|
|
|
Evaluating thermal expansion in fluorides and oxides: Machine learning predictions with connectivity descriptors |
| Yilin Zhang(张轶霖)1,†, Huimin Mu(穆慧敏)2,†, Yuxin Cai(蔡雨欣)1,†, Xiaoyu Wang(王啸宇)2, Kun Zhou(周琨)1, Fuyu Tian(田伏钰)1, Yuhao Fu(付钰豪)2,3,‡, and Lijun Zhang(张立军)1,3,§ |
1 State Key Laboratory of Integrated Optoelectronics, Key Laboratory of Automobile Materials of MOE, College of Materials Science and Engineering, Jilin University, Changchun 130012, China;
2 State Key Laboratory of Superhard Materials, College of Physics, Jilin University, Changchun 130012, China;
3 International Center of Computational Method and Software, Jilin University, Changchun 130012, China |
|
|
|
|
Abstract Open framework structures (e.g., ScF3, Sc2W3O12, etc.) exhibit significant potential for thermal expansion tailoring owing to their high atomic vibrational degrees of freedom and diverse connectivity between polyhedral units, displaying positive/negative thermal expansion (PTE/NTE) coefficients at a certain temperature. Despite the proposal of several physical mechanisms to explain the origin of NTE, an accurate mapping relationship between the structural-compositional properties and thermal expansion behavior is still lacking. This deficiency impedes the rapid evaluation of thermal expansion properties and hinders the design and development of such materials. We developed an algorithm for identifying and characterizing the connection patterns of structural units in open-framework structures and constructed a descriptor set for the thermal expansion properties of this system, which is composed of connectivity and elemental information. Our developed descriptor, aided by machine learning (ML) algorithms, can effectively learn the thermal expansion behavior in small sample datasets collected from literature-reported experimental data (246 samples). The trained model can accurately distinguish the thermal expansion behavior (PTE/NTE), achieving an accuracy of 92%. Additionally, our model predicted six new thermodynamically stable NTE materials, which were validated through first-principles calculations. Our results demonstrate that developing effective descriptors closely related to thermal expansion properties enables ML models to make accurate predictions even on small sample datasets, providing a new perspective for understanding the relationship between connectivity and thermal expansion properties in the open framework structure. The datasets that were used to support these results are available on Science Data Bank, accessible via the link https://doi.org/10.57760/sciencedb.j00113.00100.
|
Received: 15 April 2023
Revised: 17 April 2023
Accepted manuscript online: 18 April 2023
|
|
PACS:
|
63.20.dk
|
(First-principles theory)
|
|
| Fund: Project supported by the National Natural Science Foundation of China (Grant Nos. 12004131, 22090044, 62125402, and 92061113). Calculations were performed in part at the high-performance computing center of Jilin University. |
Corresponding Authors:
Yuhao Fu, Lijun Zhang
E-mail: fuyuhaoy@gmail.com;lijun_zhang@jlu.edu.cn
|
Cite this article:
Yilin Zhang(张轶霖), Huimin Mu(穆慧敏), Yuxin Cai(蔡雨欣), Xiaoyu Wang(王啸宇), Kun Zhou(周琨), Fuyu Tian(田伏钰), Yuhao Fu(付钰豪), and Lijun Zhang(张立军) Evaluating thermal expansion in fluorides and oxides: Machine learning predictions with connectivity descriptors 2023 Chin. Phys. B 32 056302
|
[1] Moore A L and Shi L 2014 Mater. Today 17 163
[2] Takeuchi Y, Sakamoto M and Sata T 1982 Precis. Eng. 4 19
[3] Moore A L and Shi L 2014 Mater. Today 17 163
[4] Cai Y, Faizan M, Mu H, Zhang Y, Zou H, Zhao H J, Fu Y and Zhang L 2023 Front. Phys. 18 43303
[5] Cen D, Wang B, Chu R, Gong Y, Xu G, Chen F and Xu F 2020 Scripta Mater 186 331
[6] Ding L, Wang C, Na Y, Chu L and Yan J 2011 Scripta Mater. 65 687
[7] Takenaka K, Hamada T, Kasugai D and Sugimoto N 2012 J. Appl. Phys. 112 083517
[8] Takenaka K and Ichigo M 2014 Compos. Sci. Technol. 104 47
[9] Yan X, Miao J, Liu J, Wu X, Zou H, Sha D, Ren J, Dai Y, Wang J and Cheng X 2016 J. Alloys Compd. 677 52
[10] Takenaka K 2012 Sci. Technol. Adv. Mat. 13 013001
[11] Dove M T and Fang H 2016 Rep. Prog. Phys. 79 066503
[12] Attfield J P 2018 Front. Chem. 6 371
[13] Coates C S and Goodwin A L 2019 Mater. Horizons 6 211
[14] Takenaka K 2018 Front. Chem. 6 267
[15] Lalpoor M, Eskin D G and Katgerman L 2011 Int. J. Mater. Res. 102 1286
[16] Mittal R, Gupta M K and Chaplot S L 2018 Prog. Mater. Sci. 92 360
[17] Ji T, He S, Ai F, Wu J, Yan L, Hu J and Liao M 2021 Nano Res. 14 3423
[18] Li C W, Tang X, Muñoz J A, Keith J B, Tracy S J, Abernathy D L and Fultz B 2011 Phys. Rev. Lett. 107 195504
[19] Liu Y, Wang Z, Wu M, Sun Q, Chao M and Jia Y 2015 Comp. Mater. Sci. 107 157
[20] Huu H T, Viswanath N S M, Vu N H, Lee J W and Im W B 2021 Nano Res. 14 3977
[21] Wang L, Yuan P F, Wang F, Sun Q, Liang E J, Jia Y and Guo Z X 2014 Phys. Lett. A 378 2906
[22] Wu J, Li Q, Shuck C E, Maleski K, Alshareef H N, Zhou J, Gogotsi Y and Huang L 2022 Nano Res. 15 535
[23] Grima J N, Bajada M, Scerri S, Attard D, Dudek K K and Gatt R 2015 Proc. Royal Soc. Math. Phys. Eng. Sci. 471 20150188
[24] Vila F D, Hayashi S T and Rehr J J 2018 Front. Chem. 6 296
[25] Mary T A, Evans J S O, Vogt T and Sleight A W 1996 Science 272 90
[26] Wang H, Yang M, Chao M, Guo J, Gao Q, Jiao Y, Tang X and Liang E 2019 Solid State Ionics 343 115086
[27] Ernst G, Broholm C, Kowach G R and Ramirez A P 1998 Nature 396 147
[28] Suzuki I, Seya K, Takei H and Sumino Y 1981 Phys. Chem. Minerals 7 60
[29] Zhao Y, Weidner D J, Parise J B and Cox D E 1993 Phys. Earth Planet. In. 76 1
[30] Mu H, Zhang Y, Zou H, Tian F, Fu Y and Zhang L 2023 J. Phys. Chem. Lett. 14 190
[31] Gao Q, Wang J, Sanson A, Sun Q, Liang E, Xing X and Chen J 2020 J. Am. Chem. Soc. 142 6935
[32] Zhang Y, Mu H, Xing B, Zou H, Fu Y and Zhang L 2022 Phys. Rev. Mater. 6 083603
[33] Peng J, Gunda N S H, Bridges C A, Lee S, Haynes J A and Shin D 2022 Comp. Mater. Sci. 210 111034
[34] Liaw A and Wiener M 2002 R news 2 18
[35] Friedman J H 2001 Ann. Statistics 29 1189
[36] Cortes C and Vapnik V 1995 Mach. Learn. 20 273
[37] Zhao R, Xing B, Mu H, Fu Y and Zhang L 2022 Chin. Phys. B 31 056302
[38] Freedman D A 2009 Statistical models: theory and practice (Cambridge University)
[39] Quinlan J R 1986 Mach. Learn. 1 81
[40] Kresse G 1995 J. Non-cryst. Solids 192 222
[41] Kresse G and Furthmüller J 1996 Comp. Mater. Sci. 6 15
[42] Kresse G and Joubert D 1999 Phys. Rev. B 59 1758
[43] Blöchl P E 1994 Phys. Rev. B 50 17953
[44] Perdew J P, Burke K and Ernzerhof M 1996 Phys. Rev. Lett. 77 3865
[45] Perdew J P, Chevary J A, Vosko S H, Jackson K A, Pederson M R, Singh D J and Fiolhais C 1992 Phys. Rev. B 46 6671
[46] Zhao X G, Zhou K, Xing B, Zhao R, Luo S, Li T, Sun Y, Na G, Xie J, Yang X, Wang X, Wang X, He X, Lv J, Fu Y and Zhang L 2021 Sci. Bull. 66 1973
[47] Zhao G, Xie J, Zhou K, Xing B, Wang X, Tian F, He X and Zhang L 2022 Chin. Phys. B 31 037104
[48] Altman N S 1992 The American Statistician 46 175
[49] Togo A and Tanaka I 2015 Scripta Mater. 108 1
[50] Sebastian L, Sumithra S, Manjanna J, Umarji A M and Gopalakrishnan J 2003 Mater. Sci. Eng. B 103 289
[51] Sanson A, Rocca F, Dalba G, Fornasini P, Grisenti R, Dapiaggi M and Artioli G 2006 Phys. Rev. B 73 214305
[52] Gupta M K, Mittal R, Chaplot S L and Rols S 2014 J. Appl. Phys. 115 093507 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
