Abstract
A brief overview of the problems is given in the field of inorganic chemistry and materials science, solved using machine learning (ML). The main ML methods limitations and the subject area peculiarities are considered that must be taken into account when using ML. Solved problems examples of new inorganic compounds design and the results of comparing predictions with new experimental data are given. Systems developed by the authors are considered that aimed at not yet obtained inorganic compounds design, based on ML methods, as well as promising directions for such systems development in order to improve the predictions accuracy for new substances and their corresponding properties values estimations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Savitskii, E.M., Devingtal’, Yu.V., Gribulya, V.B.: Prediction of metallic compounds with composition A3B using computer. Dokl. Akad. Nauk SSSR 183, 1110–1112 (1968). (in Russ.)
Kiselyova, N.N., Pokrovskii, B.I., Komissarova, L.N., Vaschenko, N.D.: Simulation of the complicated oxides formation from initial components based on the cybernetic method of concept formation. Russ. J. Inorg. Chem. 22, 883–886 (1977). (in Russ.)
Kiselyova, N.N., Dudarev, V.A., Stolyarenko, A.V.: Integrated system of databases on the properties of inorganic substances and materials. High Temp. 54, 215–222 (2016). https://doi.org/10.1134/S0018151X16020085
Kiselyova, N.N., Stolyarenko, A.V., Ryazanov, V.V., Sen’ko, O.V., Dokukin, A.A., Podbel’skii, V.V.: A system for computer-assisted design of inorganic compounds based on computer training. Pattern Recognit. Image Anal. 21, 88–94 (2011). https://doi.org/10.1134/S1054661811010081
Dudarev, V.A., et al.: An information system for inorganic substances physical properties prediction based on machine learning methods. In: CEUR Workshop Proceedings (CEUR-WS.org), vol. 2790. Supplementary Proceedings of the XXII International Conference on Data Analytics and Management in Data Intensive Domains (DAMDID/RCDL 2020), pp. 89–102 (2020). http://ceur-ws.org/Vol-2790/paper09.pdf
Site of Materials Genome Initiative. https://www.mgi.gov/. Accessed 30 Mar 2021
Site of Novel Materials Discovery Laboratory. http://nomad-lab.eu/. Accessed 30 Mar 2021
Site of Center for Materials Research by Information Integration. http://www.nims.go.jp/eng/research/MII-I/index.html. Accessed 30 Mar 2021
Site of scikit. http://scikit-learn.org/. Accessed 30 Mar 2021
Site of R. https://www.r-project.org/. Accessed 30 Mar 2021
Devingtal’, Yu.V.: Coding of objects at application of separating hyper-plane for their classification. Izv. Akad. Nauk SSSR. Tekhn. Kibernetika. 139–147 (1971). (in Russ.)
Seko, A., Hayashi. H., Tanaka, I.: Compositional descriptor-based recommender system for the materials discovery. J. Chem. Phys. 148, 241719/1-7 (2018). https://doi.org/10.1063/1.5016210
Gladun, V.P.: Heuristic Search in Complex Environments. Naukova Dumka, Kiev (1977).(in Russ.)
Liu, C.-H., Tao, Y., Hsu, D., Du, Q., Billinge, S.J.L.: Using a machine learning approach to determine the space group of a structure from the atomic pair distribution function. Acta Crystallogr. A 75, 633–643 (2019). https://doi.org/10.1107/S2053273319005606
Xie, S.R., Kotlarz, P., Hennig, R.G., Nino, J.C.: Machine learning of octahedral tilting in oxide perovskites by symbolic classification with compressed sensing. Comp. Mater. Sci. 180, 109690/1-9 (2020). https://doi.org/10.1016/j.commatsci.2020.109690
Senko, O.V.: An optimal ensemble of predictors in convex correcting procedures. Pattern Recognit Image Anal. 19, 465–468 (2009). https://doi.org/10.1134/S1054661809030110
Yuan, G.-X., Ho, C.-H., Lin, C.-J.: An improved GLMNET for L1-regularized logistic regression. J. Mach. Learn. Res. 13, 1999–2030 (2012)
Yang, Y., Zou, H.A.: Coordinate majorization descent algorithm for L1 penalized learning. J. Stat. Comput. Simul. 2014(84), 1–12 (2014). https://doi.org/10.1080/00949655.2012.695374
Ozhereliev, I.S., Senko, O.V., Kiselyova, N.N.: Method for searching outlier objects using parameters of learning instability. Sist. Sredstva inform. – Syst. Means Inform. 29, 122–134 (2019). https://doi.org/10.14357/08696527190211. (inRuss.)
Dineev, V.D., Dudarev, V.A.: Extendable system for multicriterial outlier detection. In: CEUR Workshop Proceedings (CEUR-WS.org), vol. 2790. Supplementary Proceedings of the XXII International Conference on Data Analytics and Management in Data Intensive Domains (DAMDID/RCDL 2020), pp. 103–113 (2020). http://ceur-ws.org/Vol-2790/paper10.pdf. (in Russ.)
Senko, O.V., Dokukin, A.A., Kiselyova, N.N., Khomutov, N.: Two-stage method for constructing linear regressions using optimal convex combinations. Dokl. Math. 97, 113–114 (2018). https://doi.org/10.1134/S1064562418020035
Kiselyova, N.N., Dudarev, V.A., Ryazanov, V.V., Sen’ko, O.V., Dokukin, A.A.: Predictions of chalcospinels with composition ABCX4 (X – S or Se). Inorg. Mater.: Appl. Res. 12, 328–336 (2021). https://doi.org/10.1134/S2075113321020246
Vasala, S., Karppinen, M.: A2B’B’’O6 perovskites: a review. Progr. Solid State Chem. 43, 1–36 (2015). https://doi.org/10.1016/j.progsolidstchem.2014.08.001
Awasthi, S.K., Chackraburtty, D.M., Tondon, V.K.: Studies on A2BB′O6 type compounds of actinides: Plutonium compounds. J. Inorg. Nucl. Chem. 30, 819–821 (1968). https://doi.org/10.1016/0022-1902(68)80442-7
Landolt-Bornstein. Zahlenwerte und Funktionen aus Naturwissenschaften und Technik. Neue Serie. Gr.III: Kristal- und Festkorperphysik. B.7. Kristallstrukturdaten anorganischer Verbindungen. T.e: Schlusselemente: d9-, d10-, d1...d3-, f-Elemente. Springer, Berlin, Heidelberg, New York (1976)
Sleight, A.W., Ward, R.: Compounds of hexavalent and pentavalent uranium with the ordered perovskite structure. Inorg. Chem. 1, 790–793 (1962). https://doi.org/10.1021/ic50004a015
Torshin, I.Yu, Rudakov, K.V.: Topological data analysis in materials science: the case of high-temperature cuprate superconductors. Pattern Recognit. Image Anal. 30, 264–276 (2020). https://doi.org/10.1134/S1054661820020157
Kauwe, S.K., Graser, J., Vazquez, A., Sparks, T.D.: Machine learning prediction of heat capacity for solid inorganics. Integr. Mater. Manuf. Innov. 7(2), 43–51 (2018). https://doi.org/10.1007/s40192-018-0108-9
Seko, A., Hayashi, H., Nakayama, K., Takahashi, A., Tanaka, I.: Representation of compounds for machine-learning prediction of physical properties. Phys. Rev. B99, 144110/1-11 (2017). https://doi.org/10.1103/PhysRevB.95.144110
Lee, J., Seko, A., Shitara, K., Tanaka, I.: Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques. Phys. Rev. B93, 115104/1-12 (2016). https://doi.org/10.1103/PhysRevB.93.115104
Chen, Y., et al.: Machine learning assisted multi-objective optimization for materials processing parameters: a case study in Mg alloy. J. Alloys Compounds. 844, 156159/1-7 (2020). https://doi.org/10.1016/j.jallcom.2020.156159
Abueidda, D.W., Koric, S., Sobh, N.A., Sehitoglu, H.: Deep learning for plasticity and thermo-viscoplasticity. Int. J. Plasticity. 136, 102852/1-30 (2021). https://doi.org/10.1016/j.ijplas.2020.102852
Dang, Y., Liu, L., Li, Z.: Optimization of the controlling recipe in quasi-single crystalline silicon growth using artificial neural network and genetic algorithm. J. Crystal Growth. 522, 195–203 (2019). https://doi.org/10.1016/j.jcrysgro.2019.06.033
Parwaiz, S., Malik, O.A., Pradhan, D., Khan, M.M.: Machine learning-based cyclic voltammetry behavior model for supercapacitance of co-doped Ceria/rGO nanocomposite. J. Chem. Inf. Model. 58, 2517–2527 (2018). https://doi.org/10.1021/acs.jcim.8b00612
Yaseen, Z.M., et al.: Predicting compressive strength of lightweight foamed concrete using extreme learning machine model. Adv. Eng. Software. 115, 112–125 (2018). https://doi.org/10.1016/j.advengsoft.2017.09.004
Kautz, E.J., Hagen, A.R., Johns, J.M., Burkes, D.E.: A machine learning approach to thermal conductivity modeling: a case study on irradiated uranium-molybdenum nuclear fuels. Comp. Mater. Sci. 161, 107–118 (2019). https://doi.org/10.1016/j.commatsci.2019.01.044
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015). https://doi.org/10.1016/j.neunet.2014.09.003
Acknowledgements
The authors are grateful to V.V. Ryazanov, O. V. Sen’ko, A.A. Dokukin, V.S. Pereverzev-Orlov, M.A. Vitushko, and E.A. Vaschenko for their help in developing algorithms and programs. This work was supported in part by the Russian Foundation for Basic Research, project nos. 20-01-00609 and 18-07-00080. The study was carried out as part of the state assignment (project no. № 075-00328-21-00).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Kiselyova, N., Dudarev, V., Stolyarenko, A. (2022). Machine Learning Application to Predict New Inorganic Compounds – Results and Perspectives. In: Pozanenko, A., Stupnikov, S., Thalheim, B., Mendez, E., Kiselyova, N. (eds) Data Analytics and Management in Data Intensive Domains. DAMDID/RCDL 2021. Communications in Computer and Information Science, vol 1620. Springer, Cham. https://doi.org/10.1007/978-3-031-12285-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-12285-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12284-2
Online ISBN: 978-3-031-12285-9
eBook Packages: Computer ScienceComputer Science (R0)