Situation analysis of domestic geological big data research based on bibliometrics

Based on the relevant papers collected in CNKI database from 2012 to 2022, this paper makes a scientometric analysis of the research in the field of geological big data in China, in order to provide reference for the relevant management departments and the general peers to understand the development trend and evolution of domestic geological big data research in the past decade. The results show that geological big data research has received more attention after 2015, and is currently in a stable and high-yield period. There are three research institution networks with the largest number of publications and the greatest influence, the core of which are the Development Research Center of China Geological Survey, China University of Geosciences（Beijing） and China University of Geosciences（Wuhan）. Co-occurrence analysis shows that 1 large and 4 small groups of authors have been formed, but the core group of authors in this field has not yet been formed. The main research hotspots are geological big data storage and management, geological big data mining process and algorithm research, geological big data application. Among them, the geological big data mining methods represented by machine learning and deep learning have the highest research heat and the most achievements. The hot areas of geological big data application exploration mainly include intelligent geological survey, mineral resource prediction, geochemistry, geological disaster warning, and intelligent resource mining. The research hotspots in this field have undergone three distinct developmental phases: the technology exploration phase （2013-2015）, primarily focusing on preliminary applications of big data technologies in geological hazard early warning and mineral resource prediction; the platformization and data governance phase （2016-2018）, where research emphasis shifted toward standardized integration of geological data and cloud platform development, establishing geological big data platforms based on distributed computing technologies such as Hadoop and Spark to facilitate data sharing and collaborative analysis; and the intelligent integration phase （2019-2022）, during which research advanced into an intelligent development stage centered on deep learning and geoscience knowledge graphs, forming a “data-knowledge” dual-driven research paradigm. The current research frontier focuses on multi-modal data fusion, hybrid modeling approaches, and collaborative intelligent technologies, marking a transformative trend in geospatial big data toward intelligence, knowledge-driven processing, and collaboration.