TY - JOUR
T1 - Structural phase transition of monochalcogenides investigated with machine learning
AU - Zhang, J.
AU - Zhang, Feng
AU - Wei, D.
AU - Liu, L.
AU - Liu, X.
AU - Wang, Dangqi
AU - Zhang, G. X.
AU - Chen, X.
AU - Wang, D.
N1 - Funding Information:
We are grateful to Professor W. Zhang for fruitful discussion. This work is financially supported by the National Natural Science Foundation of China (NSFC), Grants No. 11974268 and No. 12111530061. X.C. thanks the financial support from Academy of Finland Project No. 308647. D.W. thanks the support from the Guangxi Key Laboratory of Optical and Electronic Materials and Devices (20KF-13), L.L. thanks the support from the Natural Science Foundation of Guangxi (Grants No. FA198015, No. GA245006, No. BA245069, No. FA198015, No. BA297029, and No. 20AA-7). D.F. thanks the support from the Natural Science Foundation of Shaanxi Province (Grant No. 2019JQ-240). G.Z. thanks the support from NSFC (Grant No. 21503057) and the Fundamental Research Funds for the Central Universities (Grant No. HIT.NSRIF.2017032). X.C. and D.W. also thank the support from CSC (IT Center for Science, Finland), Project No. 2001447, for providing computation resources.
Publisher Copyright:
© 2022 American Physical Society.
PY - 2022/3/28
Y1 - 2022/3/28
N2 - As machine learning becomes increasingly important in science and engineering, it holds the promise to provide a universal approach applicable to various systems to investigate their crystalline phase transitions. Here, we build and train accurate artificial neural networks that can distinguish tiny energy difference, which is crucial to predict the crystalline phase transitions. Employing the trained artificial neural networks in Monte Carlo simulations as the surrogate energy function, we apply this approach to monochalcogenides, including bulk and two-dimensional monolayer SnTe and GeTe, investigating their crystalline phase transitions. The machine-learning approach, when viewed as providing a universal mathematical structure, can be transferred to the investigation of other materials when the training data set generated with ab initio methods are available. Moreover, the machine-learning approach resolves the difficulties associated with constructing the effective Hamiltonian for monochalcogenides, showing great potential with its accuracy and efficiency.
AB - As machine learning becomes increasingly important in science and engineering, it holds the promise to provide a universal approach applicable to various systems to investigate their crystalline phase transitions. Here, we build and train accurate artificial neural networks that can distinguish tiny energy difference, which is crucial to predict the crystalline phase transitions. Employing the trained artificial neural networks in Monte Carlo simulations as the surrogate energy function, we apply this approach to monochalcogenides, including bulk and two-dimensional monolayer SnTe and GeTe, investigating their crystalline phase transitions. The machine-learning approach, when viewed as providing a universal mathematical structure, can be transferred to the investigation of other materials when the training data set generated with ab initio methods are available. Moreover, the machine-learning approach resolves the difficulties associated with constructing the effective Hamiltonian for monochalcogenides, showing great potential with its accuracy and efficiency.
UR - http://www.scopus.com/inward/record.url?scp=85128554481&partnerID=8YFLogxK
U2 - 10.1103/PhysRevB.105.094116
DO - 10.1103/PhysRevB.105.094116
M3 - Article
AN - SCOPUS:85128554481
SN - 2469-9950
VL - 105
SP - 1
EP - 14
JO - Physical Review B
JF - Physical Review B
IS - 9
M1 - 094116
ER -