Recent Implementations in LASP 3.0: Global Neural Network Potential with Multiple Elements and Better Long-Range Description<sup>†</sup>

Pei-lin Kang; Cheng Shang; Zhi-pan Liu

doi:10.1063/1674-0068/cjcp2108145

Volume 34 Issue 5

Oct. 2021

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Chemical Physics > 2021 > 34(5): 583-590

Pei-lin Kang, Cheng Shang, Zhi-pan Liu. Recent Implementations in LASP 3.0: Global Neural Network Potential with Multiple Elements and Better Long-Range Description†[J]. Chinese Journal of Chemical Physics , 2021, 34(5): 583-590. doi: 10.1063/1674-0068/cjcp2108145

Citation:

Pei-lin Kang, Cheng Shang, Zhi-pan Liu. Recent Implementations in LASP 3.0: Global Neural Network Potential with Multiple Elements and Better Long-Range Description^†[J]. Chinese Journal of Chemical Physics , 2021, 34(5): 583-590. doi: 10.1063/1674-0068/cjcp2108145

Citation:

PDF( 3737 KB)

Recent Implementations in LASP 3.0: Global Neural Network Potential with Multiple Elements and Better Long-Range Description^†

doi: 10.1063/1674-0068/cjcp2108145

Collaborative Innovation Center of Chemistry for Energy Material, Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials, Key Laboratory of Computational Physical Science (Ministry of Education), Department of Chemistry, Fudan University, Shanghai 200433, China Shanghai Qi Zhi Institute, Shanghai 200030, China

More Information

Corresponding author: Cheng Shang, E-mail: cshang@fudan.edu.cn; Zhi-pan Liu, E-mail: zpliu@fudan.edu.cn
Received Date: 2021-08-24
Accepted Date: 2021-09-08
Publish Date: 2021-10-27

Abstract

Abstract

LASP (large-scale atomistic simulation with neural network potential) software developed by our group since 2018 is a powerful platform (www.lasphub.com) for performing atomic simulation of complex materials. The software integrates the neural network (NN) potential technique with the global potential energy surface exploration method, and thus can be utilized widely for structure prediction and reaction mechanism exploration. Here we introduce our recent update on the LASP program version 3.0, focusing on the new functionalities including the advanced neural network training based on the multi-network framework, the newly-introduced $ S^7 $ and $ S^8 $ power type structure descriptor (PTSD). These new functionalities are designed to further improve the accuracy of potentials and accelerate the neural network training for multiple-element systems. Taking Cu$ - $C$ - $H$ - $O neural network potential and a heterogeneous catalytic model as the example, we show that these new functionalities can accelerate the training of multi-element neural network potential by using the existing single-network potential as the input. The obtained double-network potential CuCHO is robust in simulation and the introduction of $ S^7 $ and $ S^8 $ PTSDs can reduce the root-mean-square errors of energy by a factor of two.
- Large-scale atomistic simulation with neural network potential,
- Machine learning,
- Neural network,
- Structure descriptor,
- Simulation software

^†Part of special topic of "the Young Scientist Forum on Chemical Physics: Theoretical and Computational Chemistry Workshop 2020".

FullText(HTML)

References(33)

References

[1]	A. P. Bartók and G. Csányi, Int. J. Quantum Chem. 115, 1051 (2015). doi: 10.1002/qua.24927
[2]	H. Wang, L. Zhang, J. Han, and W. E, Comput. Phys. Commun. 228, 178 (2018). doi: 10.1016/j.cpc.2018.03.016
[3]	K. T. Schütt, H. E. Sauceda, P. J. Kindermans, A. Tkatchenko, and K. R. Müller, J. Chem. Phys. 148, 241722 (2018). doi: 10.1063/1.5019779
[4]	J. S. Smith, O. Isayev, and A. E. Roitberg, Chem. Sci. 8, 3192 (2017). doi: 10.1039/C6SC05720A
[5]	A. Khorshidi and A. A. Peterson, Comput. Phys. Commun. 207, 310 (2016). doi: 10.1016/j.cpc.2016.05.010
[6]	F. A. Faber, A. S. Christensen, B. Huang, and O. A. v. Lilienfeld, J. Chem. Phys. 148, 241717 (2018). doi: 10.1063/1.5020710
[7]	S. D. Huang, C. Shang, P. L. Kang, X. J. Zhang, and Z. P. Liu, WIREs Comput. Mol. Sci. 9, e1415 (2019).
[8]	S. D. Huang, C. Shang, X. J. Zhang, and Z. P. Liu, Chem. Sci. 8, 6327 (2017). doi: 10.1039/C7SC01459G
[9]	S. Ma, C. Shang, C. M. Wang, and Z. P. Liu, Chem. Sci. 11, 10113 (2020). doi: 10.1039/D0SC03918G
[10]	Y. Zhu, J. He, C. Shang, X. Miao, J. Huang, Z. Liu, H. Chen, and Y. Han, J. Am. Chem. Soc. 136, 12746 (2014). doi: 10.1021/ja506554j
[11]	X. T. Li, L. Chen, C. Shang, and Z. P. Liu, J. Am. Chem. Soc. 143, 6281 (2021). doi: 10.1021/jacs.1c02471
[12]	J. Behler and M. Parrinello, Phys. Rev. Lett. 98, 146401 (2007). doi: 10.1103/PhysRevLett.98.146401
[13]	Y. Zhang, C. Hu, and B. Jiang, J. Phys. Chem. Lett. 10, 4962 (2019). doi: 10.1021/acs.jpclett.9b02037
[14]	S. D. Huang, C. Shang, P. L. Kang, and Z. P. Liu, Chem. Sci. 9, 8644 (2018). doi: 10.1039/C8SC03427C
[15]	C. Shang, S. D. Huang, and Z. P. Liu, J. Comput. Chem. 40, 1091 (2019). doi: 10.1002/jcc.25636
[16]	X. Xie, K. A. Persson, and D. W. Small, J. Chem. Theory Comput. 16, 4256 (2020). doi: 10.1021/acs.jctc.0c00217
[17]	T. W. Ko, J. A. Finkler, and S. Goedecker, J. Behler, Acc. Chem. Res. 54, 808 (2021). doi: 10.1021/acs.accounts.0c00689
[18]	LASP Software. www.lasphub.com
[19]	C. Shang, X. J. Zhang, and Z. P. Liu, Phys. Chem. Chem. Phys. 16, 17845 (2014). doi: 10.1039/C4CP01485E
[20]	C. Shang and Z. P. Liu, J. Chem. Theory Comput. 9, 1838 (2013). doi: 10.1021/ct301010b
[21]	C. Shang and Z. P. Liu, J. Chem. Theory Comput. 6, 1136 (2010). doi: 10.1021/ct9005147
[22]	X. J. Zhang, C. Shang, and Z. P. Liu, J. Chem. Theory Comput. 9, 5745 (2013). doi: 10.1021/ct4008475
[23]	D. Frenkel and B. Smit, In Understanding Molecular Simulation (Second Edition), D. Frenkel and B. Smit, Eds., San Diego: Academic Press, 139 (2002).
[24]	N. Shuichi, Prog. Theor. Phys. Suppl. 103, 1 (1991). doi: 10.1143/PTPS.103.1
[25]	M. Parrinello and A. Rahman, Phys. Rev. Lett. 45, 1196 (1980). doi: 10.1103/PhysRevLett.45.1196
[26]	T. D. Kühne, M. Iannuzzi, M. D. Ben, V. V. Rybkin, P. Seewald, F. Stein, T. Laino, R. Z. Khaliullin, O. Schütt, F. Schiffmann, D. Golze, J. Wilhelm, S. Chulkov, M. H. Bani-Hashemian, V. Weber, U. Borštnik, M. Taillefumier, A. S. Jakobovits, A. Lazzaro, H. Pabst, T. Müller, R. Schade, M. Guidon, S. Andermatt, N. G. Holmberg, K. Schenter, A. Hehn, A. Bussy, F. Belleflamme, G. Tabacchi, A. Glöß, M. Lass, I. Bethune, C. J. Mundy, C. Plessl, M. Watkins, J. VandeVondele, M. Krack, and J. Hutter, J. Chem. Phys. 152, 194103 (2020). doi: 10.1063/5.0007045
[27]	P. Giannozzi, S. Baroni, N. Bonini, M. Calandra, R. Car, C. Cavazzoni, D. Ceresoli, G. L. Chiarotti, M. Cococcioni, I. Dabo, A. Dal Corso, S. de Gironcoli, S. Fabris, G. Fratesi, R. Gebauer, U. Gerstmann, C. Gougoussis, A. Kokalj, M. Lazzeri, L. Martin-Samos, N. Marzari, F. Mauri, R. Mazzarello, S. Paolini, A. Pasquarello, L. Paulatto, C. Sbraccia, S. Scandolo, G. Sclauzero, A. P. Seitsonen, A. Smogunov, P. Umari, and R. M. Wentzcovitch, J. Phys: Condens Matter. 21, 395502 (2009). doi: 10.1088/0953-8984/21/39/395502
[28]	Y. Zhang, C. Hu, and B. Jiang, Phys. Chem. Chem. Phys. 23, 1815 (2021). doi: 10.1039/D0CP05089J
[29]	B. N. Zope, D. D. Hibbitts, M. Neurock, and R. J. Davis, Science 330, 74 (2010). doi: 10.1126/science.1195055
[30]	C. H. C. Zhou, J. N. Beltramini, Y. X. Fan, and G. Q. M. Lu, Chem. Soc. Rev. 37, 527 (2008). doi: 10.1039/B707343G
[31]	J. ten Dam and U. Hanefeld, Chemsuschem 4, 1017 (2011). doi: 10.1002/cssc.201100162
[32]	G. Kresse and D. Joubert, Phys. Rev. B 59, 1758 (1999).
[33]	G. Kresse and J. Furthmller, Phys. Rev B 54, 11169 (1996). doi: 10.1103/PhysRevB.54.11169