Abstract
In data-intensive science, machine learning plays a critical role in processing big data. However, the potential of machine learning has been limited in the field of materials science because of the difficulty in treating complex real-world information as a digital language. Here, we propose to use graph-shaped databases with a common format to describe almost any materials science experimental data digitally, including chemical structures, processes, properties, and natural languages. The graphs can express real world’s data with little information loss. In our approach, a single neural network treats the versatile materials science data collected from over ten projects, whereas traditional approaches require individual models to be prepared to process each individual database and property. The multitask learning of miscellaneous factors increases the prediction accuracy of parameters synergistically by acquiring broad knowledge in the field. The integration is beneficial for developing general prediction models and for solving inverse problems in materials science.
Highlights
In data-intensive science, machine learning plays a critical role in processing big data
All related information from more than ten projects was inputted into a single neural network to predict more than 40 parameters simultaneously, including numeric properties, chemical structures, and text (Fig. 1)
As a model case to demonstrate the effect of the graph format, we examined the process informatics of poly(3,4-ethylenedioxythiophene) doped with poly(4-styrenesulfonate) (PEDOT-PSS; Fig. 3)
Summary
In data-intensive science, machine learning plays a critical role in processing big data. We propose to use graph-shaped databases with a common format to describe almost any materials science experimental data digitally, including chemical structures, processes, properties, and natural languages. Integration of data by machine learning is important in materials science New devices, such as nextgeneration batteries and photovoltaics, could be developed more efficiently by automatically exploring materials with superior properties, chemical structures, and processes[4,5]. The models could not perform essential tasks that are easy for humans, such as learning, considering, and predicting multiple real-world phenomena with a single intelligence This limitation arises from the use of traditional, inflexible table databases. All related information from more than ten projects was inputted into a single neural network to predict more than 40 parameters simultaneously, including numeric properties, chemical structures, and text (Fig. 1). Our graph approach will be the key to developing general-purpose artificial intelligence for materials science, including inverse problem solving
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
