Text-mined dataset of inorganic materials synthesis recipes

Abstract

Materials discovery has become significantly facilitated and accelerated by high-throughput ab-initio computations. This ability to rapidly design interesting novel compounds has displaced the materials innovation bottleneck to the development of synthesis routes for the desired material. As there is no a fundamental theory for materials synthesis, one might attempt a data-driven approach for predicting inorganic materials synthesis, but this is impeded by the lack of a comprehensive database containing synthesis processes. To overcome this limitation, we have generated a dataset of “codified recipes” for solid-state synthesis automatically extracted from scientific publications. The dataset consists of 19,488 synthesis entries retrieved from 53,538 solid-state synthesis paragraphs by using text mining and natural language processing approaches. Every entry contains information about target material, starting compounds, operations used and their conditions, as well as the balanced chemical equation of the synthesis reaction. The dataset is publicly available and can be used for data mining of various aspects of inorganic materials synthesis.

A database of battery materials auto-generated using ChemDataExtractor

“…For instance, chemical names containing special symbols, or ending with abnormal words such as “mole”, were cleaned from the database. All of these chemical names were then normalised by ChemDataExtractor as well as a materials parser 31 , so that these chemicals can be presented as elements and the number of these elements, which make it easier to process for a future prediction task. The chemical compounds that could not be normalised were all removed.…”

The Devices, Experimental Scaffolds, and Biomaterials Ontology (DEB): A Tool for Mapping, Annotation, and Analysis of Biomaterials Data

“…Algorithms used in machine learning systems and artificial intelligence (AI) can only be as good as the data used for their development, [ 29 ] and getting good quality annotated data is a well‐known bottleneck for applying those techniques. With knowledge in the biomaterials domain continuously expanding, efforts to mine data from published studies are already being made in sub‐areas such as inorganic materials [ 30,31 ] and polymers, [ 32 ] and the potential value of text mining in the biomaterial domain is clear. Thus, the aim of this study was to develop a biomaterials ontology to facilitate information extraction in the domain.…”

Prospects for lithium-ion batteries and beyond—a 2030 vision

“…Subsequent structure prediction activities have generated many (meta)stable structures, but the challenge remains to identify structures that are stable on cycling, for example to oxygen loss particularly at the top of charge, or more generally, to structural reorganisations. Even if a structure is predicted, it is not currently easy to predict if and how they can be synthesised 12 .…”