Abstract
Scientists who design chemical substances often use materials informatics (MI), a data-driven approach with either computer simulation or artificial intelligence (AI). MI is a valuable technique, but applying it to layered structures is difficult. Most of the proposed computer-aided material search techniques use atomic or molecular simulations, which are limited to small areas. Some AI approaches have planned layered structures, but they require a physical theory or abundant experimental results. There is no universal design tool for multilayer films in MI. Here, we show a multilayer film can be designed through machine learning (ML) of experimental procedures extracted from chemical-coating articles. We converted material names according to International Union of Pure and Applied Chemistry rules and stored them in databases for each fabrication step without any physicochemical theory. Compared with experimental results which depend on authors, experimental protocol is superiority at almost unified and less data loss. Connecting scientific knowledge through ML enables us to predict untrained film structures. This suggests that AI imitates research activity, which is normally inspired by other scientific achievements and can thus be used as a general design technique.
Highlights
We prepared training data using the following procedures: First, layered structures (= 300) and functionalities (= 26) were stored in the Film_DB by hand (see Fig. 2, Table S1 and S3)
Machine learning method for multilayer functional films. (a) Starting from substrate, CNNWs estimate upper layer’s material on down layer, and this procedure is repeated until the end of outermost surface. (b) Strongly connect scientific knowledge such as antifouling films with different specialties. (c) Whole system for learning and inference. d, Summary of training datasets and neural network (NNW) structures
To estimate multilayer functional film by machine learning (ML), we propose CNNWs, a cascade connection of multiple NNWs
Summary
We prepared training data using the following procedures: First, layered structures (= 300) and functionalities (= 26) were stored in the Film_DB by hand (see Fig. 2, Table S1 and S3). After classifying 297 structures for training and three untrained structures as test samples for hold-out validation (see section S5), it learned the material pairs in 5,422 data derived from 297 structures. 47.5% of material pairs from 5422 training data had film-forming properties.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
