Abstract
Designing and understanding the mechanism of non-stoichiometric materials with enhanced properties is challenging, both experimentally and even computationally, due to the large number of chemical spaces and their distributions through the material. In the current work, it is proposed a Machine Learning approach coupled with the Efficient Global Optimization (EGO) method—an Adaptive Design (AD)—to model local defects in materials from first-principle calculations. Our method takes into account the smallest sample set as possible, envisioning the material defect structure relationship with target properties for new insights. As an example, the AD framework allows us to study the stability and the structure of the modified goethite (Fe0.875Al0.125OOH) by considering a proper defect distribution, from first-principle calculations. The chemical space search for the modified goethite was evaluated by starting from different sizes and configurations of the samples as well as different surrogate models (ANN and Gaussian Process; GP), acquisition functions, and descriptors. Our results show that the same local solution of several defect arrangements in Fe0.875Al0.125OOH is found regardless of the initial sample and regression model. This indicates the efficiency of our search method. We also discuss the role of the descriptors in the accelerated global search for defects in material modeling. We conclude that the AD method applied in material defects is a successful approach in automating the search within huge chemical spaces from first-principle calculations by considering small samples. This method can be applied to mechanistic elucidation of non-stoichiometric materials, solid solutions, alloys, and Schottky and Frenkel defects, essential for material design and discovery.
Similar content being viewed by others
References
Ulissi ZW, Tang MT, Xiao J, Liu X, Torelli DA, Karamad M, Cummins K, Hahn C, Lewis NS, Jaramillo TF, Chan K, Nørskov JK (2017) Machine-learning methods enable exhaustive searches for active bimetallic facets and reveal active site motifs for CO2 reduction. ACS Catal 7(10):6600–6608. https://doi.org/10.1021/acscatal.7b01648
Freeze JG, Kelly HR, Batista VS (2019) Search for catalysts by inverse design: artificial intelligence, mountain climbers, and alchemists. Chem Rev 119(11):6595–6612. https://doi.org/10.1021/acs.chemrev.8b00759
Chang C-K, Kataria S, Kuo C-C, Ganguly A, Wang B-Y, Hwang J-Y, Huang K-J, Yang W-H, Wang S-B, Chuang C-H, Chen M, Huang C-I, Pong W-F, Song K-J, Chang S-J, Guo J-H, Tai Y, Tsujimoto M, Isoda S, Chen C-W, Chen L-C, Chen K-H (2013) Band gap engineering of chemical vapor deposited Graphene by in situ BN doping. ACS Nano 7(2):1333–1341. https://doi.org/10.1021/nn3049158
Balachandran PV, Kowalski B, Sehirlioglu A, Lookman T (2018) Experimental search for high-temperature ferroelectric perovskites guided by two-step machine learning. Nat Commun 9(1):1668. https://doi.org/10.1038/s41467-018-03821-9
Le TC, Winkler DA (2016) Discovery and optimization of materials using evolutionary approaches. Chem Rev 116(10):6107–6132. https://doi.org/10.1021/acs.chemrev.5b00691
Graser J, Kauwe SK, Sparks TD (2018) Machine learning and energy minimization approaches for crystal structure predictions: a review and new horizons. Chem Mater 30(11):3601–3612. https://doi.org/10.1021/acs.chemmater.7b05304
Lookman T, Balachandran PV, Xue D, Yuan R (2019) Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design. npj Computational Materials 5(1):21. https://doi.org/10.1038/s41524-019-0153-8
von Lilienfeld OA (2018) Quantum machine learning in chemical compound space. Angew Chem Int Ed 57(16):4164–4169. https://doi.org/10.1002/anie.201709686
Schmidt J, Marques MRG, Botti S, Marques MAL (2019) Recent advances and applications of machine learning in solid-state materials science. npj Computational Materials 5(1):83. https://doi.org/10.1038/s41524-019-0221-0
Dong Y, Wu C, Zhang C, Liu Y, Cheng J, Lin J (2019) Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride. npj Computational Materials 5(1):26. https://doi.org/10.1038/s41524-019-0165-4
Schmidt J, Shi J, Borlido P, Chen L, Botti S, Marques MAL (2017) Predicting the thermodynamic stability of solids combining density functional theory and machine learning. Chem Mater 29(12):5090–5103. https://doi.org/10.1021/acs.chemmater.7b00156
Zhang Y, Ling C (2018) A strategy to apply machine learning to small datasets in materials science. npj Computational Materials 4(1):25. https://doi.org/10.1038/s41524-018-0081-z
Himanen L, Geurts A, Foster AS, Rinke P Data-driven materials science: status, challenges, and perspectives. Adv Sci 6:1900808. https://doi.org/10.1002/advs.201900808
Schroff F, Kalenichenko D, Philbin J FaceNet: a unified embedding for face recognition and clustering. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7–12 June 2015 2015. pp 815–823. doi: https://doi.org/10.1109/CVPR.2015.7298682
Weyand T, Kostrikov I, Philbin J (2016) PlaNet - photo geolocation with convolutional neural networks. arXiv e-prints
Silver D, Huang A, Maddison CJ, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529:484. https://doi.org/10.1038/nature16961 https://www.nature.com/articles/nature16961#supplementary-information
Dehghannasiri R, Xue D, Balachandran PV, Yousefi MR, Dalton LA, Lookman T, Dougherty ER (2017) Optimal experimental design for materials discovery. Comput Mater Sci 129:311–322. https://doi.org/10.1016/j.commatsci.2016.11.041
Janet JP, Liu F, Nandy A, Duan C, Yang T, Lin S, Kulik HJ (2019) Designing in the face of uncertainty: exploiting electronic structure and machine learning models for discovery in inorganic chemistry. Inorg Chem. https://doi.org/10.1021/acs.inorgchem.9b00109
Chen X, Jørgensen MS, Li J, Hammer B (2018) Atomic energies from a convolutional neural network. J Chem Theory Comput 14(7):3933–3942. https://doi.org/10.1021/acs.jctc.8b00149
Vamathevan J, Clark D, Czodrowski P, Dunham I, Ferran E, Lee G, Li B, Madabhushi A, Shah P, Spitzer M, Zhao S (2019) Applications of machine learning in drug discovery and development. Nat Rev Drug Discov. https://doi.org/10.1038/s41573-019-0024-5
Moriwaki H, Tian Y-S, Kawashita N, Takagi T (2018) Mordred: a molecular descriptor calculator. J Cheminform 10(1):4. https://doi.org/10.1186/s13321-018-0258-y
Balachandran PV (2019) Machine learning guided design of functional materials with targeted properties. Comput Mater Sci 164:82–90. https://doi.org/10.1016/j.commatsci.2019.03.057
Singh AR, Rohr BA, Gauthier JA, Nørskov JK (2019) Predicting chemical reaction barriers with a machine learning model. Catal Lett 149(9):2347–2354. https://doi.org/10.1007/s10562-019-02705-x
Ulissi ZW, Medford AJ, Bligaard T, Nørskov JK (2017) To address surface reaction network complexity using scaling relations machine learning and DFT calculations. Nat Commun 8(1):14621. https://doi.org/10.1038/ncomms14621
Todorović M, Gutmann MU, Corander J, Rinke P (2019) Bayesian inference of atomistic structure in functional materials. npj Computational Materials 5(1):35. https://doi.org/10.1038/s41524-019-0175-2
Zarzycki P, Rosso KM (2019) Energetics and the role of defects in Fe(II)-catalyzed goethite recrystallization from molecular simulations. ACS Earth Space Chem 3(2):262–272. https://doi.org/10.1021/acsearthspacechem.8b00175
Gualtieri AF, Venturelli P (1999) In situ study of the goethite-hematite phase transformation by real time synchrotron powder diffraction. Am Mineral 84(5–6):895–904. https://doi.org/10.2138/am-1999-5-624
Spathariotis E, Kallianou C (2007) Adsorption of copper, zinc, and cadmium on goethite, aluminum-substituted goethite, and a system of kaolinite–goethite: surface complexation modeling. Commun Soil Sci Plant Anal 38(5–6):611–635. https://doi.org/10.1080/00103620701216005
Liu H, Chen T, Frost R (2013) An overview of the role of goethite surfaces in the environment. Chemosphere 103. https://doi.org/10.1016/j.chemosphere.2013.11.065
Jäger MOJ, Morooka EV, Federici Canova F, Himanen L, Foster AS (2018) Machine learning hydrogen adsorption on nanoclusters through structural descriptors. npj Computational Materials 4(1):37. https://doi.org/10.1038/s41524-018-0096-5
Kresse G, Furthmüller J (1996) Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput Mater Sci 6(1):15–50. https://doi.org/10.1016/0927-0256(96)00008-0
Kresse G, Hafner J (1993) Ab initio molecular dynamics for liquid metals. Phys Rev B 47(1):558–561. https://doi.org/10.1103/PhysRevB.47.558
Kresse G, Hafner J (1994) Ab initio molecular-dynamics simulation of the liquid-metal--amorphous-semiconductor transition in germanium. Phys Rev B 49(20):14251–14269. https://doi.org/10.1103/PhysRevB.49.14251
Perdew JP, Burke K, Ernzerhof M (1996) Generalized gradient approximation made simple. Phys Rev Lett 77(18):3865–3868. https://doi.org/10.1103/PhysRevLett.77.3865
Blöchl PE (1994) Projector augmented-wave method. Phys Rev B 50(24):17953–17979. https://doi.org/10.1103/PhysRevB.50.17953
Dudarev SL, Botton GA, Savrasov SY, Humphreys CJ, Sutton AP (1998) Electron-energy-loss spectra and the structural stability of nickel oxide: an LSDA+U study. Phys Rev B 57(3):1505–1509. https://doi.org/10.1103/PhysRevB.57.1505
Monkhorst HJ, Pack JD (1976) Special points for Brillouin-zone integrations. Phys Rev B 13(12):5188–5192. https://doi.org/10.1103/PhysRevB.13.5188
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, Louppe G (2012) Scikit-learn: machine learning in python. J Mach Learn Res 12
Gopakumar AM, Balachandran PV, Xue D, Gubernatis JE, Lookman T (2018) Multi-objective optimization for materials discovery via adaptive design. Sci Rep 8(1):3738. https://doi.org/10.1038/s41598-018-21936-3
Abraham A, Pedregosa F, Eickenberg M, Gervais P, Mueller A, Kossaifi J, Gramfort A, Thirion B, Varoquaux G (2014) Machine learning for neuroimaging with scikit-learn. Front Neuroinform 8(14). https://doi.org/10.3389/fninf.2014.00014
Wu S, Chang C-M, Mai G-S, Rubenstein DR, Yang C-M, Huang Y-T, Lin H-H, Shih L-C, Chen S-W, Shen S-F (2019) Artificial intelligence reveals environmental constraints on colour diversity in insects. Nat Commun 10(1):4554. https://doi.org/10.1038/s41467-019-12500-2
Simm GN, Reiher M (2018) Error-controlled exploration of chemical reaction networks with Gaussian processes. J Chem Theory Comput 14(10):5238–5248. https://doi.org/10.1021/acs.jctc.8b00504
Rouet-Leduc B, Hulbert C, Barros K, Lookman T, Humphreys CJ (2017) Automatized convergence of optoelectronic simulations using active machine learning. Appl Phys Lett 111(4):043506. https://doi.org/10.1063/1.4996233
Springenberg JT, Klein A, Falkner S, Hutter F (2016) Bayesian optimization with robust Bayesian neural networks. Paper presented at the Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain,
Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. Paper presented at the Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2, Montreal, Quebec, Canada,
Brochu E, Cora V. M, De Freitas N (2010) A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning, vol abs/1012.2599
Jones DR, Schonlau M, Welch WJ (1998) Efficient global optimization of expensive black-box functions. J Glob Optim 13(4):455–492. https://doi.org/10.1023/A:1008306431147
Viana FAC, Haftka RT, Watson LT (2013) Efficient global optimization algorithm assisted by multiple surrogate techniques. J Glob Optim 56(2):669–689. https://doi.org/10.1007/s10898-012-9892-5
Mockus J, Tiesis V, Zilinskas A (2014) The application of Bayesian methods for seeking the extremum. In, vol 2. pp 117–129
Fukazawa T, Harashima Y, Hou Z, Miyake T (2019) Bayesian optimization of chemical composition: a comprehensive framework and its application to RFe12 -type magnet compounds, vol 3. doi:https://doi.org/10.1103/PhysRevMaterials.3.053807
Liu Y, Zhao T, Ju W, Shi S (2017) Materials discovery and design using machine learning. J Mater 3(3):159–177. https://doi.org/10.1016/j.jmat.2017.08.002
Jørgensen MS, Larsen UF, Jacobsen KW, Hammer B (2018) Exploration versus exploitation in global atomistic structure optimization. J Phys Chem A 122(5):1504–1509. https://doi.org/10.1021/acs.jpca.8b00160
Ryan K, Lengyel J, Shatruk M (2018) Crystal structure prediction via deep learning. J Am Chem Soc 140(32):10158–10168. https://doi.org/10.1021/jacs.8b03913
Lookman T, Balachandran PV, Xue D, Hogden J, Theiler J (2017) Statistical inference and adaptive design for materials discovery. Curr Opinion Solid State Mater Sci 21(3):121–128. https://doi.org/10.1016/j.cossms.2016.10.002
Himanen L, Jäger MOJ, Morooka EV, Federici Canova F, Ranawat YS, Gao DZ, Rinke P, Foster AS (2020) DScribe: library of descriptors for machine learning in materials science. Comput Phys Commun 247:106949. https://doi.org/10.1016/j.cpc.2019.106949
Papalambros PY (2002) The optimization paradigm in engineering design: promises and challenges. Comput Aided Des 34(12):939–951. https://doi.org/10.1016/S0010-4485(01)00148-8
Balachandran PV, Xue D, Theiler J, Hogden J, Gubernatis JE, Lookman T (2018) Importance of feature selection in machine learning and adaptive design for materials. In: Lookman T, Eidenbenz S, Alexander F, Barnes C (eds) Materials discovery and design: by means of data science and optimal learning. Springer International Publishing, Cham, pp 59–79. https://doi.org/10.1007/978-3-319-99465-9_3
Bisbo MK, Hammer B (2020) Efficient global structure optimization with a machine-learned surrogate model. Phys Rev Lett 124(8):086102. https://doi.org/10.1103/PhysRevLett.124.086102
Acknowledgements
The support of the Brazilian agencies: Fundação de Amparo à Pesquisa do Espírito Santo (FAPES)—project CNPq/FAPES PPP 22/2018, Conselho Nacional para o Desenvolvimento Científico e Tecnológico (CNPq), and Coordenação de Aperfeiçoamento de Pessoal de Ensino Superior (CAPES) are gratefully acknowledged. Also, we acknowledge the Computational resources provided by the Centro Nacional de Processamento de Alto Desempenho em São Paulo (CENAPAD-SP) and by the Bremen Center for Computational Material Science (BCCMS). Financial support from the DFG grant Nr. DE1158/8-1, the Research Training Group grant DFG-RTG2247, and the Max-Planck-Institute for Structure and Dynamics of Matter (MPSD) are gratefully acknowledged by the author M. C. da Silva.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interest
The authors declare that they have no competing interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This paper belongs to Topical Collection XX - Brazilian Symposium of Theoretical Chemistry (SBQT2019)
Electronic supplementary material
ESM 1
In the Support Information (SI), the following can be found: (1) Density of States of the pure and modified goethite; (2) a brief discussion about statistical regression as used in the current Adaptive Design approach; (3) the Expected Improvement (EI) plot (in 3D) as a function of (μ − fmax) and σ(x); and (4) additional results of the stability and structure of the modified goethite. (PDF 1.26 MB)
Rights and permissions
About this article
Cite this article
Lourenço, M.P., dos Santos Anastácio, A., Rosa, A.L. et al. An adaptive design approach for defects distribution modeling in materials from first-principle calculations. J Mol Model 26, 187 (2020). https://doi.org/10.1007/s00894-020-04438-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00894-020-04438-w