journal article·2026-01Open access

Learning Crystallographic Disorder: Bridging Prediction and Experiment in Materials Discovery

Konstantin S. Jakob, Aron Walsh, Karsten Reuter, Johannes T. Margraf

Advanced Materials· Volume 38· Issue 5

Abstract

Abstract Recent computational materials discovery efforts have led to an enormous number of predictions of previously unknown, potentially stable inorganic, crystalline compounds. In particular, both high‐throughput screenings and generative models have benefited tremendously from recent advances in computational resources and available data. However, these efforts are currently limited to predicting pristine crystalline materials. As a consequence, many of these predictions cannot be realized in experiments, where kinetic effects, defects, and crystallographic disorder can be crucial. To address this shortcoming, the current work aims to introduce disorder into computational materials discovery with machine learning (ML) based classification models. Trained on the inorganic crystal structure database (ICSD), these classifiers capture the chemical trends of crystallographic disorder and estimate the prevalence of disorder in computational databases produced by the Materials Project or Graph Networks for Materials Science (GNoME) initiatives. This opens the door toward disorder‐aware computational materials discovery workflows, bridging the gap between prediction and experiment.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · X-ray Diffraction in Crystallography · Computational Drug Discovery Methods

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Theory Department Fritz Haber Institute of the Max Planck Society Faradayweg 4‐6 14195 Berlin Germany

Department of Materials Imperial College London London SW7 2AZ UK

Chair of Physical Chemistry V: Theory and Machine Learning University of Bayreuth Bavarian Center for Battery Technology (BayBatt) Weiherstraße 26 95448 Bayreuth Germany

Funding

Thomas Young Centre

References (73)

Show source-provided references
1. 10.1063/1.481232310.1063/1.4812323 ↗
2. 10.1002/adma.20221078810.1002/adma.202210788 ↗
3. 10.1016/j.mtphys.2024.10156010.1016/j.mtphys.2024.101560 ↗
4. 10.1038/s41586-023-06735-910.1038/s41586-023-06735-9 ↗
5. L.Barroso‐Luque M.Shuaibi X.Fu B. M.Wood M.Dzamba M.Gao A.Rizvi C. L.Zitnick Z. W.Ulissi arXiv2024 https://arxiv.org/abs/2410.12771.
6. K.Jakob K.Reuter J. T.Margraf Chemrxiv2025 https://chemrxiv.org/engage/chemrxiv/article‐details/67c32744fa469535b977cb88.
7. 10.1063/5.007622010.1063/5.0076220 ↗
8. T.Xie X.Fu O.‐E.Ganea R.Barzilay T.Jaakkola arXiv2022 https://arxiv.org/abs/2110.06197.
9. 10.1016/j.matt.2024.05.04210.1016/j.matt.2024.05.042 ↗
10. A.Nouira N.Sokolovska J.‐C.Crivello arXiv2019 https://arxiv.org/abs/1810.11203.
11. 10.1038/s41524-021-00526-410.1038/s41524-021-00526-4 ↗
12. Zeni C. · Nature · 2025 · 1
13. Jiao R. · Adv. Neural Inf. Process. Syst. · 2023 · 36
14. S.Yang K.Cho A.Merchant P.Abbeel D.Schuurmans I.Mordatch E. D.Cubuk arXiv2024 https://arxiv.org/abs/2311.09235.
15. H.Park A.Onwuli A.Walsh Chemrxiv2024 https://chemrxiv.org/engage/chemrxiv/article‐details/6728e27cf9980725cf118177.
16. 10.1038/s41467-024-54639-710.1038/s41467-024-54639-7 ↗
17. D.Flam‐Shepherd A.Aspuru‐Guzik arXiv2023 https://arxiv.org/abs/2305.05708.
18. N.Gruver A.Sriram A.Madotto A. G.Wilson C. L.Zitnick Z.Ulissi arXiv2024 https://arxiv.org/abs/2402.04379.
19. 10.1039/a901227c10.1039/a901227c ↗
20. 10.1016/j.cpc.2006.07.02010.1016/j.cpc.2006.07.020 ↗
21. 10.1038/s43588-022-00349-310.1038/s43588-022-00349-3 ↗
22. I.Batatia P.Benner Y.Chiang A. M.Elena D. P.Kovács J.Riebesell X. R.Advincula M.Asta M.Avaylon W. J.Baldwin F.Berger N.Bernstein A.Bhowmik S. M.Blau V.Cărare J. P.Darby S.De F. D.Pia V. L.Deringer R.Elijošius Z.El‐Machachi F.Falcioni E.Fako A. C.Ferrari A.Genreith‐Schriever J.George R. E. A.Goodall C. P.Grey P.Grigorev S.Han et al. arXiv2024 https://arxiv.org/abs/2401.00096.
23. 10.1021/acs.jctc.4c0019010.1021/acs.jctc.4c00190 ↗
24. 10.1021/cm702327g10.1021/cm702327g ↗
25. 10.1126/sciadv.160022510.1126/sciadv.1600225 ↗
26. 10.1038/s41578-019-0101-810.1038/s41578-019-0101-8 ↗
27. 10.1038/s41467-019-10030-510.1038/s41467-019-10030-5 ↗
28. 10.1126/science.aaa676010.1126/science.aaa6760 ↗
29. 10.1103/PRXEnergy.3.01100210.1103/PRXEnergy.3.011002 ↗
30. 10.1038/s41578-020-00263-y10.1038/s41578-020-00263-y ↗
31. 10.1038/s41566-021-00950-410.1038/s41566-021-00950-4 ↗
32. 10.1038/s41570-020-00228-310.1038/s41570-020-00228-3 ↗
33. 10.1016/j.jcat.2021.07.01610.1016/j.jcat.2021.07.016 ↗
34. 10.1006/jcat.1999.248410.1006/jcat.1999.2484 ↗
35. 10.1021/acscatal.0c0313710.1021/acscatal.0c03137 ↗
36. 10.1002/anie.20141073810.1002/anie.201410738 ↗
37. 10.1007/s10562-015-1684-310.1007/s10562-015-1684-3 ↗
38. 10.1021/acsenergylett.0c0057610.1021/acsenergylett.0c00576 ↗
39. 10.1126/science.124643210.1126/science.1246432 ↗
40. 10.1021/acs.chemmater.8b0509610.1021/acs.chemmater.8b05096 ↗
41. 10.1002/aenm.20210020410.1002/aenm.202100204 ↗
42. 10.1021/acs.chemmater.6b0144910.1021/acs.chemmater.6b01449 ↗
43. 10.1103/PhysRevB.61.787710.1103/PhysRevB.61.7877 ↗
44. 10.1063/1.499724210.1063/1.4997242 ↗
45. 10.1002/adma.20190276510.1002/adma.201902765 ↗
46. 10.1039/D3TA02088F10.1039/D3TA02088F ↗
47. 10.1002/adts.20190001510.1002/adts.201900015 ↗
48. 10.1107/S160057671900997X10.1107/S160057671900997X ↗
49. 10.1088/1367-2630/18/9/09301110.1088/1367-2630/18/9/093011 ↗
50. 10.1021/acs.chemrev.1c0064410.1021/acs.chemrev.1c00644 ↗
51. 10.1016/j.jallcom.2023.17060110.1016/j.jallcom.2023.170601 ↗
52. 10.1016/j.jpowsour.2004.02.03610.1016/j.jpowsour.2004.02.036 ↗
53. 10.1039/D3DD00121K10.1039/D3DD00121K ↗
54. 10.1162/neco.1997.9.8.173510.1162/neco.1997.9.8.1735 ↗
55. 10.1039/D4FD00063C10.1039/D4FD00063C ↗
56. 10.1021/acs.jcim.9b0047010.1021/acs.jcim.9b00470 ↗
57. 10.1038/s41586-019-1335-810.1038/s41586-019-1335-8 ↗
58. 10.1016/j.matt.2024.05.00210.1016/j.matt.2024.05.002 ↗
59. 10.1039/C9RA07755C10.1039/C9RA07755C ↗
60. 10.1016/j.patrec.2005.10.01010.1016/j.patrec.2005.10.010 ↗
61. 10.1007/s11837-013-0755-410.1007/s11837-013-0755-4 ↗
62. 10.1038/npjcompumats.2015.1010.1038/npjcompumats.2015.10 ↗
63. 10.1038/s41586-023-06734-w10.1038/s41586-023-06734-w ↗
64. 10.1021/acs.chemmater.4c0064310.1021/acs.chemmater.4c00643 ↗
65. 10.1107/S160057672500300010.1107/S1600576725003000 ↗
66. D. E.Widdowson V. A.Kurlin arXiv2024 https://arxiv.org/abs/2410.13796.
67. M.Juelsholt Chemrxiv2025 https://chemrxiv.org/engage/chemrxiv/article‐details/685057d9c1cb1ecda05e9aec.
68. 10.1002/adma.20230708510.1002/adma.202307085 ↗
69. M. H.Petersen R.Zhu H.Dai S.Aggarwal W.Nong A. P.Chen A.Bhowmik J. M.Garcia‐Lastra K.Hippalgaonkar Dis‐CSP: Disordered crystal structure predictions2025 https://openreview.net/forum?id=QAtKMi5epl.
70. C.Hargreaves E.Patyukova D.Antypov Icsdclient: A python interface for the icsd api clients with the requests library https://github.com/lrcfmd/ICSDClient(accessed: April 2025).
71. 10.1088/1361-648X/aa680e10.1088/1361-648X/aa680e ↗
72. 10.1107/S160057671502239610.1107/S1600576715022396 ↗
73. R.Liaw E.Liang R.Nishihara P.Moritz J. E.Gonzalez I.Stoica arXiv2018 https://arxiv.org/abs/1807.05118.