Journal Home > Volume 12 , Issue 9
Journal of Advanced Ceramics 2023, 12(9): 1793-1804 https://doi.org/10.26599/JAC.2023.9220788
Research Article | Open Access | Issue | Published: 18 September 2023

Machine learning assisted prediction of dielectric temperature spectrum of ferroelectrics

Show Author's Information Jingjin Hea,b,c,  Changxin Wanga,b,  Junjie Lid,  Chuanbao Liue,  Dezhen Xuef,  Jiangli Caob,  Yanjing Sua,b,  Lijie Qiaoa,b,  Turab Lookmang,  Yang Baia,b( )
Beijing Advanced Innovation Center for Materials Genome Engineering, University of Science and Technology Beijing, Beijing 100083, China
Institute for Advanced Material and Technology, University of Science and Technology Beijing, Beijing 100083, China
Faculty of Materials Science and Engineering, Kunming University of Science and Technology, Kunming 650093, China
Sichuan Province Key Laboratory of Information Materials and Devices Application, College of Optoelectronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China
School of Materials Science and Technology, University of Science and Technology Beijing, Beijing 100083, China
State Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong University, Xi’an 710049, China
AiMaterials Research LLC, Santa Fe, NM 87501, USA
Keywords:
ferroelectrics, machine learning (ML), dielectric temperature spectrum, phase transition information
Cite this article:
He J, Wang C, Li J, et al. Machine learning assisted prediction of dielectric temperature spectrum of ferroelectrics. Journal of Advanced Ceramics, 2023, 12(9): 1793-1804. https://doi.org/10.26599/JAC.2023.9220788
Download citation
EndNote(RIS)
BibTeX

3270

Views

677

Downloads

Citations

0

Crossref

0

WoS

0

Scopus

0

CSCD

Abstract Full text Electronic supplementary material About this article

In material science and engineering, obtaining a spectrum from a measurement is often time-consuming and its accurate prediction using data mining can also be difficult. In this work, we propose a machine learning strategy based on a deep neural network model to accurately predict the dielectric temperature spectrum for a typical multi-component ferroelectric system, i.e., (Ba1−x−yCaxSry)(Ti1−u−v−wZruSnvHfw)O3. The deep neural network model uses physical features as inputs and directly outputs the full spectrum, in addition to yielding the octahedral factor, Matyonov–Batsanov electronegativity, ratio of valence electron to nuclear charge, and core electron distance (Schubert) as four key descriptors. Owing to the physically meaningful features, our model exhibits better performance and generalization ability in the broader composition space of BaTiO3-based solid solutions. And the prediction accuracy is superior to traditional machine learning models that predict dielectric permittivity values at each temperature. Furthermore, the transition temperature and the degree of dispersion of the ferroelectric phase transition are easily extracted from the predicted spectra to provide richer physical information. The prediction is also experimentally validated by typical samples of (Ba0.85Ca0.15)(Ti0.98–xZrxHf0.02)O3. This work provides insights for accelerating spectra predictions and extracting ferroelectric phase transition information.


menu
Abstract
Full text
Outline
Electronic supplementary material
About this article

Machine learning assisted prediction of dielectric temperature spectrum of ferroelectrics

Show Author's information Jingjin Hea,b,c, Changxin Wanga,b, Junjie Lid, Chuanbao Liue, Dezhen Xuef, Jiangli Caob, Yanjing Sua,b, Lijie Qiaoa,b, Turab Lookmang, Yang Baia,b( )
Beijing Advanced Innovation Center for Materials Genome Engineering, University of Science and Technology Beijing, Beijing 100083, China
Institute for Advanced Material and Technology, University of Science and Technology Beijing, Beijing 100083, China
Faculty of Materials Science and Engineering, Kunming University of Science and Technology, Kunming 650093, China
Sichuan Province Key Laboratory of Information Materials and Devices Application, College of Optoelectronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China
School of Materials Science and Technology, University of Science and Technology Beijing, Beijing 100083, China
State Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong University, Xi’an 710049, China
AiMaterials Research LLC, Santa Fe, NM 87501, USA

Abstract

In material science and engineering, obtaining a spectrum from a measurement is often time-consuming and its accurate prediction using data mining can also be difficult. In this work, we propose a machine learning strategy based on a deep neural network model to accurately predict the dielectric temperature spectrum for a typical multi-component ferroelectric system, i.e., (Ba1−x−yCaxSry)(Ti1−u−v−wZruSnvHfw)O3. The deep neural network model uses physical features as inputs and directly outputs the full spectrum, in addition to yielding the octahedral factor, Matyonov–Batsanov electronegativity, ratio of valence electron to nuclear charge, and core electron distance (Schubert) as four key descriptors. Owing to the physically meaningful features, our model exhibits better performance and generalization ability in the broader composition space of BaTiO3-based solid solutions. And the prediction accuracy is superior to traditional machine learning models that predict dielectric permittivity values at each temperature. Furthermore, the transition temperature and the degree of dispersion of the ferroelectric phase transition are easily extracted from the predicted spectra to provide richer physical information. The prediction is also experimentally validated by typical samples of (Ba0.85Ca0.15)(Ti0.98–xZrxHf0.02)O3. This work provides insights for accelerating spectra predictions and extracting ferroelectric phase transition information.

Keywords: ferroelectrics, machine learning (ML), dielectric temperature spectrum, phase transition information

References(61)

[1]
Ghosh K, Stuke A, Todorović M, et al. Deep learning spectroscopy: Neural networks for molecular excitation spectra. Adv Sci 2019, 6: 1801367.
DOI Google Scholar
[2]
Iwasaki Y, Kusne AG, Takeuchi I. Comparison of dissimilarity measures for cluster analysis of X-ray diffraction data from combinatorial libraries. npj Comput Mater 2017, 3: 4.
DOI Google Scholar
[3]
Xing H, Zhao BB, Wang YJ, et al. Rapid construction of Fe–Co–Ni composition-phase map by combinatorial materials chip approach. ACS Comb Sci 2018, 20: 127–131.
DOI Google Scholar
[4]
Oviedo F, Ren ZK, Sun SJ, et al. Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks. npj Comput Mater 2019, 5: 60.
DOI Google Scholar
[5]
Sun SJ, Hartono NTP, Ren ZD, et al. Accelerated development of perovskite-inspired materials via high-throughput synthesis and machine-learning diagnosis. Joule 2019, 3: 1437–1451.
DOI Google Scholar
[6]
He TF, Cao ZZ, Li GR, et al. High efficiently harvesting visible light and vibration energy in (1−x)AgNbO3−xLiTaO3 solid solution around antiferroelectric−ferroelectric phase boundary for dye degradation. J Adv Ceram 2022, 11: 1641–1653.
DOI Google Scholar
[7]
Suzuki Y, Hino H, Kotsugi M, et al. Automated estimation of materials parameter from X-ray absorption and electron energy-loss spectra with similarity measures. npj Comput Mater 2019, 5: 39.
DOI Google Scholar
[8]
Zheng C, Mathew K, Chen C, et al. Automated generation and ensemble-learned matching of X-ray absorption spectra. npj Comput Mater 2018, 4: 12.
DOI Google Scholar
[9]
Zheng C, Chen C, Chen YM, et al. Random forest models for accurate identification of coordination environments from X-ray absorption near-edge structure. Patterns 2020, 1: 100013.
DOI Google Scholar
[10]
Timoshenko J, Lu DY, Lin YW, et al. Supervised machine-learning-based determination of three-dimensional structure of metallic nanoparticles. J Phys Chem Lett 2017, 8: 5091–5098.
DOI Google Scholar
[11]
Miyazato I, Takahashi L, Takahashi K. Automatic oxidation threshold recognition of XAFS data using supervised machine learning. Mol Syst Des Eng 2019, 4: 1014–1018.
DOI Google Scholar
[12]
Torrisi SB, Carbone MR, Rohr BA, et al. Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships. npj Comput Mater 2020, 6: 109.
DOI Google Scholar
[13]
Huang QC, Fan Z, Hong LQ, et al. Machine learning based distinguishing between ferroelectric and non-ferroelectric polarization–electric field hysteresis loops. Adv Theory Simul 2020, 3: 2000106.
DOI Google Scholar
[14]
Li JJ, Yin RW, Li JT, et al. Correlation between multi-factor phase diagrams and complex electrocaloric behaviors in PNZST antiferroelectric ceramic system. J Adv Ceram 2023, 12: 463–473.
DOI Google Scholar
[15]
Ueno T, Hino H, Hashimoto A, et al. Adaptive design of an X-ray magnetic circular dichroism spectroscopy experiment with Gaussian process modelling. npj Comput Mater 2018, 4: 4.
DOI Google Scholar
[16]
Li MX, Zhao SF, Lu Z, et al. High-temperature bulk metallic glasses developed by combinatorial methods. Nature 2019, 569: 99–103.
DOI Google Scholar
[17]
Hattrick-Simpers JR, Gregoire JM, Kusne AG. Perspective: Composition–structure–property mapping in high-throughput experiments: Turning data into knowledge. APL Mater 2016, 4: 053211.
DOI Google Scholar
[18]
Kusne AG, Gao TR, Mehta A, et al. On-the-fly machine-learning for high-throughput experiments: Search for rare-earth-free permanent magnets. Sci Rep 2014, 4: 6367.
DOI Google Scholar
[19]
Yoo YK, Ohnishi T, Wang G, et al. Continuous mapping of structure-property relations in Fe1−xNix metallic alloys fabricated by combinatorial synthesis. Intermetallics 2001, 9: 541–545.
DOI Google Scholar
[20]
Wang L. Discovering phase transitions with unsupervised learning. Phys Rev B 2016, 94: 195105.
DOI Google Scholar
[21]
Zhu Q, Samanta A, Li BX, et al. Predicting phase behavior of grain boundaries with evolutionary search and machine learning. Nat Commun 2018, 9: 467.
DOI Google Scholar
[22]
Hu CZ, Zuo YX, Chen C, et al. Genetic algorithm-guided deep learning of grain boundary diagrams: Addressing the challenge of five degrees of freedom. Mater Today 2020, 38: 49–57.
DOI Google Scholar
[23]
Yuan RH, Liu Z, Balachandran PV, et al. Accelerated discovery of large electrostrains in BaTiO3-based piezoelectrics using active learning. Adv Mater 2018, 30: 1702884.
DOI Google Scholar
[24]
Yuan RH, Tian Y, Xue DZ, et al. Accelerated search for BaTiO3-based ceramics with large energy storage at low fields using machine learning and experimental design. Adv Sci 2019, 6: 1901395.
DOI Google Scholar
[25]
Im J, Lee S, Ko TW, et al. Identifying Pb-free perovskites for solar cells by machine learning. npj Comput Mater 2019, 5: 37.
DOI Google Scholar
[26]
Balachandran PV, Kowalski B, Sehirlioglu A, et al. Experimental search for high-temperature ferroelectric perovskites guided by two-step machine learning. Nat Commun 2018, 9: 1668.
DOI Google Scholar
[27]
Chen CT, Gu GX. Generative deep neural networks for inverse materials design using backpropagation and active learning. Adv Sci 2020, 7: 1902607.
DOI Google Scholar
[28]
Lu SH, Zhou QH, Guo YL, et al. Coupling a crystal graph multilayer descriptor to active learning for rapid discovery of 2D ferromagnetic semiconductors/half-metals/metals. Adv Mater 2020, 32: 2002658.
DOI Google Scholar
[29]
Kunkel C, Margraf JT, Chen K, et al. Active discovery of organic semiconductors. Nat Commun 2021, 12: 2422.
DOI Google Scholar
[30]
Wang XK, Rai N, Merchel Piovesan Pereira B, et al. Accelerated knowledge discovery from omics data by optimal experimental design. Nat Commun 2020, 11: 5026.
DOI Google Scholar
[31]
Duan XJ, Fang Z, Yang T, et al. Maximizing the mechanical performance of Ti3AlC2-based MAX phases with aid of machine learning. J Adv Ceram 2022, 11: 1307–1318.
DOI Google Scholar
[32]
Zeng QF, Gao Y, Guan K, et al. Machine learning and a computational fluid dynamic approach to estimate phase composition of chemical vapor deposition boron carbide. J Adv Ceram 2021, 10: 537–550.
DOI Google Scholar
[33]
Kiyohara S, Miyata T, Tsuda K, et al. Data-driven approach for the prediction and interpretation of core−electron loss spectroscopy. Sci Rep 2018, 8: 13548.
DOI Google Scholar
[34]
Liu JC, Osadchy M, Ashton L, et al. Deep convolutional neural networks for Raman spectrum recognition: A unified solution. Analyst 2017, 142: 4067–4074.
DOI Google Scholar
[35]
Pradhan DK, Kumari S, Strelcov E, et al. Reconstructing phase diagrams from local measurements via Gaussian processes: Mapping the temperature-composition space to confidence. npj Comput Mater 2018, 4: 23.
DOI Google Scholar
[36]
Malkiel I, Mrejen M, Nagler A, et al. Plasmonic nanostructure design and characterization via Deep Learning. Light Sci Appl 2018, 7: 60.
DOI Google Scholar
[37]
Ma W, Cheng F, Liu YM. Deep-learning-enabled on-demand design of chiral metamaterials. ACS Nano 2018, 12: 6326–6334.
DOI Google Scholar
[38]
Liu DJ, Tan YX, Khoram E, et al. Training deep neural networks for the inverse design of nanophotonic structures. ACS Photonics 2018, 5: 1365–1369.
DOI Google Scholar
[39]
Li Y, Xu YJ, Jiang ML, et al. Self-learning perfect optical chirality via a deep neural network. Phys Rev Lett 2019, 123: 213902.
DOI Google Scholar
[40]
Timoshenko J, Anspoks A, Cintins A, et al. Neural network approach for characterizing structural transformations by X-ray absorption fine structure spectroscopy. Phys Rev Lett 2018, 120: 225502.
DOI Google Scholar
[41]
Liu WF, Ren XB. Large piezoelectric effect in Pb-free ceramics. Phys Rev Lett 2009, 103: 257602.
DOI Google Scholar
[42]
Kalyani AK, Senyshyn A, Ranjan R. Polymorphic phase boundaries and enhanced piezoelectric response in extended composition range in the lead free ferroelectric BaTi1−xZrxO3. J Appl Phys 2013, 114: 014102.
DOI Google Scholar
[43]
Kalyani AK, Brajesh K, Senyshyn A, et al. Orthorhombic-tetragonal phase coexistence and enhanced piezo-response at room temperature in Zr, Sn, and Hf modified BaTiO3. Appl Phys Lett 2014, 104: 252906.
DOI Google Scholar
[44]
Krishnan H, Sen A, Senyshyn A, et al. Polarization switching and high piezoelectric response in Sn-modified BaTiO3. Phys Rev B 2015, 91: 024101.
Google Scholar
[45]
Zhao CL, Wang H, Xiong J, et al. Composition-driven phase boundary and electrical properties in (Ba0.94Ca0.06)(Ti1−xMx)O3 (M = Sn, Hf, Zr) lead-free ceramics. Dalton Trans 2016, 45: 6466–6480.
DOI Google Scholar
[46]
Bai WF, Chen DQ, Zhang JJ, et al. Phase transition behavior and enhanced electromechanical properties in (Ba0.85Ca0.15)(ZrxTi1−x)O3 lead-free piezoceramics. Ceram Int 2016, 42: 3598–3608.
DOI Google Scholar
[47]
Zhu LF, Zhang BP, Zhao XK, et al. Phase transition and high piezoelectricity in (Ba,Ca)(Ti1−xSnx)O3 lead-free ceramics. Appl Phys Lett 2013, 103: 072905.
DOI Google Scholar
[48]
Tian Y, Wei LL, Chao XL, et al. Phase transition behavior and large piezoelectricity near the morphotropic phase boundary of lead-free (Ba0.85Ca0.15)(Zr0.1Ti0.9)O3 ceramics. J Am Ceram Soc 2012, 96: 496–502.
DOI Google Scholar
[49]
Li W, Xu ZJ, Chu RQ, et al. Piezoelectric and dielectric properties of (Ba1−xCax)(Ti0.95Zr0.05)O3 lead-free ceramics. J Am Ceram Soc 2010, 93: 2942–2944.
DOI Google Scholar
[50]
Li W, Xu ZJ, Chu RQ, et al. Large piezoelectric coefficient in (Ba1−xCax)(Ti0.96Sn0.04)O3 lead-free ceramics. J Am Ceram Soc 2011, 94: 4131–4133.
DOI Google Scholar
[51]
Xue DZ, Zhou YM, Bao HX, et al. Large piezoelectric effect in Pb-free Ba(Ti,Sn)O3−x(Ba,Ca)TiO3 ceramics. Appl Phys Lett 2011, 99: 122901.
DOI Google Scholar
[52]
Zhu LF, Zhang BP, Zhao L, et al. High piezoelectricity of BaTiO3–CaTiO3–BaSnO3 lead-free ceramics. J Mater Chem C 2014, 2: 4764–4771.
DOI Google Scholar
[53]
Li W, Xu ZJ, Chu RQ, et al. Enhanced ferroelectric properties in (Ba1−xCax)(Ti0.94Sn0.06)O3 lead-free ceramics. J Eur Ceram Soc 2012, 32: 517–520.
DOI Google Scholar
[54]
Zhao CL, Feng YM, Wu HP, et al. Phase boundary design and high piezoelectric activity in (1−x)(Ba0.93Ca0.07) TiO3−xBa(Sn1−yHfy)O3 lead-free ceramics. J Alloy Compd 2016, 666: 372–379.
DOI Google Scholar
[55]
Zhu LF, Zhang BP, Zhao L, et al. Large piezoelectric effect of (Ba,Ca)TiO3–xBa(Sn,Ti)O3 lead-free ceramics. J Eur Ceram Soc 2016, 36: 1017–1024.
DOI Google Scholar
[56]
Wang DL, Jiang ZH, Yang B, et al. Phase diagram and enhanced piezoelectric response of lead-free BaTiO3− CaTiO3−BaHfO3 system. J Am Ceram Soc 2014, 97: 3244–3251.
DOI Google Scholar
[57]
Wang DL, Jiang ZH, Yang B, et al. Phase transition behavior and high piezoelectric properties in lead-free BaTiO3–CaTiO3–BaHfO3 ceramics. J Mater Sci 2014, 49: 62–69.
DOI Google Scholar
[58]
Huang WJ, Martin P, Zhuang HL. Machine-learning phase prediction of high-entropy alloys. Acta Mater 2019, 169: 225–236.
DOI Google Scholar
[59]
He JJ, Li JJ, Liu CB, et al. Machine learning identified materials descriptors for ferroelectricity. Acta Mater 2021, 209: 116815.
DOI Google Scholar
[60]
He JJ, Su XP, Wang CX, et al. Machine learning assisted predictions of multi-component phase diagrams and fine boundary information. Acta Mater 2022, 240: 118341.
DOI Google Scholar
[61]
Tian Y, Yuan RH, Xue DZ, et al. Determining multi-component phase diagrams with desired characteristics using active learning. Adv Sci 2021, 8: 2003165.
DOI Google Scholar
File
JAC0788_ESM.pdf (744.2 KB)
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 03 June 2023
Revised: 02 July 2023
Accepted: 18 July 2023
Published: 18 September 2023
Issue date: September 2023

Copyright

© The Author(s) 2023.

Acknowledgements

This work was supported by the National Key R&D Program of China (2022YFB3807401), National Natural Science Foundation of China (52173217), and 111 project (B170003).

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Return