Prediction and Optimization of Ion Transport Characteristics in Nanoparticle-Based Electrolytes Using Convolutional Neural Networks.

Sanket Kadulkar,Michael P Howard,Venkat Ganesan,Thomas M Truskett

doi:10.1021/acs.jpcb.1c02004

Sanket Kadulkar, Michael P Howard + Show 2 more

https://doi.org/10.1021/acs.jpcb.1c02004

Copy DOI

Export

Save

Cite

Abstract
Highlights/Summary
Full-Text
Similar Papers

Abstract

Listen

We develop a convolutional neural network (CNN) model to predict the diffusivity of cations in nanoparticle-based electrolytes and use it to identify the characteristics of morphologies that exhibit optimal transport properties. The ground truth data are obtained from kinetic Monte Carlo (kMC) simulations of cation transport parametrized using a multiscale modeling strategy. We implement deep learning approaches to quantitatively link the diffusivity of cations to the spatial arrangement of the nanoparticles. We then integrate the trained CNN model with a topology optimization algorithm for accelerated discovery of nanoparticle morphologies that exhibit optimal cation diffusivities at a specified nanoparticle loading, and we investigate the ability of the CNN model to quantitatively account for the influence of interparticle spatial correlations on cation diffusivity. Finally, by using data-driven approaches, we explore how simple descriptors of nanoparticle morphology correlate with cation diffusivity, thus providing a physical rationale for the observed optimal microstructures. The results of this study highlight the capability of CNNs to serve as surrogate models for structure-property relationships in composites with monodisperse spherical particles, which can in turn be used with inverse methods to discover morphologies that produce optimal target properties.

Highlights

Nanocomposites comprising spherical nanoparticles dispersed in polymeric matrices or liquid hosts have emerged as a promising class of materials for a broad range of applications
We develop a convolutional neural network (CNN) model to predict the diffusivity of cations in nanoparticle-based electrolytes, and use it to identify the characteristics of morphologies which exhibit optimal transport properties
We observe that the CNN model predicts the cation diffusivity for the unseen microstructures in the testing set with high accuracy

Summary

Introduction

Nanocomposites comprising spherical nanoparticles dispersed in polymeric matrices or liquid hosts have emerged as a promising class of materials for a broad range of applications. Jana and coworkers reported polybenzimidazole nanocomposite systems with morphologydependent proton conduction[13,14,15] and storage modulus[14] properties at a fixed nanoparticle loading. In their studies, the characteristic structure of the dispersed nanoparticles was altered by modifying the nanoparticle surface with various functional groups. Akcora et al 16 reported tunability in mechanical properties of polymer nanocomposites at a fixed nanoparticle volume fraction by varying the grafting density and molecular weight of tethered chains, and attributed such behavior to the resulting modulation of the nanoparticles’ self-assembled structure. A recent mesoscale simulation study of ours[17] highlighted the potential for modifying nanoparticles structure to significantly influence the tracer diffusivity through nanocomposite gels in the presence of interface-assisted transport pathways

Objectives

Results

Conclusion