Construction and Application of Materials Knowledge Graph Based on Author Disambiguation: Revisiting the Evolution of LiFePO₄

Abstract

Due to the recent innovations in computer technology, the emerging field of materials informatics has now become a catalyst for a revolution of the research paradigm in materials science. Knowledge graphs, which provide support for knowledge management, are able to collectively capture the scientific knowledge from the vast collection of research articles and accomplish the automatic recognition of the relationships between entities. In this work, a materials knowledge graph, named MatKG, is constructed, which establishes a unique correspondence between subjects and objects in the materials science area. An emphasis is placed on the disambiguation of authors, addressed by a deduplication model based on machine learning and matching dependencies algorithms. Specifically, MatKG is applied to perform tracking on research trends in the study of LiFePO4 and to automatically chronicle the milestones achieved so far. It is believed that MatKG can serve as a versatile research platform for amalgamating and refining the scientific knowledge of materials in a variety of subfields and intersectional domains.

Scholarly knowledge graphs through structuring scholarly communication: a review

“…Furthermore, bottom-up approaches are used to construct the knowledge graph using machine learning techniques in which, text mining and analytic is important step to implement. MatKG [ 61 ] framework is constructed using Naive Bayes Classifier to disambiguate authors. Similarly, statistical method is applied on geoscience literature to construct knowledge graph [ 62 ] in order to represent key facts in structured manner.…”

Function Decomposition Tree with Causality-First Perspective and Systematic Description of Problems in Materials Informatics

“…Studies on a citation map [9] have considered other entities, such as material properties, as well as the citation relationship. [10] One study aimed to understand the correlation of entities (properties) from the data [11] which makes it easy to understand the relationship between properties. Some studies use ontologies to organize relationships.…”

Encoding the atomic structure for machine learning in materials science

“…This is the era of big data where data‐driven innovation has entered the spotlight of scientific research. In the field of materials science, numerous kinds of experimental and computational data are accumulated on the structures and properties (e.g., physical, chemical, electronic, mechanical, thermodynamic) of different compounds 1–7 . Now that we have a pool of over 190,000 inorganic compounds from the Inorganic Crystal Structure Database 8 and millions of organic compounds contained in a number of databases (such as ZINC, 9 ChEMBL, 10 and PubChem 11 ), it is time to consider the question of how to manage and utilize these material datasets to identify new science.…”