AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Materiomics Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Machine learning approaches for permittivity prediction and rational design of microwave dielectric ceramics

Jincheng Qina,b, Zhifu Liua( ), Mingsheng Maa, Yongxiang Lia( )
CAS Key Laboratory of Inorganic Functional Materials and Devices, Shanghai Institute of Ceramics, Chinese Academy of Sciences, Shanghai, 201899, China
Center of Materials Sciences and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing, 100049, China

Peer review under responsibility of The Chinese Ceramic Society.

Show Author Information

Graphical Abstract

· A permittivity prediction model for MWDCs was first established via machine learning based on measured permittivity.

Abstract

Low permittivity microwave dielectric ceramics (MWDCs) are attracting great interest because of their promising applications in the new era of 5G and IoT. Although theoretical rules and computational methods are of practical use for permittivity prediction, unsatisfactory predictability and universality impede rational design of new high-performance materials. In this work, based on a dataset of 254 single-phase microwave dielectric ceramics (MWDCs), machine learning (ML) methods established a high accuracy model for permittivity prediction and gave insights of quantitative chemistry/structure-property relationships. We employed five commonly-used algorithms, and introduced 32 intrinsic chemical, structural and thermodynamic features which have correlations with permittivity for modeling. Machine learning results help identify the permittivity decisive factors, including polarizability per unit volume, average bond length, and average cell volume per atom. The feature-property relationships were discussed. The optimal model constructed by support vector regression with radial basis function kernel was validated its superior predictability and generalization by verification dataset. Low permittivity material systems were screened from a dataset of ~3300 materials without reported microwave permittivity by high-throughput prediction using optimal model. Several predicted low permittivity ceramics were synthesized, and the experimental results agree well with ML prediction, which confirmed the reliability of the prediction model.

Keywords

Microwave dielectric ceramicsLow permittivity ceramicsPermittivity predictionMachine learningQuantitative structure-property relationship

References

[1]

Sebastian MT, Ubic R, Jantunen H. Low-loss dielectric ceramic materials and their properties. Int Mater Rev 2015;60(7): 392-412.
Crossref Google Scholar
[2]

Ohsato H, Tsunooka T, Kan A, Ohishi Y, Miyauchi Y, Tohdo Y, Okawa T, Kakimoto K, Ogawa H. Microwave-millimeterwave dielectric materials. Key Eng Mater 2004;269: 195-8.
Crossref Google Scholar
[3]

Reaney I, Iddles D. Microwave dielectric ceramics for resonators and filters in mobile phone networks. J Am Ceram Soc 2006;89(7): 2063-72.
Crossref Google Scholar
[4]

Zhou D, Pang L-X, Wang D-W, Li C, Jin B-B, Reaney IM. High permittivity and low loss microwave dielectrics suitable for 5G resonators and low temperature co-fired ceramic architecture. J Mater Chem C 2017;5(38): 10094-8.
Crossref Google Scholar
[5]

Ohsato H, Tsunooka T, Sugiyama T, Kakimoto K-i, Ogawa H. Forsterite ceramics for millimeterwave dielectrics. J Electroceram 2006;17(2–4): 445-50.
Crossref Google Scholar
[6]

Ohsato H, Varghese J, Vahera T, Kim JS, Sebastian MT, Jantunen H, Iwata M. Micro/Millimeter-wave dielectric indialite/cordierite glass-ceramics applied as LTCC and direct casting substrates: current status and prospects. J Korean Ceram Soc 2019;56(6): 526-33.
Crossref Google Scholar
[7]

Szwagierczak D, Synkiewicz-Musialska B, Kulawik J, Czerwińska E, Pałka N, Bajurko PR. Low temperature sintering of Zn4B6O13 based substrates, their microstructure and dielectric properties up to the THz range. J Alloys Compd 2020;819: 153025.
Crossref Google Scholar
[8]

Onsager L. Electric moments of molecules in liquids. J Am Chem Soc 1936;58(8): 1486-93.
Crossref Google Scholar
[9]

Kirkwood JG. On the theory of dielectric polarization. J Chem Phys 1936;4(9): 592-601.
Crossref Google Scholar
[10]

Fröhlich H. General theory of the static dielectric constant. Trans Faraday Soc 1948;44: 238-43.
Crossref Google Scholar
[11]

Penn DR. Wave-number-dependent dielectric function of semiconductors. Phys Rev 1962;128(5): 2093-7.
Crossref Google Scholar
[12]

Ravindra NM, Auluck S, Srivastava VK. On the penn gap in semiconductors. Phys Status Solidi B 1979;93(2): K155-60.
Crossref Google Scholar
[13]

Gladstone JH, Dale TP. XIV. Researches on the refraction, dispersion, and sensitiveness of liquids. Phil Trans Roy Soc Lond 1863;153: 317-43.
Crossref Google Scholar
[14]

Wu Z, Zhang S. Semiempirical method for the evaluation of bond covalency in complex crystals. J Phys Chem A 1999;103(21): 4270-4.
Crossref Google Scholar
[15]

Yang H, Zhang S, Yang H, Yuan Y, Li E. Intrinsic dielectric properties of columbite ZnNb2O6 ceramics studied by P-V-L bond theory and Infrared spectroscopy. J Am Ceram Soc 2019;102(9): 5365-74.
Crossref Google Scholar
[16]

Liu D, Zhang S, Wu Z. Lattice energy estimation for inorganic ionic crystals. Inorg Chem 2003;42(7): 2465-9.
Crossref Google Scholar
[17]

Fan X, Chen X, Liu X. Structural dependence of microwave dielectric properties of SrRAlO4 (R= Sm, Nd, La) ceramics: crystal structure refinement and infrared reflectivity study. Chem Mater 2008;20(12): 4092-8.
Crossref Google Scholar
[18]

Lufaso MW. Crystal structures, modeling, and dielectric property relationships of 2: 1 ordered Ba3MM‘2O9 (M = Mg, Ni, Zn; M‘ = Nb, Ta) perovskites. Chem Mater 2004;16(11): 2148-56.
Crossref Google Scholar
[19]

Wu S, Song K, Liu P, Lin H, Zhang F, Zheng P, Qin H, Alford N. Effect of TiO2 doping on the structure and microwave dielectric properties of cordierite ceramics. J Am Ceram Soc 2015;98(6): 1842-7.
Crossref Google Scholar
[20]

Kim ES, Chun BS, Freer R, Cernik RJ. Effects of packing fraction and bond valence on microwave dielectric properties of A2+B6+O4 (A2+: Ca, Pb, Ba; B6+: Mo, W) ceramics. J Eur Ceram Soc 2010;30(7): 1731-6.
Crossref Google Scholar
[21]

Takahashi H, Baba Y, Ezaki K, Okamoto Y, Nakano S. Dielectric characteristics of (A1/21+●A1/23+)TiO3 ceramics at microwave frequencies. Jpn J Appl Phys 1991;30(9B): 2339-42.
Crossref Google Scholar
[22]

Abdul Khalam L, Sreemoolanathan H, Ratheesh R, Mohanan P, Sebastian MT. Preparation, characterization and microwave dielectric properties of Ba(B′1/2Nb1/2)O3 [B′ = La, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Y, Yb and In] ceramics. Mater Sci Eng B 2004;107(3): 264-70.
Crossref Google Scholar
[23]

Guo J, Zhou D, Li Y, Shao T, Qi ZM, Jin BB, Wang H. Structure-property relationships of novel microwave dielectric ceramics with low sintering temperatures: (Na0.5xBi0.5xCa1-x)MoO4. Dalton Trans 2014;43(31): 11888-96.
Crossref Google Scholar
[24]

Kamba S, Samoukhina P, Kadlec F, Pokorný J, Petzelt J, Reaney IM, Wise PL. Composition dependence of the lattice vibrations in Srn+1TinO3n+1 Ruddlesden–Popper homologous series. J Eur Ceram Soc 2003;23(14): 2639-45.
Crossref Google Scholar
[25]

Levine BF. Bond susceptibilities and ionicities in complex crystal structures. J Chem Phys 1973;59(3): 1463-86.
Crossref Google Scholar
[26]

Song XQ, Xie MQ, Du K, Lu WZ, Lei W. Synthesis, crystal structure and microwave dielectric properties of self-temperature stable Ba1-xSrxCuSi2O6 ceramics for millimeter-wave communication. J. Materiomics 2019;5(4): 606-17.
Crossref Google Scholar
[27]

Agrawal A, Choudhary A. Perspective: materials informatics and big data: realization of the “fourth paradigm” of science in materials science. Apl Mater 2016;4(5): 053208.
Crossref Google Scholar
[28]

Lookman T, Balachandran PV, Xue D, Yuan R. Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design. npj Comput Mater 2019;5(1).
Crossref Google Scholar
[29]

Liu Y, Zhao T, Ju W, Shi S. Materials discovery and design using machine learning. J. Materiomics 2017;3(3): 159-77.
Crossref Google Scholar
[30]

Rajan K. Materials informatics: the materials “gene” and big data. Annu Rev Mater Res 2015;45(1): 153-69.
Crossref Google Scholar
[31]

Kim C, Pilania G, Ramprasad R. Machine learning assisted predictions of intrinsic dielectric breakdown strength of ABX3 perovskites. J Phys Chem C 2016;120(27): 14575-80.
Crossref Google Scholar
[32]

Kim C, Pilania G, Ramprasad R. From organized high-throughput data to phenomenological theory using machine learning: the example of dielectric breakdown. Chem Mater 2016;28(5): 1304-11.
Crossref Google Scholar
[33]

Sun YT, Bai HY, Li MZ, Wang WH. Machine learning approach for prediction and understanding of glass-forming ability. J Phys Chem Lett 2017;8(14): 3434-9.
Crossref Google Scholar
[34]

Weng B, Song Z, Zhu R, Yan Q, Sun Q, Grice CG, Yan Y, Yin WJ. Simple descriptor derived from symbolic regression accelerating the discovery of new perovskite catalysts. Nat Commun 2020;11(1): 3513.
Crossref Google Scholar
[35]

Xue D, Balachandran PV, Yuan R, Hu T, Qian X, Dougherty ER, Lookman T. Accelerated search for BaTiO3-based piezoelectrics with vertical morphotropic phase boundary using Bayesian learning. Proc Natl Acad Sci USA 2016;113(47): 13301-6.
Crossref Google Scholar
[36]

Raccuglia P, Elbert KC, Adler PD, Falk C, Wenny MB, Mollo A, Zeller M, Friedler SA, Schrier J, Norquist AJ. Machine-learning-assisted materials discovery using failed experiments. Nature 2016;533(7601): 73-6.
Crossref Google Scholar
[37]

Kim E, Huang K, Jegelka S, Olivetti E. Virtual screening of inorganic materials synthesis parameters with deep learning. npj Comput Mater 2017;3(1): 1-9.
Crossref Google Scholar
[38]

Umeda Y, Hayashi H, Moriwake H, Tanaka I. Materials informatics for dielectric materials. Jpn J Appl Phys 2018;57(11S): 11UB01.
Crossref Google Scholar
[39]

Umeda Y, Hayashi H, Moriwake H, Tanaka I. Prediction of dielectric constants using a combination of first principles calculations and machine learning. Jpn J Appl Phys 2019;58(SL): SLLC01.
Crossref Google Scholar
[40]

Noda Y, Otake M, Nakayama M. Descriptors for dielectric constants of perovskite-type oxides by materials informatics with first-principles density functional theory. Sci Technol Adv Mater 2020;21(1): 92-9.
Crossref Google Scholar
[41]

Morita K, Davies DW, Butler KT, Walsh A. Modeling the dielectric constants of crystals using machine learning. J Chem Phys 2020;153(2): 024503.
Crossref Google Scholar
[42]

Jain A, Ong SP, Hautier G, Chen W, Richards WD, Dacek S, Cholia S, Gunter D, Skinner D, Ceder G, Persson KA. The Materials Project: a materials genome approach to accelerating materials innovation. Apl Mater 2013;1(1): 011002.
Crossref Google Scholar
[43]

Shannon RD. Dielectric polarizabilities of ions in oxides and fluorides. J Appl Phys 1993;73(1): 348-66.
Crossref Google Scholar
[44]

Momma K, Izumi F. VESTA 3 for three-dimensional visualization of crystal, volumetric and morphology data. J Appl Crystallogr 2011;44(6): 1272-6.
Crossref Google Scholar
[45]

Park HS, Yoon KH, Kim ES. Effect of bond valence on microwave dielectric properties of complex perovskite ceramics. Mater Chem Phys 2003;79: 181-3.
Crossref Google Scholar
[46]

Cho YS, Yoon KH, Lee BD, Lee HR, Kim ES. Understanding microwave dielectric properties of Pb-based complex perovskite ceramics via bond valence. Ceram Int 2004;30(8): 2247-50.
Crossref Google Scholar
[47]

Valant M, Suvorov D, Rawn C. Intrinsic reasons for variations in dielectric properties of Ba6-3xR8+2xTi18O54 (R = LA-Gd) solid solutions. Jpn J Appl Phys 1999;38(5A): 2820-6.
Crossref Google Scholar
[48]

Colla EL, David N, Rau C, Setter N. Prediction of the dielectric properties of non-ferroelectric complex perovskites and of the ternary system Ba/SrO-Ln2O3-xTiO2 for microwave applications. Ferroelectrics 1996;184(1): 151-60.
Crossref Google Scholar
[49]

Diao C, Shi F. Correlation among dielectric properties, vibrational modes, and crystal structures in Ba[SnxZn(1–x)/3Nb2(1–x)/3]O3 solid solutions. ACS Sustainable Chem Eng 2012;116(12): 6852-8.
Crossref Google Scholar
[50]

Kwon D-K, Lanagan MT, Shrout TR. Microwave dielectric properties and low-temperature cofiring of BaTe4O9 with aluminum metal electrode. J Am Ceram Soc 2005;88(12): 3419-22.
Crossref Google Scholar
[51]

Phillips JC. Dielectric definition of electronegativity. Phys Rev Lett 1968;20(11): 550-3.
Crossref Google Scholar
[52]

Simpson J, Clair A St. Fundamental insight on developing low dielectric constant polyimides. Thin Solid Films 1997;308–309: 480-5.
Crossref Google Scholar
[53]

Timothy ML, Timothy MS. Molecular design of free volume as a route to low-κ dielectric materials. J Am Chem Soc 2003;125(46): 14113-9.
Crossref Google Scholar
[54]

Sebastian MT, Wang H, Jantunen H. Low temperature co-fired ceramics with ultra-low sintering temperature: a review. Curr Opin Solid State Mater Sci 2016;20(3): 151-70.
Crossref Google Scholar
[55]
Ohsato H. Millimeter-wave materials. In: Sebastian M, Jantunen H, Ubic R, editors. Microwave materials and applications. Chichester, UK: John Wiley &Sons; 2017. p. 203-91.
Crossref
[56]

Song X-Q, Du K, Li J, Lan X-K, Lu W-Z, Wang X-H, Lei W. Low-fired fluoride microwave dielectric ceramics with low dielectric loss. Ceram Int 2019;45(1):279-86.
Crossref Google Scholar
[57]

Xie C, Oganov AR, Dong D, Liu N, Li D, Debela TT. Rational design of inorganic dielectric materials with expected permittivity. Sci Rep 2015;5:16769.
Crossref Google Scholar
Journal of Materiomics
Volume 7 Issue 6,
November 2021
Pages 1284-1293
DOI: 10.1016/j.jmat.2021.02.012
Cite this article:
Qin J, Liu Z, Ma M, et al. Machine learning approaches for permittivity prediction and rational design of microwave dielectric ceramics. Journal of Materiomics, 2021, 7(6): 1284-1293. https://doi.org/10.1016/j.jmat.2021.02.012

213

Views

29

Crossref

29

Web of Science

35

Scopus

Altmetrics
Received: 24 December 2020
Revised: 15 February 2021
Accepted: 17 February 2021
Published: 04 March 2021
© 2021 The Chinese Ceramic Society.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Return