The atomistic modeling of amorphous materials requires structure sizes and sampling statistics that are challenging to achieve with first-principles methods. Here, we propose a methodology to speed up the sampling of amorphous and disordered materials using a combination of a genetic algorithm and a specialized machine-learning potential based on artificial neural networks (ANNs). We show for the example of the amorphous LiSi alloy that around 1000 first-principles calculations are sufficient for the ANN-potential assisted sampling of low-energy atomic configurations in the entire amorphous LixSi phase space. The obtained phase diagram is validated by comparison with the results from an extensive sampling of LixSi configurations using molecular dynamics simulations and a general ANN potential trained to ∼45 000 first-principles calculations. This demonstrates the utility of the approach for the first-principles modeling of amorphous materials.
Skip Nav Destination
Article navigation
28 June 2018
Research Article|
March 16 2018
Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm
Special Collection:
Data-Enabled Theoretical Chemistry
Nongnuch Artrith
;
Nongnuch Artrith
a)
Department of Materials Science and Engineering, University of California
, Berkeley, California 94720, USA
and Materials Science Division, Lawrence Berkeley National Laboratory
, Berkeley, California 94720, USA
Search for other works by this author on:
Alexander Urban;
Alexander Urban
Department of Materials Science and Engineering, University of California
, Berkeley, California 94720, USA
and Materials Science Division, Lawrence Berkeley National Laboratory
, Berkeley, California 94720, USA
Search for other works by this author on:
Gerbrand Ceder
Gerbrand Ceder
b)
Department of Materials Science and Engineering, University of California
, Berkeley, California 94720, USA
and Materials Science Division, Lawrence Berkeley National Laboratory
, Berkeley, California 94720, USA
Search for other works by this author on:
a)
Electronic mail: [email protected]
b)
Electronic mail: [email protected]
J. Chem. Phys. 148, 241711 (2018)
Article history
Received:
November 29 2017
Accepted:
February 12 2018
Citation
Nongnuch Artrith, Alexander Urban, Gerbrand Ceder; Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm. J. Chem. Phys. 28 June 2018; 148 (24): 241711. https://doi.org/10.1063/1.5017661
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
DeePMD-kit v2: A software package for deep potential models
Jinzhe Zeng, Duo Zhang, et al.
Beyond the Debye–Hückel limit: Toward a general theory for concentrated electrolytes
Mohammadhasan Dinpajooh, Nadia N. Intan, et al.
Related Content
First-principles study of the structural and dynamic properties of the liquid and amorphous Li–Si alloys
J. Chem. Phys. (January 2016)
Brittle-to-ductile transition of lithiated silicon electrodes: Crazing to stable nanopore growth
J. Chem. Phys. (September 2015)
Lithium concentration dependent structure and mechanics of amorphous silicon
J. Appl. Phys. (June 2016)
Theoretical prediction of fracture conditions for delithiation in silicon anode of lithium ion battery
APL Mater. (October 2017)
Li diffusion in Si and LiSi: Nuclear quantum effects and anharmonicity
J. Chem. Phys. (June 2020)