Loading...
Welcome to Geological Journal of China Universities ! Today is
Share:

Table of Content

    20 June 2023, Volume 29 Issue 3
    One-stop Sharing and Service System for Geoscience Knowledge Graph
    ZHU Yunqiang, DAI Xiaoliang, YANG Jie, WANG Shu, SUN Kai, QIU Qinjun, LI Weirong, QI Yanmin, HU Lei, LYU Hairong, WANG Xinbing, ZHOU Chenghu
    2023, 29(3):  325-336.  DOI: 10.16108/j.issn1006-7493.2023029
    Asbtract ( 1478 )   PDF (7167KB) ( 1058 )  
    Related Articles | Metrics
    As the most effective way of knowledge organization and service at present, knowledge graph has become the cornerstone of artificial intelligence and has been widely used in semantic search, machine translation, information recommendation and so on. In the era of big data, there is an urgent need of Geoscience knowledge graphs for integrating, mining and analysis of scattered, multi-source and heterogeneous Geo-data and its unknown knowledge intelligent discovery. To promote the construction and application of Geoscience knowledge graphs, the Deep-time Digital Earth (DDE) International Big Science Program has taken knowledge graph as its one of the core research contents since its launch in 2019. After more than three years of construction, DDE has built a large number of Geoscience knowledge graphs, and it strong needs one-stop sharing and service system of these knowledge graphs. Firstly, this paper introduces the content framework, composition as well as characteristics of the DDE knowledge graphs. On this basis, the design of the one-stop sharing and service system for the Geoscience knowledge graph is designed that include the design of the system functional and technical architecture. Finally, the development and operation environment & tools, and key technologies of the system are discussed in detail. The practice has proved that the system can effectively realize the one-stop sharing and open access of DDE knowledge graphs. Meanwhile, it sets an example for other fields or domains’ knowledge graph integrating and sharing systems.
    Spatial Entity-Text Information Matching for Geological Surveys Based on Siamese Network with Attention Mechanism
    QIU Qinjun, MA Kai, XIE Zhong, TAO Liufeng, HUANG Bo
    2023, 29(3):  337-344.  DOI: 10.16108/j.issn1006-7493.2023025
    Asbtract ( 901 )   PDF (1534KB) ( 485 )  
    Related Articles | Metrics
    Association matching of geological objects with different sources and representation of their structures, attributes and semantic relationships by models is an important support for later tasks such as semantic query and clustering. In this paper, we propose a twin network geological survey spatial entities and text description information association matching model based on attention mechanism for the problems of semantic heterogeneity and expression differences between geological survey spatial entities and external text descriptions. First, the attribute information of geological survey spatial entities is converted into text paragraphs, and the text semantics of geological spatial entities is encoded with the basic granularity of sentence vectors; then the two types of text objects are mapped into a unified vector space and input to the twin network for feature learning, and finally the experimental evaluation of model performance is conducted on the constructed real dataset. The results demonstrate that the model can better represent the sentence semantic information of geological survey spatial entities, and its recognition F1 value is improved by 8.4 percentage points compared with the benchmark experiment, which is better than the selected comparison method.
    Construction and Application of Lithofacies Paleogeography Knowledge Graphs
    ZHANG Jiajia, ZHANG Lei, ZHONG Hanting, WANG Han, CHEN Anqing, LI Fengjie, REN Qiang, ZHENG Dongyu, ZHAO Hongyi, HOU Mingcai
    2023, 29(3):  345-358.  DOI: 10.16108/j.issn1006-7493.2023027
    Asbtract ( 1101 )   PDF (2348KB) ( 719 )  
    Related Articles | Metrics
    Big data has brought new ideas and challenges to lithofacies paleogeography research. However, due to the problems of complex data types, rich semantic relationships and unclear sharing mechanisms, it is difficult to conduct in-depth data mining, analysis, and effective utilization of lithofacies paleogeographic data, which makes making many advantages of big data not fully exploited in this field. The powerful semantic processing and open interconnection capabilities of knowledge graphs, make it plays an important role in solving the problems of big data text analysis and image understanding, which and haves broad application prospects. This paper summarizes the research background of lithofacies paleogeography knowledge graphs from the perspective of construction and application; by systematically investigates investigating the construction ideas, technologies and processes of lithofacies paleogeography knowledge graphs., and The paper also lists outlines the relevant applications of knowledge graphs in lithofacies paleogeography; and points out the main problems of lithofacies paleogeography knowledge graphs, prospects for future research directions.
    Construction of Nb-Ta Deposit Knowledge Graph and Its Application
    RAN Yizao, DONG Shaochun, WANG Rucheng, HU Huan, FANG Siyuan, CHANG Fengnian, KONG Jia
    2023, 29(3):  359-371.  DOI: 10.16108/j.issn1006-7493.2021107
    Asbtract ( 986 )   PDF (4845KB) ( 700 )  
    Related Articles | Metrics
    As an important resource for emerging industries, critical metals have gradually gain attention both domestically and overseas in recent years. However there are still some bottlenecks existing in the critical metal research due to its low abundance, difficulty to trace, identify and separate. As an important infrastructure of big data and artificial intelligence, knowledge graph provides new insights to tackle these issues. Most of the research achievements related to critical metal deposits are published in academic journals, which are written in natural language and is difficult to be understood and directly used by machines. In this paper, the ontology layer of Nb-Ta deposit knowledge graph was constructed and data extracted from literatures consists of the fact layer of the Nb-Ta deposit knowledge graph. Based on the Nb-Ta deposit knowledge graph, the features and relationships among the metallogenic periods, types of Nb-Ta deposits and the co-occurrence of niobium and tantalum related minerals were analyzed. It will help to further reveal the spatio-temporal distribution and evolution characteristics of China Nb-Ta deposits. 
    Deformation Prediction of Reservoir Landslides Using Knowledge Graph Optimized Kalman Filter
    HE Wangyan, ZHANG Wei, LI Houzhi, PAN Bo, DENG Lu, ZHU Honghu, SHI Bin
    2023, 29(3):  372-381.  DOI: 10.16108/j.issn1006-7493.2022068
    Asbtract ( 1026 )   PDF (3065KB) ( 646 )  
    Related Articles | Metrics
    Reservoir landslides occur frequently in the Three Gorges Reservoir area. Predicting the deformation of the landslides is an important measure to reduce the risk. This paper constructs a Chinese reservoir landslide knowledge graph combined with multivariate Taylor series Kalman filter and proposes a knowledge graph optimized Kalman filter model KG-MTKF. Taking the
    Xinpu landslide in Fengjie County in the Three Gorges Reservoir area as an example, the effectiveness of the model was verified by using on-site monitoring data. Results show that compared with the monitoring data, the multivariate Taylor series Kalman filter model (MT-KF) and the knowledge graph optimized Kalman filter model (KG-MTKF) show good consistency in the stationary stage when used to predict reservoir landslides. In the initial stage and step-like stage of the landslide deformation, the prediction accuracy of KG-MTKF is higher. The error of the two models in the initial stage is relatively large, which is caused by the small initial deformation value of the landslide and the more significant influence of system noise. The errors of the two models are
    relatively small in the step-like stage, the stationary stage, and the entire monitoring cycle, and KG-MTKF has higher accuracy than MT-KF. For nonlinear dynamic systems like Xinpu landslides, the KG-MTKF can maintain high accuracy and strong robustness at different positions and deformation stages.
    Comparative Analysis and Enlightenment of Geoscience Knowledge Graphs: A Perspective of Construction Methods and Contents
    ZHU Yunqiang, SUN Kai, LI Weirong, WANG Shu, SONG Jia, CHENG Quanying, YANG Jie, MU Xinglin, GENG Wenguang, DAI Xiaoliang
    2023, 29(3):  382-394.  DOI: 10.16108/j.issn1006-7493.2021111
    Asbtract ( 1325 )   PDF (1366KB) ( 689 )  
    Related Articles | Metrics
    Geoscience knowledge graphs (GKGs) formally represent geoscience knowledge in a way of directed graph and have strong capabilities in knowledge representation, openness and interconnectivity, and reasoning and prediction. GKGs have been one of the important infrastructures for the development of combining geoscience and artificial intelligence, thereby becoming one of the important research focuses in geoscience. Therefore, many international scientific organizations or groups have successively carried out studies in this domain, and constructed some representative GKGs. However, there is a lack of an in-depth study and analysis of these existing GKGs. To this end, this paper makes a systematic comparative analysis on their general information, construction methods, and main contents. On this basis, some enlightenments about future research of GKGs are discussed. In terms of the construction method, a unified representation framework for GKGs should be built, the source of geoscience knowledge should be enhanced by conflating multi-source and multimodal data, and methods for the representation and computation of geoscience knowledge should be studied. Regarding the contents of GKGs, complex spatiotemporal characteristics, relations, and reasoning rules should be considered. From the perspective of application, methods for assessing quality and making correction for geoscience knowledge should be developed, and application effects of GKGs should be improved.
    Overview and Reflections on the Development of Geological Information Sharing Platform
    NI Haijiang, ZHU Hehua, LI Cheng, XIAO Yulan, LIU Xiaobo
    2023, 29(3):  395-402.  DOI: 10.16108/j.issn1006-7493.2022060
    Asbtract ( 933 )   PDF (2500KB) ( 394 )  
    Related Articles | Metrics
    In recent decades, the geotechnical survey industry has been developinged slowly. The Internet digital platform model was introduced, and sharing platform of engineering geological information was developed, which realized the effective use of geological survey results, promoted the development of the geotechnical engineering experience evaluation system, and enhanced the vitality and efficiency of the engineering geological survey industry. This paper systematically reviews the development of geological information sharing platform and related standards at home and abroad, and summarizes the significance of platform development and the current problems and challenges. The suggestions for the construction ofng the an all-element geological information platform are as follows: (1) Strengthen the exploration of the co-construction and sharing mechanism of all-element geological information; (2) The AGS format is widely used in European and American countries, and it should be introduced to develop data storage and transmission standards; (3) The engineering geological survey industry has long been conservative and closed in thinking, and urgently needs to be more liberatedliberal; (4) Taking in venture capital can effectively guarantee the capital investment for the continuous development of the platform.
    3D Digitization of Geological Outcrops and Specimens:Status and Prospects
    XU Qi, SHEN Hanxiao, DONG Shaochun, SHI Yukun, FAN Junxuan
    2023, 29(3):  403-418.  DOI: 10.16108/j.issn1006-7493.2022092
    Asbtract ( 1029 )   PDF (3613KB) ( 920 )  
    Related Articles | Metrics
    In the era of big data, the high techniques such as knowledge graph, artificial intelligence and virtual simulation rapidly developed, and as a result the research methods of geosciences are evolving with the times. Compared to the traditional two-dimensional images and texts, three-dimensional digital models can provide more diverse data, and therefore hold enormous potential for both the scientific research and technology fields. The digitization of geological outcrops and specimens are two typical cases of 3D modeling technology in geoscience. This paper investigated the construction of digital outcrop and 3D specimen digitization, introduced the common digitization technologies, data sharing and development services, and the current representative digital geological outcrop and 3D specimen database. The investigation results were summarized and analyzed. Moreover, some problems that exist at present were summarized, and the future development was prospected in terms of data construction standard specification, construction content and function expansion.
    Research on the Joint Extraction Method of Entity Relations in Geological Domain
    QIU Qinjun, WANG Bin, XU Dexin, MA Kai, XIE Zhong, PAN Shengyong, TAO Liufeng
    2023, 29(3):  419-428.  DOI: 10.16108/j.issn1006-7493.2023026
    Asbtract ( 1077 )   PDF (1153KB) ( 689 )  
    Related Articles | Metrics
    Entity relationship extraction for the geological domain is the basis for building a geological knowledge graph, and is very important for text information extraction and knowledge base construction in the geological domain. In view of the complexity of entity relations in geological domain and the lack of a manually annotated corpus, a joint extraction model for entity relations in geological domain is proposed, focusing on the recognition of complex overlapping relations in multiple geological texts and avoiding cascading errors caused by entity recognition errors in the traditional pipeline model. In this paper, a high-quality corpus of entity relations in the geological domain is constructed, and a pre-trained language model based on BERT (Bidirectional Encoder Representations from Transformers) and BiGRU (Bidirectional Gated Recurrent Units) is proposed. Recurrent Units and Conditional Random Field (CRF) sequence annotation models to achieve joint extraction of entity relations. Experiments were conducted on the constructed dataset, and the results showed that the F1 value of the joint extraction model proposed in this paper reached 0.671 for entity relationship extraction, which verified the effectiveness of the model in this paper for geological entity relationship extraction.
    Chinese Text-oriented Geological Semantic Information Annotation and Corpus Construction
    ZHANG Xueying, ZHANG Chunju, WANG Chen, LIU Wencong, PENG Ye, LU Yanxu
    2023, 29(3):  429-438.  DOI: 10.16108/j.issn1006-7493.2023028
    Asbtract ( 1092 )   PDF (4406KB) ( 679 )  
    Related Articles | Metrics
    The structured extraction of geological information, semantic analysis, visual expression and the construction of knowledge map in text will provide a strong data foundation and technical support for the deep mining and utilization of geological big data. Whether it is a traditional statistical model or a deep learning model, the semantic analysis of geological information needs the support of tag corpus. In particular, the textual description of geological information has domain characteristics and cannot be achieved by migrating natural language corpora. Therefore, the construction of different levels of geological information annotation corpus has become the key foundation of geological semantic information analysis. Based on the analysis of the characteristics of the geological semantic information description language in Chinese text, according to the spatial and temporal characteristics and attribute description features of the geological entities, various semantic relations of geological entities are clearly expressed, and the geological semantic information is formed, formulating Chinese text labeling system and labeling specifications. The self-developed “interactive geological semantic information labeling tool”solves the shortcomings of traditional manual labeling methods such as high error rates and large workload. Using Chinese mineral resources literature and reports as data sources, a large-scale geological semantic information annotation corpus is constructed, which effectively solves the problem of the lack of large-scale standard data.
    Tectonic Attributes and Continental Affinities of the Precambrian Blocks in the Southwestern Central Asian Orogenic Belt
    WANG Bo, SUN Zhaochen, SONG Fang, NI Xinghua, CAO Tingting, LIU Jiashuo
    2023, 29(3):  439-454.  DOI: 10.16108/j.issn1006-7493.2021073
    Asbtract ( 1134 )   PDF (2285KB) ( 655 )  
    Related Articles | Metrics
    Numerous ribbon-like micro-plates develop in the southwestern part of the Central Asian Orogenic Belt (CAOB), they are important constituents of the Kazakhstan microcontinent, understanding of their tectonic attributes, continental affinities and crustal evolution is essential for the reconstruction of the accretionary history and geodynamic processes of the CAOB. The controversies remain for a long time about the basement compositions, tectonic settings and affinities of the micro-plates. This paper compiles recently published geological and isotopic chronological data, and summarizes rock assemblages, ages and tectonic settings of the Precambrian basement, and further analyzes the tectonic attributes of the micro-plates and their possible affinities with the surrounding continental plates. The available data indicate that the Meso- and Paleoproterozoic crystalline basement only develop in a few micro-plates (such as Chinese Central Tianshan, Kyrgyz Middle Tianshan, Issyk-Kul, Zheltau and Kokchetav), but are not recorded in the other micro-plates (such as South Yili, North Yili-Aktau, Chu-Ili, Karatau, Baikonur, Erementau and Ulutau) in the SW CAOB. However, similar Neoproterozoic metamorphic and magmatic rocks were documented in all these micro- plates and form the comparable metamorphic and crystalline basement. A comprehensive comparison and analysis allow us to conclude that these micro-plates may have different origins, but they experienced similar tectonic and magmatic evolution since Neoproterozoic, and underwent comparable paleogeographic environment, suggesting Early Neoproterozoic convergent orogenesis, Late Neoproterozoic continental rifting and formation of passive continental margins during the opening of the Paleo-Asian Ocean.
    Identification of Early Cretaceous Dioritic Enclave of Guposhan Granite in Guangxi and Its Geological Significances
    LIU Fenglei, ZHOU Yun, SHI Shuiping, FENG Zuohai, CAI Yongfeng, FU Wei, ZHAO Kai
    2023, 29(3):  455-470.  DOI: 10.16108/j.issn1006-7493.2021077
    Asbtract ( 1197 )   PDF (3195KB) ( 396 )  
    Related Articles | Metrics
    In order to figure out the Mesozoic tectonic evolution of the northeastern Guangxi, this paper presented detailed petrological, chronological and geochemical data on the Guposhan composite rock mass and its dioritic enclaves. The chronological results show that the formation age of the dioritic enclaves is 142±1 Ma, for the first time to identify Early Cretaceous dioritic enclaves in this area. Elemental geochemical analysis results show that the contents of SiO2, MgO and Fe2O3T of the dioritic enclaves are 55.66%-56.72%, 2.26%-2.30% and 10.43%-10.77%, respectively; the contents of SiO2, MgO and Fe2O3T of the host granite sample are 68.33%-68.67%, 0.60%-0.64% and 3.73%-3.89%, respectively. The granites are characterized by high 10000*Ga/Al ratios and Zr+Nb+Ce+Y contents, similar with those of A-type granite. Both the host rock and the dioritic enclave are enriched in large ion lithophile elements and high field strength elements. The above data indicate that the dioritic enclaves are produced by magmatic mixing, and their formation is related to extension and thinning of the lithosphere in the Late Mesozoic. Together with regional geological data, it is suggested that the Mesozoic extension of the lithosphere in South China was episodic, which led to the development of multi-stage magmatism in South China.
    Macroscopic and Mesoscopic Investigation on the Physical and Mechanical Characteristics of Coral Limestone at Different Depths
    MA Linjian, LIU Huachao, ZHANG Wei, LI Qi, ZHU Honghu, WU Jiawen
    2023, 29(3):  471-478.  DOI: 10.16108/j.issn1006-7493.2021074
    Asbtract ( 1558 )   PDF (2519KB) ( 1033 )  
    Related Articles | Metrics
    In order to investigate the physical and mechanical characteristics of coral reefs with different depth in the South China Sea, scanning electron microscopy (SEM) and X-ray tomography (CT) technology are used to characterize the micro morphology and internal pore structure characteristics of shallow and deep reef limestone. Quantitative relationships between P-wave velocity and porosity as well as density were established. Uniaxial compression tests on dry and saturated reef limestone were also carried out. Results show that shallow reef limestone is porous with excellent pore connectivity, and the main mineral composition is aragonite, which belongs to the biological sedimentary rock. While deep reef limestone is dense with poor pore connectivity, and the main mineral composition is calcite, belonging to the metamorphic rock. The porosity of deep reef limestone is about 1/10, with an average peak compressive strength of about 4.8 times and an average elastic modulus of about 4.5 times that of shallow reef limestone. Reef limestone belongs to soft or extremely soft rock, characterized by brittle destruction property. The typical damage pattern is multiple rupture surface destruction along the primary pore, growing line of corals and weak bond surface, with high  residual strength. The hydrogenic effect of reef limestone is significant, and the water rationality of deep reef limestone is stronger than shallow reef limestone. The significant difference of physical and mechanical performances in shallow and deep reef limestone are mainly due to the variety in mineral components, pore structure and lithology caused by the varying degree of rock cementation with different depths.

    Sensitivity Analysis of Rock Stress Wave Propagation and Attenuation Characteristics Based on MatDEM
    FAN Guansheng, HUANG Yehuan, LIU Chun, LE Tiancheng
    2023, 29(3):  479-486.  DOI: 10.16108/j.issn1006-7493.2021102
    Asbtract ( 921 )   PDF (6972KB) ( 588 )  
    Related Articles | Metrics
    The study of stress waves is a key issue in the dynamic action of rocks. Based on the discrete element method, this paper carries out numerical simulation tests on rock samples to explore the influence factors and laws of stress wave propagation and attenuation. The analysis focuses on the influence of the element radius, damping coefficient, incident wave frequency and amplitude on the stress wave propagation of the rock numerical sample, compares and analyzes the real test results. The research results show that the discrete element method can effectively simulate the dynamic process, and the variation law of the stress wave propagation in the numerical rock sample is consistent with previous studies. The increase in the radius of the rock sample unit will increase the unevenness of the rock sample and increase the scattering attenuation; the larger the damping coefficient, the greater the attenuation of the amplitude at the same distance; the frequency of the incident wave in the rock sample decreases, the wave propagation trend develops from logarithmic attenuation to linear attenuation; the greater the amplitude of the loading wave, the greater the attenuation of the stress wave due to scattering, and the attenuation rate at the same propagation distance remains constant. 
    Investigation of Oedometer Test and Mechanism of Soft Soil Improved Using Microbial Composite Material
    LIU Qing, LIN Jun, XIE Jiamin, QIN Pengfei
    2023, 29(3):  487-496.  DOI: 10.16108/j.issn1006-7493.2021114
    Asbtract ( 1206 )   PDF (2723KB) ( 715 )  
    Related Articles | Metrics
    Microbial induced carbonate precipitation (MICP), as an eco-friendly technology, has been used to improve the mechanical properties of soil. However, it is difficult to apply the MICP to soft soil foundation treatment due to the poor engineering properties. The MICP-sand drain combined with vacuum drainage and MICP-biochar were introduced to the soft soil, and the amount of sand drain and biochar mixing ratio were studied using oedometer test. The microstructures were investigated to reveal the precipitation patterns of calcium carbonate by using SEM and XRD tests. The results showed that porosity ratio decreased with the increase of in number of sand drain and biochar mixing ratio. The coefficient of compressibility and modulus of compression could be improved when the contents of biochar were in a certain range (about 8%). The analysis of calcium carbonate content showed reveal that the amount of calcium carbonate decreased gradually with the increase of in depth, which presented presents non-uniformity of calcium carbonate distribution. Additionally, a large amount of calcium carbonate was observed in the two methods, which were deposited on the contact of soil particles. The crystal type of calcium carbonate was determined as vaterite.