Prediction of High Performance Surfactant Molecules using Machine Learning and Coarse-grained Molecular Simulation
Year: 2018
Type: article
Abstract: The success of machine learning combined with molecular simulation has been demonstrated in predicting electronic structure of materials(1)(2). A breakthrough that can aid in the design of new molecules that can be used to enhance the performance of material science. However, the prediction of physical properties of functional materials is one of the most challenging issue because of a multiscale problem across scientific disciplines in soft matter systems(3). In this study, first we used the coarse-grained molecular simulation to solve the multiscale problem. Second, we determined whether machine learning can be used to predict dispersion and viscosity, as the representative physical properties of 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 will aid in further our scientific understanding and gain new insights(4).
Authors: Na LI, Kei MOROHOSHI, Takuya INOKUCHI, Noriyoshi ARAI
Institutions: Toyota Motor Corporation (Japan), Kindai University
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W2945217697