Scholar
  46. Sandratskii L (1986) Energy band structure calculations for crystals with spiral magnetic structure. Phys Status Solidi B 136:167ADSCrossRefGoogle Scholar
  47. Sanvito S, Oses C, Xue J, Tiwari A, Zic M, Archer T, Tozman P, Venkatesan M, Coey M, Curtarolo S (2017) Accelerated discovery of new magnets in the Heusler alloy family. Sci Adv 3:e1602241ADSCrossRefGoogle Scholar
  48. Savrasov S (1998) Linear response calculations of spin fluctuations. Phys Rev Lett 81:2570–2573ADSCrossRefGoogle Scholar
  49. Shalev-Shwartz S, Ben-David S (2014) Understanding machine learning. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  50. Toher C, Plata J, Levy O, de Jong M, Asta M, Nardelli MB, Curtarolo S (2014) High-throughput computational screening of thermal conductivity, Debye temperature, and Grüneisen parameter using a quasi-harmonic Debye model. Phys Rev B 90:174107ADSCrossRefGoogle Scholar
  51. Toher C, Oses C, Hicks D, Gossett E, Rose F, Nath P, Usanmaz D, Perim DCFE, Calderon CE, JPlata J, Lederer Y, MichalJahnátek, Setyawan W, Wang S, Xue J, Chepulskii KRRV, Taylor RH, Gomez G, Shi H, Supka AR, Orabi RARA, Gopal P, Cerasoli FT, Liyanage L, Wang H, Siloi I, Agapito LA, Nyshadham C, Hart GLW, Carrete J, Legrain F, Mingo N, Zurek E, Isayev O, Tropsha A, Sanvito S, Hanson RM, Takeuchi I, Mehl MJ, Kolmogorov AN, Yang K, D’Amico P, Calzolari A, Costa M, Gennaro RD, Nardelli MB, Fornari M, Levy O, Curtarolo S (2018) The AFLOW fleet for materials discovery. In: Handbook of materials modeling. Methods: theory and modeling, vol 1. SpringerGoogle Scholar
  52. Žic M (2017) Towards data-driven magnetic materials discovery. Ph.D Thesis, Trinity College DublinGoogle Scholar
  53. Žic M, Archer T, Sanvito S (2017) Designing magnetism in Fe-based Heusler alloys: a machine learning approach. arXiv p 1706.01840Google Scholar
  54. Wadley P, Novák V, Campion R, Rinaldi C, Martí X, Reichlová H, Železný J, Gazquez J, Roldan M, Varela M, Khalyavin D, Langridge S, Kriegner D, Máca F, Mašek J, Bertacco R, Holý V, Rushforth A, Edmonds K, Gallagher B, Foxon C, Wunderlich J, Jungwirth T (2013) Tetragonal phase of epitaxial room-temperature antiferromagnet cumnas. Nat Commun 4:2322ADSCrossRefGoogle Scholar
  55. Wohlfarth EP (1980) Ferromagnetic materials: a handbook on the properties of magnetically ordered substances. Elsevier, New YorkGoogle Scholar
  56. Yan F, Zhang X, Yu Y, Yu L, Nagaraja A, Mason T, Zunger A (2015) Design and discovery of a novel half-Heusler transparent hole conductor made of all-metallic heavy elements. Nat Commun 6:7308ADSCrossRefGoogle Scholar
  57. Yang K, Setyawan W, Wang S, Nardelli MB, Curtarolo S (2012) A search model for topological insulators with high-throughput robustness descriptors. Nat Mater 11:614–619ADSCrossRefGoogle Scholar
  58. Yang K, Oses C, Curtarolo S (2016) Modeling off-stoichiometry materials with a high-throughput ab-initio approach. Chem Mater 28:6484–6492CrossRefGoogle Scholar
  59. Yong J, Jiang Y, Usanmaz D, Curtarolo S, Zhang X, Shin J, Li L, Pan X, Tachuchi I, Greene R (2014) Composition-spread growth and the robust topological surface state of Kondo insulator SmB6 thin films. Appl Phys Lett 105:222403ADSCrossRefGoogle Scholar
  60. Yu L, Zunger A (2012) Identification of potential photovoltaic absorbers based on first-principles spectroscopic screening of materials. Phys Rev Lett 108:068701ADSCrossRefGoogle Scholar
  61. Ziebeckt K, Webster P (1975) Helical magnetic order in Ni2MnAl. J Phys F Met Phys 5:1756–1766ADSCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • S. Sanvito
    • 1
  • M. Žic
    • 1
  • J. Nelson
    • 1
  • T. Archer
    • 1
  • C. Oses
    • 2
    • 3
  • S. Curtarolo
    • 2
    • 3
  1. 1.School of Physics and CRANN InstituteTrinity CollegeDublinIreland
  2. 2.Center for Materials GenomicsDuke UniversityDurhamUSA
  3. 3.Departments of Mechanical Engineering and Materials Science, Physics, and ChemistryDuke UniversityDurhamUSA

Section editors and affiliations

  • Stefano Sanvito
    • 1
  1. 1.Department of PhysicsTrinity CollegeDublinIreland

Personalised recommendations