Using support vector machine for materials design

Abstract

Materials design is the most important and fundamental work on the background of materials genome initiative for global competitiveness proposed by the National Science and Technology Council of America. As far as the methodologies of materials design, besides the thermodynamic and kinetic methods combing databases, both deductive approaches so-called the first principle methods and inductive approaches based on data mining methods are gaining great progress because of their successful applications in materials design. In this paper, support vector machine (SVM), including support vector classification (SVC) and support vector regression (SVR) based on the statistical learning theory (SLT) proposed by Vapnik, is introduced as a relatively new data mining method to meet the different tasks of materials design in our lab. The advantage of using SVM for materials design is discussed based on the applications in the formability of perovskite or BaNiO₃ structure, the prediction of energy gaps of binary compounds, the prediction of sintered cold modulus of sialon-corundum castable, the optimization of electric resistances of VPTC semiconductors and the thickness control of In₂O₃ semiconductor film preparation. The results presented indicate that SVM is an effective modeling tool for the small sizes of sample sets with great potential applications in materials design.

Keywords

Support vector machine / Materials genome initiative / Materials design / Data mining / Quantitative structure–property relationship / Materials exploration and optimization

References

[1] National Science and technology Coucil (2011) Materials genome initiative for global competitiveness, Washington DC, America, June 24, 2011

[2] Choi YM, Lin MC, Liu ML. Rational design of novel cathode materials in solid oxide fuel cells using first-principles simulations. J Power Sources, 2010, 195(5): 1441-1445.

[3] Ceder G. Opportunities and challenges for first-principles materials design and applications to Li battery materials. MRS Bull, 2010, 35(9): 693-701.

[4] Curtarolo S, Hart GLW, Nardelli MB, Mingo N, Sanvito S, Levy O. The high-throughput highway to computational materials design. Nat Mater, 2013, 12(3): 191-201.

[5] Kong CS, Rajan K. Rational design of binary halide scintillators via data mining. Nucl Instrum Methods Phys Res A, 2012, 680(1): 145-154.

[6] Suh C, Kim K, Berry JJ, Lee J, Jones WB. Data mining-aided crystal engineering for the design of transparent conducting oxides materials research society fall meeting, 2010, Cambridge: Cambridge University Press

[7] Liu X, Lu WC, Peng CR, Su Q. Guo. J., Two semi-empirical approaches for the prediction of oxide ionic conductivities in ABO₃ perovskites. Comp Mater Sci, 2009, 46(4): 860-868.

[8] Gu TH, Lv W, Shao X, Lu WC. Detection of high energy materials using support vector classification. Adv Mater Res, 2012, 556: 554-1631.

[9] Wu ML, Zhang LM, Gu TH, Qian N, Ma WJ, Lu WC. Shape-controlled synthesis and pattern recognition of dendritic Co3O4 superstructures. Adv Mater Res, 2013, 654: 652-355.

[10] Liu HL, Guo J, Chen NY. A PLS-BPN pattern recognition method applied to computer-aided materials design. Anal Lett, 1996, 29(2): 341-350.

[11] Chen NY, Li CH, Qin P. KDPAG expert system applied to materials design and manufacture. Eng Appl Artif Intell, 1998, 11(5): 669-674.

[12] Patterson DW. Artificial neural networks: theory and applications, 1996, New Jersey: Prentice Hall.

[13] Wold S, Sjostroma M, Eriksson L. PLS-regression: a basic tool of chemometrics. Chemometr Intell Lab, 2001, 58(2): 109-130.

[14] Vapnik VN. Statistical learning theory, 1998, New York: Wiley.

[15] Burbidge R, Trotter M, Buxton B, Holden S. Drug design by machine learning: support vector machines for pharmaceutical data analysis. J Comput Chem, 2001, 26(1): 5-14.

[16] Lu WC, Dong N, Nάray-Szabό G. Predicting anti-HIV-1 activities of HEPT-analog compounds by using support vector classification. QSAR Comb Sci, 2005, 24(9): 1021-1025.

[17] Li J, Qi M, Kong J, Wang J, Yan Y, Huo W, Yu J, Xu R, Xu Y. Computational prediction of the formation of microporous aluminophosphates with desired structural features. Micropor Mesopor Mat, 2010, 129(1–2): 251-255.

[18] Yan Q. Prediction of porosity of porous NiTi alloy from processing parameters based on SVR. Adv Mater Res, 2012, 395: 393-235.

[19] Liu X, Lu WC, Jin SL, Li YW, Chen NY. Support vector regression applied to materials optimization of sialon ceramics. Chemometr Intell Lab, 2006, 82(1–2): 8-14.

[20] Chen NY, Lu WC, Yang J, Li GZ. Support vector machine in chemistry, 2004, Singapore: World Scientific Publishing Company.

[21] Niu B, Lu WC, Yang SS, Cai YD, Li GZ. Support vector machine for SAR/QSAR of phenethyl-amines. Acta Pharmacol Sin, 2007, 28(7): 1075-1086.

[22] Zhu JX, Lu WC, Liu L, Gu TH, Niu B. Classification of Src kinase inhibitors based on support vector machine. QSAR Comb Sci, 2009, 28(6–7): 719-727.

[23] Yang SS, Lu WC, Gu TH, Yan LM, Li GZ. QSPR study of n-octanol/water partition coefficient of some aromatic compounds using support vector regression. QSAR Comb Sci, 2009, 28(2): 175-182.

[24] Liu X, Chen HC, Liu TA, Li YL, Lu ZR, Lu WC. Application of PCA-SVR to NIR prediction model for tobacco chemical composition. Spectrosc Spect Anal, 2007, 27(12): 2460-2463.

[25] Gu TH, Lu WC, Bao XH, Chen NY. Using support vector regression for the prediction of the band gap and melting point of binary and ternary compound semiconductors. Solid State Sci, 2006, 8(2): 129-136.

[26] Galasso FS. Perovskites and high Tc superconductors, 1990, New York: Wiley

[27] Liu L, Lu WC, Chen NY. On the criteria of formation and lattice distortion of perovskite-type complex halides. J Phys Chem Solids, 2004, 65(5): 855-860.

[28] Müller O, Roy R. The major ternary structural families, 1974, Berlin: Springer

[29] Madelung O. Semiconductors—basic data, 1996, Berlin: Springer.

[30] Boca R. Semiconductors Materials, 1997, New York: CRC Press

[31] Chen NY. Application of bond parameter function, 1976, Beijing: Press of Science

[32] MacKenzie KJD, Temuujin J, Smith ME, Okada K, Kameshima Y. Mechanochemical processing of sialon compositions. J Eur Ceram Soc, 2003, 23(7): 1069-1082.

[33] Kudyba-Jansen AA, Hintzen HT, Metselaar R. The influence of green processing on the sintering and mechanical properties of β-sialon. J Eur Ceram Soc, 2001, 21(12): 2153-2160.

[34] Li YW, Zhang X, Jin SL (2001) Corundum castables containing nitrogen for purging plug in Ladle. In: Proceedings of 44th international colloquium on refractories, pp 26–27, Aachen, Germany

[35] Bao XH, Pan QY, Chen NY. Support vector regression model for controlling the thickness of semiconductor In₂O₃ film. Comput Appl Chem, 2002, 19(6): 733-736.