skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Suppression of Dendrite Formation in Lithium Metal Anodes

Abstract

Next generation batteries based on lithium (Li) metal anodes have been plagued by the dendritic electrodeposition of Li metal on the anode during cycling, resulting in short circuit and capacity loss. Suppression of dendritic growth through the use of solid electrolytes has emerged as one of the most promising strategies for enabling the use of Li metal anodes. We perform a computational screening of over 12 000 inorganic solids based on their ability to suppress dendrite initiation in contact with Li metal anode. Properties for mechanically isotropic and anisotropic interfaces that can be used in stability criteria for determining the propensity of dendrite initiation are usually obtained from computationally expensive first-principles methods. In order to obtain a large data set for screening, we use machine-learning models to predict the mechanical properties of several new solid electrolytes. The machine-learning models are trained on purely structural features of the material, which do not require any first-principles calculations. We train a graph convolutional neural network on the shear and bulk moduli because of the availability of a large training data set with low noise due to low uncertainty in their first-principles-calculated values. We use gradient boosting regressor and kernel ridge regression to trainmore » the elastic constants, where the choice of the model depends on the size of the training data and the noise that it can handle. The material stiffness is found to increase with an increase in mass density and ratio of Li and sublattice bond ionicity, and decrease with increase in volume per atom and sublattice electronegativity. Cross-validation/test performance suggests our models generalize well. We predict over 20 mechanically anisotropic interfaces between Li metal and four solid electrolytes which can be used to suppress dendrite growth. Our screened candidates are generally soft and highly anisotropic, and present opportunities for simultaneously obtaining dendrite suppression and high ionic conductivity in solid electrolytes.« less

Authors:
ORCiD logo [1]; ORCiD logo [2];  [1];  [2]; ORCiD logo [3]
  1. Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States
  2. Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
  3. Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States, Department of Physics, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States
Publication Date:
Research Org.:
24M Technologies, Inc., Cambridge, MA (United States); Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); Carnegie Mellon Univ., Pittsburgh, PA (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Office of Sustainable Transportation. Vehicle Technologies Office (VTO); USDOE Advanced Research Projects Agency - Energy (ARPA-E); USDOE Office of Energy Efficiency and Renewable Energy (EERE), Vehicle Technologies Office (EE-3V)
OSTI Identifier:
1463941
Alternate Identifier(s):
OSTI ID: 1498672; OSTI ID: 1508613
Grant/Contract Number:  
EE0007810; AR0000774
Resource Type:
Journal Article: Published Article
Journal Name:
ACS Central Science
Additional Journal Information:
Journal Name: ACS Central Science Journal Volume: 4 Journal Issue: 8; Journal ID: ISSN 2374-7943
Publisher:
American Chemical Society
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE

Citation Formats

Ahmad, Zeeshan, Xie, Tian, Maheshwari, Chinmay, Grossman, Jeffrey C., and Viswanathan, Venkatasubramanian. Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Suppression of Dendrite Formation in Lithium Metal Anodes. United States: N. p., 2018. Web. doi:10.1021/acscentsci.8b00229.
Ahmad, Zeeshan, Xie, Tian, Maheshwari, Chinmay, Grossman, Jeffrey C., & Viswanathan, Venkatasubramanian. Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Suppression of Dendrite Formation in Lithium Metal Anodes. United States. https://doi.org/10.1021/acscentsci.8b00229
Ahmad, Zeeshan, Xie, Tian, Maheshwari, Chinmay, Grossman, Jeffrey C., and Viswanathan, Venkatasubramanian. 2018. "Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Suppression of Dendrite Formation in Lithium Metal Anodes". United States. https://doi.org/10.1021/acscentsci.8b00229.
@article{osti_1463941,
title = {Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Suppression of Dendrite Formation in Lithium Metal Anodes},
author = {Ahmad, Zeeshan and Xie, Tian and Maheshwari, Chinmay and Grossman, Jeffrey C. and Viswanathan, Venkatasubramanian},
abstractNote = {Next generation batteries based on lithium (Li) metal anodes have been plagued by the dendritic electrodeposition of Li metal on the anode during cycling, resulting in short circuit and capacity loss. Suppression of dendritic growth through the use of solid electrolytes has emerged as one of the most promising strategies for enabling the use of Li metal anodes. We perform a computational screening of over 12 000 inorganic solids based on their ability to suppress dendrite initiation in contact with Li metal anode. Properties for mechanically isotropic and anisotropic interfaces that can be used in stability criteria for determining the propensity of dendrite initiation are usually obtained from computationally expensive first-principles methods. In order to obtain a large data set for screening, we use machine-learning models to predict the mechanical properties of several new solid electrolytes. The machine-learning models are trained on purely structural features of the material, which do not require any first-principles calculations. We train a graph convolutional neural network on the shear and bulk moduli because of the availability of a large training data set with low noise due to low uncertainty in their first-principles-calculated values. We use gradient boosting regressor and kernel ridge regression to train the elastic constants, where the choice of the model depends on the size of the training data and the noise that it can handle. The material stiffness is found to increase with an increase in mass density and ratio of Li and sublattice bond ionicity, and decrease with increase in volume per atom and sublattice electronegativity. Cross-validation/test performance suggests our models generalize well. We predict over 20 mechanically anisotropic interfaces between Li metal and four solid electrolytes which can be used to suppress dendrite growth. Our screened candidates are generally soft and highly anisotropic, and present opportunities for simultaneously obtaining dendrite suppression and high ionic conductivity in solid electrolytes.},
doi = {10.1021/acscentsci.8b00229},
url = {https://www.osti.gov/biblio/1463941}, journal = {ACS Central Science},
issn = {2374-7943},
number = 8,
volume = 4,
place = {United States},
year = {Fri Aug 10 00:00:00 EDT 2018},
month = {Fri Aug 10 00:00:00 EDT 2018}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record at https://doi.org/10.1021/acscentsci.8b00229

Citation Metrics:
Cited by: 114 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1 Figure 1: Parity plots comparing the elastic properties: (a) shear modulus G, and elastic constants (b) C11, (c) C12, and (d) C44 predicted by the machine-learning models to the DFT-calculated values. The shear modulus is predicted using CGCNN, and the elastic constants C11 and C44 are predicted using gradient boostingmore » regression while C12 is predicted using kernel ridge regression. The parity plot for shear modulus is on 680 test data points while that for the elastic constants contains all available data (170 points) where each prediction is a cross-validated value.« less

Save / Share:

Works referenced in this record:

A Critical Review of Li∕Air Batteries
journal, January 2012


Generalized Gradient Approximation Made Simple
journal, October 1996


Review—Practical Challenges Hindering the Development of Solid State Li Ion Batteries
journal, January 2017


Transparent cubic garnet-type solid electrolyte of Al2O3-doped Li7La3Zr2O12
journal, October 2015


A sulphide lithium super ion conductor is superior to liquid ion conductors for use in rechargeable batteries
journal, January 2014


Stability of Electrodeposition at Solid-Solid Interfaces and Implications for Metal Anodes
journal, August 2017


All-Solid-State Lithium-Sulfur Battery Based on a Nanoconfined LiBH 4 Electrolyte
journal, January 2016


Dendrite-Free Lithium Deposition with Self-Aligned Nanorod Structure
journal, November 2014


A tutorial on support vector regression
journal, August 2004


Ultrathin Two-Dimensional Atomic Crystals as Stable Interfacial Layer for Improvement of Lithium Metal Anode
journal, September 2014


Performance Metrics Required of Next-Generation Batteries to Make a Practical Electric Semi Truck
journal, June 2017


Revised effective ionic radii and systematic studies of interatomic distances in halides and chalcogenides
journal, September 1976


Charting the complete elastic properties of inorganic crystalline compounds
journal, March 2015


Solid Electrolyte: the Key for High-Voltage Lithium Batteries
journal, October 2014


Lithium superionic conduction in lithium borohydride accompanied by structural transition
journal, November 2007


The Mechanism of the Dendritic Electrocrystallization of Zinc
journal, January 1969


Understanding Ionic Conductivity Trends in Polyborane Solid Electrolytes from Ab Initio Molecular Dynamics
journal, December 2016


Factors Which Limit the Cycle Life of Rechargeable Lithium (Metal) Batteries
journal, January 2000


A lithium superionic conductor
journal, July 2011


Artificial Protection Film on Lithium Metal Anode toward Long-Cycle-Life Lithium-Oxygen Batteries
journal, August 2015


Strong texturing of lithium metal in batteries
journal, October 2017


Ionic conductivity in Li5AlO4 and LiOH
journal, June 1977


The crystallographic information file (CIF): a new standard archive file for crystallography
journal, November 1991


Liquid‐Like Ionic Conduction in Solid Lithium and Sodium Monocarba‐ closo ‐Decaborates Near or at Room Temperature
journal, February 2016


The high-throughput highway to computational materials design
journal, February 2013


A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
journal, August 1997


High-power all-solid-state batteries using sulfide superionic conductors
journal, March 2016


XSEDE: Accelerating Scientific Discovery
journal, September 2014


Dynamics of Lithium Dendrite Growth and Inhibition: Pulse Charging Experiments and Monte Carlo Calculations
journal, May 2014


Evaluation of Current, Future, and Beyond Li-Ion Batteries for the Electrification of Light Commercial Vehicles: Challenges and Opportunities
journal, January 2017


Toward Safe Lithium Metal Anode in Rechargeable Batteries: A Review
journal, July 2017


The Impact of Elastic Deformation on Deposition Kinetics at Lithium/Polymer Interfaces
journal, January 2005


Materials discovery and design using machine learning
journal, September 2017


Suppression of Dendrite Formation via Pulse Charging in Rechargeable Lithium Metal Batteries
journal, December 2012


Necessary and sufficient elastic stability conditions in various crystal systems
journal, December 2014


Towards High-Safe Lithium Metal Anodes: Suppressing Lithium Dendrites via Tuning Surface Energy
journal, July 2016


Lithium metal anodes for rechargeable batteries
journal, January 2014


Enhanced strength and temperature dependence of mechanical properties of Li at small scales and its implications for Li metal anodes
journal, December 2016


Predicting the Mechanical Properties of Zeolite Frameworks by Machine Learning
journal, August 2017


Stabilizing electrodeposition in elastic solid electrolytes containing immobilized anions
journal, July 2016


Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
journal, January 2018


machine.
journal, October 2001


The Effect of Interfacial Deformation on Electrodeposition Kinetics
journal, January 2004


Dislocations and Cracks in Anisotropic Elasticity
journal, June 1958


Accelerating materials property predictions using machine learning
journal, September 2013


Bridges: a uniquely flexible HPC resource for new communities and data analytics
conference, January 2015

  • Nystrom, Nicholas A.; Levine, Michael J.; Roskies, Ralph Z.
  • Proceedings of the 2015 XSEDE Conference on Scientific Advancements Enabled by Enhanced Cyberinfrastructure - XSEDE '15
  • https://doi.org/10.1145/2792745.2792775

Design principles for solid-state lithium superionic conductors
journal, August 2015


An Empirical, yet Practical Way To Predict the Band Gap in Solids by Using Density Functional Band Structure Calculations
journal, August 2017


Resolution of the Modulus versus Adhesion Dilemma in Solid Polymer Electrolytes for Rechargeable Lithium Metal Batteries
journal, January 2012


Statistical geometrical approach to random packing density of equal spheres
journal, November 1974


Elastic Properties of Alkali Superionic Conductor Electrolytes from First Principles Calculations
journal, November 2015


Holistic computational structure screening of more than 12 000 candidates for solid lithium-ion conductor materials
journal, January 2017


Bayesian Interpolation
journal, May 1992


A solid future for battery development
journal, September 2016


Consequences of air exposure on the lithiated graphite SEI
journal, August 2013


Reviving the lithium metal anode for high-energy batteries
journal, March 2017


Suppression of Lithium Dendrite Growth Using Cross-Linked Polyethylene/Poly(ethylene oxide) Electrolytes: A New Approach for Practical Lithium-Metal Polymer Batteries
journal, May 2014


Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013


Solubility of Lithium Salts Formed on the Lithium-Ion Battery Negative Electrode Surface in Organic Solvents
journal, January 2009


Impact of air exposure and surface chemistry on Li–Li 7 La 3 Zr 2 O 12 interfacial resistance
journal, January 2017


Microstructure and its relaxation in FeB amorphous system simulated by moleculular dynamics
journal, June 1993


Misconceptions of Electric Aircraft and their Emerging Aviation Markets
conference, January 2014


Dendrite-Free Lithium Deposition via Self-Healing Electrostatic Shield Mechanism
journal, March 2013


Steady State Problems in Anisotropic Elasticity
journal, April 1962


Design principles for electrolytes and interfaces for stable lithium-metal batteries
journal, September 2016


All solid-state polymer electrolytes for high-performance lithium ion batteries
journal, October 2016


Accelerated Materials Design of Lithium Superionic Conductors Based on First-Principles Calculations and Machine Learning Algorithms
journal, April 2013


Unparalleled lithium and sodium superionic conduction in solid electrolytes with large monovalent cage-like anions
journal, January 2015


Fluoroethylene Carbonate Additives to Render Uniform Li Deposits in Lithium Metal Batteries
journal, January 2017


A new class of Solvent-in-Salt electrolyte for high-energy rechargeable metallic lithium batteries
journal, February 2013


Effect of Additives on Lithium Cycling Efficiency
journal, January 1994


Dendrite Growth in Lithium/Polymer Systems
journal, January 2003


Universal fragment descriptors for predicting properties of inorganic crystals
journal, June 2017


Halide-Stabilized LiBH 4 , a Room-Temperature Lithium Fast-Ion Conductor
journal, January 2009


Status and challenges in enabling the lithium metal electrode for high-energy and low-cost rechargeable batteries
journal, December 2017


Lithium battery chemistries enabled by solid-state electrolytes
journal, February 2017


Stable lithium electrodeposition in liquid and nanoporous solid electrolytes
journal, August 2014


Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis
journal, February 2013


High rate and stable cycling of lithium metal anode
journal, February 2015


Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.