Prediction of solar‐chargeable battery materials: A text‐mining and first‐principles investigation

Abstract

Photo-rechargeable batteries utilize the solar energy to wirelessly charge the lithium-ion batteries, which are feasible to realize more portable electric vehicles and electronic devices. However, the photo-rechargeable battery materials are scarce and the search for the potential photo-rechargeable battery materials that are capable of simultaneous light-responsiveness and lithium-ion storage is critical. In this manuscript, we employ a novel material discovery process combining the text-mining and first-principles investigation to identify and evaluate the potential photo-battery material candidates via unsupervised learning of the materials science literature. The text-mining process extracts useful information from the literature, detects possible materials reported in the papers that are previously unknown to the photo-rechargeable battery application, and establishes the hidden relationships between the chemical names and their applicability to the photo-rechargeable battery materials. New potential photo-rechargeable battery materials are proposed. The present study highlights the importance of the text-mining method for the energy conversion and storage applications, and provides a rational design strategy to develop novel energy materials.

Fast Exploring Literature by Language Machine Learning for Perovskite Solar Cell Materials Design

“…More information regarding the details of the preprocessing, named‐entity recognition, and the model construction steps can be found in the literature. [ 37 ]…”

“…[18] Zhang et al employed the text mining method to explore new energy materials and identify several potential high-performance photo-rechargeable materials that were verified via first-principle calculations. [19,20] Inverse materials design is highly desired for the materials discovery process. [21] Historically, the typical materials-design period from laboratory discovery to commercial product is 15 to 20 years.…”

“…[ 18 ] Zhang et al employed the text mining method to explore new energy materials and identify several potential high‐performance photo‐rechargeable materials that were verified via first‐principle calculations. [ 19,20 ]…”

BatteryDataExtractor: battery-aware text-mining software embedded with BERT models

“…[23][24][25][26][27] Apart from data extraction, text mining can also assist in the reviewing of research trends [28][29][30] and provide latent scientic information using unsupervised ML methods. [31][32][33] In order to improve the efficiency and effectiveness of literature mining and adapt it to a specic materials domain such as batteries, several studies have been dedicated to the development of the chemistry-aware toolkit, e.g. ChemDataExtractor 34,35 and PDFDataExtractor, 36 whose functionalities are based on NLP and ML algorithms.…”

“…23–27 Apart from data extraction, text mining can also assist in the reviewing of research trends 28–30 and provide latent scientific information using unsupervised ML methods. 31–33…”