Active learning and neural network potentials accelerate molecular screening of ether-based solvate ionic liquids.

Solvate ionic liquids (SIL) have promising applications as electrolyte materials. Despite the broad design space of oligoether ligands, most reported SILs are based on simple tri- and tetraglyme. Here, we describe a computational search for complex ethers that can better stabilize SILs. Through active learning, a neural network interatomic potential is trained from density functional theory data. The learned potential fulfills two key requirements: transferability across composition space, and high speed and accuracy to find low-energy ligand-ion poses across configurational space. Candidate ether ligands for Li+, Mg2+ and Na+ SILs with higher binding affinity and electrochemical stability than the reference compounds are identified. Lastly, their properties are related to the geometry of the coordination sphere.

• Publication year

  2020

• Venue

  Chemical Communications

• Publication date

  2020-05-18

• Fields of study

  Medicine, Materials Science, Chemistry

• Identifiers
  DOI 10.26434/chemrxiv.12317465PMID 32573576
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Solvate ionic liquids based on lithium bis(trifluoromethanesulfonyl)imide-glyme systems: coordination in MD simulations with scaled charges.

  2019cited by this paper
• Design of S-Substituted Fluorinated Aryl Sulfonamide-Tagged (S-FAST) Anions To Enable New Solvate Ionic Liquids for Battery Applications

  2019cited by this paper
• Less is more: sampling chemical space with active learning

  2018cited by this paper
• Insight into the Solvation Structure of Tetraglyme-Based Electrolytes via First-Principles Molecular Dynamics Simulation.

  2018cited by this paper
• Magnesium bis(trifluoromethanesulfonyl)amide complexes with triglyme and asymmetric homologues: phase behavior, coordination structures and melting point reduction.

  2018cited by this paper
• Solvation Structure of Sodium Bis(fluorosulfonyl)imide-Glyme Solvate Ionic Liquids and Its Influence on Cycling of Na-MNC Cathodes.

  2018cited by this paper
• Molecular dynamics study of thermodynamic stability and dynamics of [Li(glyme)]+ complex in lithium-glyme solvate ionic liquids.

  2018cited by this paper
• Johnston, Karen and Kleis, Jesper and Lundqvist, Bengt I. and Nieminen, Risto M. (2008) Influence of van der Waals forces on the adsorption structure of benzene on silicon studied using density functional theory. Physical Review B: Condensed Matter and Materials

  2018cited by this paper
• SchNet - A deep learning architecture for molecules and materials.

  2017cited by this paper
• Effect of Anion in Glyme-based Electrolyte for Li-O2 Batteries: Stability/Solubility of Discharge Intermediate

  2017cited by this paper
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

  2017cited by this paper
• The Solvation Structure of Lithium Ions in an Ether Based Electrolyte Solution from First-Principles Molecular Dynamics.

  2017cited by this paper
• Li(+) solvation in glyme-Li salt solvate ionic liquids.

  2015cited by this paper
• Convolutional Networks on Graphs for Learning Molecular Fingerprints

  2015cited by this paper
• Criteria for solvate ionic liquids.

  2014cited by this paper
• Solvate Ionic Liquid Electrolyte for Li–S Batteries

  2013cited by this paper
• Glyme-lithium salt equimolar molten mixtures: concentrated solutions or solvate ionic liquids?

  2012cited by this paper
• On representing chemical environments

  2012cited by this paper
• Oxidative-stability enhancement and charge transport mechanism in glyme-lithium salt equimolar complexes.

  2011cited by this paper
• Mathematica

  2011cited by this paper
• The fluid-mosaic model, homeoviscous adaptation, and ionic liquids: dramatic lowering of the melting point by side-chain unsaturation.

  2010cited by this paper
• Physicochemical Properties of Glyme–Li Salt Complexes as a New Family of Room-temperature Ionic Liquids

  2010cited by this paper
• Visualizing Data using t-SNE

  2008cited by this paper
• How to predict the physical properties of ionic liquids: a volume-based approach.

  2007cited by this paper
• Structural variation in copper(I) complexes with pyridylmethylamide ligands: structural analysis with a new four-coordinate geometry index, tau4.

  2007cited by this paper
• Practical Methods of Optimization: Fletcher/Practical Methods of Optimization

  2000cited by this paper
• Ion Transport in Cryptand and Crown Ether Lithium Salt Complexes

  1999cited by this paper
• Ring Strain Energies from ab Initio Calculations

  1998cited by this paper
• An NMR study of the stoichiometry and stability of lithium ion complexes with 12-crown-4, 15-crown-5 an 18-crown-6 in binary Acetonitrile-Nitrobenzene mixtures

  1996cited by this paper
• Journal of inclusion phenomena and molecular recognition in chemistry

  1989cited by this paper
• Nuclear magnetic resonance studies of some sodium ion complexes with crown ethers and [2]-cryptands in various solvents

  1981cited by this paper

• Structural and Transport Properties of LiTFSI/G3 Electrolyte with Machine-Learned Molecular Dynamics

  2025cites this paper
• Applying the active learning strategy to the construction of full-dimensional neural network potential energy surfaces: Critical tests in H2O-He spectroscopic calculation.

  2025cites this paper
• End-To-End Learning of Classical Interatomic Potentials for Benchmarking Anion Polarization Effects in Lithium Polymer Electrolytes

  2025cites this paper
• Exploring the potential of artificial intelligence and machine learning in healthcare: challenges and research directions

  2025cites this paper
• Coordination chemistry in advanced redox-active electrolyte designs

  2025cites this paper
• Assessing Uncertainty in Machine Learning for Polymer Property Prediction: A Benchmark Study

  2025cites this paper
• Progress of Machine Learning in Molecular Crystal Design and Crystallization Development

  2025cites this paper
• Machine-learned potentials for solvation modeling

  2025cites this paper
• Solvate ionic liquids: past, present and future

  2025cites this paper
• On the design space between molecular mechanics and machine learning force fields

  2024influential citation
• Active learning approaches in molecule pKi prediction

  2024cites this paper
• PAL – parallel active learning for machine-learned potentials

  2024cites this paper
• Machine learning potentials for metal-organic frameworks using an incremental learning approach

  2023cites this paper
• Exploring Optimal Water Splitting Bifunctional Alloy Catalyst by Pareto Active Learning

  2023cites this paper
• Understanding the solvation structures of glyme-based electrolytes by machine learning molecular dynamics

  2023cites this paper
• Reducing the Cost of Neural Network Potential Generation for Reactive Molecular Systems

  2023cites this paper
• Machine learning facilitating the rational design of nanozymes.

  2023cites this paper
• Effect of Framework Composition and NH3 on the Diffusion of Cu+ in Cu-CHA Catalysts Predicted by Machine-Learning Accelerated Molecular Dynamics

  2023cites this paper
• Machine Learning-Based Design of Ionic Liquids at the Atomic Scale for Highly Efficient CO2 Capture

  2023cites this paper
• Combining Molecular Modeling and Machine Learning for Accelerated Reaction Screening and Discovery.

  2023cites this paper
• Simulations with machine learning potentials identify the ion conduction mechanism mediating non-Arrhenius behavior in LGPS

  2022cites this paper
• FINETUNA: fine-tuning accelerated molecular simulations

  2022cites this paper
• Atomistic modelling approaches to understanding the interfaces of ionic liquid electrolytes for batteries and electrochemical devices

  2022cites this paper
• XGBoost model for electrocaloric temperature change prediction in ceramics

  2022cites this paper
• Prediction and Design of Cyclodextrin Inclusion Complexes formation via Machine Learning-based Strategies

  2022cites this paper
• Thermal Half-Lives of Azobenzene Derivatives: Virtual Screening Based on Intersystem Crossing Using a Machine Learning Potential

  2022cites this paper
• Human- and machine-centred designs of molecules and materials for sustainability and decarbonization

  2022cites this paper
• Predicting CO$_2$ Absorption in Ionic Liquids with Molecular Descriptors and Explainable Graph Neural Networks

  2022cites this paper
• Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations

  2022cites this paper
• Toward Autonomous Laboratories: Convergence of Artificial Intelligence and Experimental Automation

  2022cites this paper
• Fluorescent magnetic ionic liquids with multi-responses to temperature, humidity and organic vapors

  2021cites this paper
• Dreams, False Starts, Dead Ends, and Redemption: A Chronicle of the Evolution of a Chemoinformatic Workflow for the Optimization of Enantioselective Catalysts.

  2021cites this paper
• Adversarial Attacks on Uncertainty Enable Active Learning for Neural Network Potentials

  2021cites this paper
• Text Mining of Hazard and Operability Analysis Reports Based on Active Learning

  2021cites this paper
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks

  2021cites this paper
• Excited state non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential

  2021influential citation
• A review on machine learning algorithms for the ionic liquid chemical space

  2021cites this paper
• An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming

  2021cites this paper
• An orbital-based representation for accurate quantum machine learning.

  2021cites this paper
• Automated Construction of Neural Network Potential Energy Surface: The Enhanced Self-Organizing Incremental Neural Network Deep Potential Method

  2021cites this paper
• Screening and Understanding Li Adsorption on Two-Dimensional Metallic Materials by Learning Physics and Physics-Simplified Learning

  2020cites this paper
• Computational methods for training set selection and error assessment applied to catalyst design: guidelines for deciding which reactions to run first and which to run next

  2020cites this paper
• Bias free multiobjective active learning for materials design and discovery

  2020cites this paper
• TorchMD: A Deep Learning Framework for Molecular Simulations

  2020cites this paper