Multiscale prediction of functional self-assembled materials using machine learning: high-performance surfactant molecules

Abstract

Various physical properties of functional materials can be induced by controlling their chemical molecular structures. Therefore, molecular design is crucial in the fields of engineering and materials science. With its remarkable development in various fields, machine learning combined with molecular simulation has recently been found to be effective at predicting the electronic structure of materials (Nat. Commun., 2017, 8, 872 and Nat. Commun., 2017, 8, 13890). However, previous studies have used similar microscale information as input and output data for machine learning, i.e., molecular structures and electronic structures. In this study, we determined whether multiscale data can be predicted using machine learning via a self-assembly functional material system. In particular, we investigated whether machine learning can be used to predict dispersion and viscosity, as the representative physical properties of a self-assembled surfactant solution, from the chemical molecular structures of a surfactant. The results showed that relatively accurate information on these physical properties can be predicted from the molecular structure, suggesting that machine learning can be used to predict multiscale systems, such as surfactant molecules, self-assembled micelle structures, and physical properties of solutions. The results of this study will aid in further development of the application of machine learning to materials science and molecular design.

Theoretical analyses on water cluster structures in polymer electrolyte membrane by using dissipative particle dynamics simulations with fragment molecular orbital based effective parameters

“…Very recently, Inokuchi et al published an interesting paper in which DPD results of surfactants were analyzed and predicted by machine learning (ML) techniques. 100 The combination of DPD and ML should be suggestive for our future works. Finally, we would note that the sequenced protocols to evaluate a set of χ parameters through the FMO calculations has been packaged as a workflow system (FCEWS, FMO-based Chi-parameter Evaluation System).…”

Numerical simulation, clustering, and prediction of multicomponent polymer precipitation

“…ML has also been used to improve the accuracy of physical simulations by enabling the development of data-driven closures (Duraisamy et al, 2019) andmodels (Chmiela et al, 2017), which can capture more data than traditional first principles or empirical models. Within the material sciences, ML has similarly found increasing use in a variety of cases ranging from the prediction of macroscopic self-assembled structures using molecular properties (Inokuchi et al, 2018) to the prediction of novel permanent magnets (Möller et al, 2018) and in the optimization of alloy properties (Ward et al, 2018).…”

Toward the Prediction of Multi-Spin State Charges of a Heme Model by Random Forest Regression

“…In recent years, many efforts have been directed to the efficient improvement of force fields. In particular, machine learning combined with molecular simulation has been verified by many groups to be effective to develop force field including inferring charges based on a set of reference molecules (Botu et al, 2016;Chen et al, 2018;Inokuchi et al, 2018;Engler et al, 2019;Hu et al, 2019;Roman et al, 2019;Sanvito, 2019;Unke and Meuwly, 2019;Ye et al, 2019). Among these, the random forest regression (RFR) method has been proven to be feasible for the prediction of atomic charge without expending much effort on parameter tuning or descriptor selection.…”