Top Read

Published in last 1 year |

In last 2 years |

In last 3 years |

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Overview: A glimpse of the latest advances in artificial intelligence and big data geoscience research ZHOU Yongzhang, XIAO Fan Earth Science Frontiers    2024, 31 (4): 1-6.   DOI: 10.13745/j.esf.sf.2024.6.99 Abstract （1670）   HTML （54）    PDF（pc） （640KB）（1262）       Knowledge map    Save This special issue titled “Artificial Intelligence and Big Data Geoscience” consists of 17 papers covering topics such as knowledge graphs, deep learning-based image recognition, machine-readable expression of unstructured geological information, big graph data and community detection, association rule algorithms, 3D geological simulation and mineral prospecting, and the Internet of Things and online monitoring systems. A progressive multi-granularity training deep learning method is proposed for mineral image identification; the model achieves 86.5% accuracy on a commonly used dataset comprising 36 mineral types, increasing the accuracy of mineral identification. Knowledge related to porphyry copper ore in the Qinzhou-Hangzhou mineralization belt, South China, is collected using both primary and literature data sources, and Natural Language Processing (NLP) techniques are used to semantically correlate and reason over the knowledge graph, enabling automated knowledge extraction and reasoning. The association rule algorithm is used to analyze the correlation between trace elements and gold mineralization in major Carlin-type gold deposits in the “Golden Triangle” region of Yunnan-Guizhou-Guangxi provinces, China, and combined with the migration and enrichment law of elements to analyze the genetic mechanism of deposits. By builing a quantitative prospecting indicator method based on association rule algorithm, this study provides new ideas for establishing quantitative prospecting indicators for other types of deposits. In study of machine-readable expression of unstructured geological information and intelligent prediction of mineralization associated anomaly areas in Pangxidong District, western Guangdong, China, unstructured geological information such as stratigraphy, lithology and faults is processed by machine-readable conversion, and two machine learning algorithms—namely, One-Class Support Vector Machine and Auto-Encoder network—are applied to mine the geochemical test data of the stream sediment as well as the comprehensive geological information such as faults and stratigraphy, to extract the features of the mineralizing anomalies, and ultimately realize the intelligent circling of mineralizing anomalous areas. In study of networked monitoring of urban soil pollutants and visualized system based on microservice architecture, a system capable of real-time online monitoring, processing, and analyzing urban soil pollution data to enhance the timeliness of predictions and warnings is developed, where the integrated monitoring and data visualization system is based on the microservices framework Spring Cloud Alibaba. The above mentioned studies provide highly valuable application scenarios and research cases, reflecting to some extent the latest research advances in the field of artificial intelligence and big data geoscience in China, and are worthy of peer attention. Reference | Related Articles | Metrics | Comments（0）

Select

Knowledge graph-infused quantitative mineral resource forecasting WANG Chengbin, WANG Mingguo, WANG Bo, CHEN Jianguo, MA Xiaogang, JIANG Shu Earth Science Frontiers    2024, 31 (4): 26-36.   DOI: 10.13745/j.esf.sf.2024.5.3 Abstract （1488）   HTML （39）    PDF（pc） （6062KB）（490）       Knowledge map    Save Big data and artificial intelligence have greatly transformed mineral exploration practices with the development of innovative mineral forecasting models and improvement of forecasting efficiency for strategic minerals. In the field of quantitative mineral forecasting, comprehensive intelligent forecasting by combining knowledge and data has gradually become a common consensus, however, the challenge lies in how to combine knowledge and data. Knowledge graphs integrate multi-source, heterogeneous geoscience big data and drive knowledge discovery through rules and reasoning. Here, we discuss the feasibility and technical roadmap of knowledge graph-infused intelligent and automated mineral resource forecasting, particularly in consideration of the characteristics of knowledge graphs in the era of big data and artificial intelligence. We focus mainly on the construction of multi-temporal, all-element knowledge graphs for mineral deposit-mineral exploration systems and the methodology for establishing forecasting models from the perspectives of ore commonality and distinctiveness based on knowledge graphs. The opportunities and challenges of knowledge graph embedding for geological anomaly information extraction and quantitative resource forecasting are also discussed, in the hope that the infusion of knowledge representation and reasoning from knowledge graphs into the technical workflow of quantitative mineral resource forecasting can aid geologists in building ore forecasting models and enhancing automated and intelligent mineral forecasting. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Mechanical behavior of calcite vein-bearing shale of the Niutitang Formation in Fenggang area, northern Guizhou based on CT tests WU Zhonghu, MENG Xiangrui, LAN Baofeng, LIU Jingshou, GONG Lei, YANG Yuhan Earth Science Frontiers    2024, 31 (5): 117-129.   DOI: 10.13745/j.esf.sf.2024.6.15 Abstract （1384）   HTML （5）    PDF（pc） （10828KB）（189）       Knowledge map    Save Core observations of shales from the Niutitang Formation in the northern Qianbei region show that calcite veins often act as natural fracture fillers and largely influence the shale damage patterns. The damage characteristics of calcite vein-bearing shales is important for the prediction of fracture initiation and extension behavior during hydraulic fracturing and for the engineering design. In order to reveal the influence of calcite veins on the mechanical properties and fracture characteristics of shale, uniaxial compression and acoustic emission tests are conducted at seven inclination angles of 0° to 90° in 15° increment. Combined with CT scanning technology and finite element calculations, a three-dimensional (3D) microscopic numerical model is constructed. The effects of calcite vein angle on the fine-scale shale damage process as well as shale mechanical properties are discussed, and the spatiotemporal evolution of shale microcracks are analyzed. The results show that (1) under different calcite vein angles the shale acoustic emission and stress-strain curves show similar curve shape changes, in four stages, namely compression-density, elasticity, yielding, and post-peak damage, with obvious distinctions between stages. The change curve of the characteristic intensity is “U”-shaped with a local minimum at θ of 75°. (2) Calcite veins significantly affect the damage mode: As the vein angle decreases, the damage mode changes from cleavage to cleavage-type shear, to shear-slip, and finally to cleavage-tension. (3) The reconstructed 3D model is largely consistent with physical testing data, providing insights into the process of crack expansion and penetration at shale’s interior and surface. The spatial distribution of acoustic emission reflects the compression, tension, and shear damage types at different stages, revealing the fracture mechanism of calcite-containing shale from the microscopic point of view. (4) Calcite and matrix simulatineously and anisotropically affect the macroscopic mechanical properties of shale: The higher the calcite vein angle, the stronger its slip guidance effect, and the weaker the mechanical properties of the specimens. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Characterization and 3D modeling of multiscale natural fractures in shale gas reservoir: A case study in the Pingqiao structural belt, Sichuan Basin QIAO Hui, ZHANG Yonggui, NIE Haikuan, PENG Yongmin, ZHANG Ke, SU Haikun Earth Science Frontiers    2024, 31 (5): 89-102.   DOI: 10.13745/j.esf.sf.2023.6.13 Abstract （1368）   HTML （9）    PDF（pc） （10680KB）（225）       Knowledge map    Save Natural fractures in shale reservoirs are important reservoir spaces and seepage channels. Identifying the types and spatial distribution of natural fractures is essential for shale gas exploration and development. This paper, based on seismic/outcrop data, core observation, well logging and micro-test analysis, mainly considering the effect of fractures on shale gas enrichment and high production, divides natural fractures of shale reservoirs into three scale levels: large, medium-small and micro, and clarifies the methodologies for fracture characterization and modeling at each scale level and application results. In summary: (1) large fractures were mainly characterized using stacked 3D seismic data; medium-small fractures using a combination of core, image log and seismic attributes data; and microfractures using microanalysis such as core description, high-resolution scanning electron microscope and maps analysis. Through fracture characterization, the fracture density, crack opening, dip, orientation and filling status at each scale level were determined. (2) The DFN model of large fractures was established via deterministic modeling, using the characterization parameters of post-stack seismic attributes as the input. For medium-small fractures, single-well image logs were used as prior information; a fracture probability model of multi-information fusion was established as the spatial trend; and the DFN model was established via stochastic modelling. Microfracture modeling was based on microfracture parameters obtained from micro-test analysis; microfracture density model was established by combining well data with TOC and other main control factors; and the DFN model was established via stochastic modeling. (3) Taking the shale gas reservoir in the Pingqiao tectonic zone, Sichuan Basin as an example, fracture characterization and fracture 3D geological modeling for different fracture types were carried out. The fracture initiation site, scale, orientation and occurrence characteristics were defined, and fracture attributes such as fracture location, dip angle, azimuth angle, geometric size, development density, porosity and permeability were described. The methodologies for the multiscale natural fracture characterization and modeling provide a basis for numerical modeling of shale gas reservoirs. The 3D geological model of shale reservoir in the Pingqiao tectonic belt and the simulation results are in good agreement with geological knowledge and production data, thus providing a reference for the devlopment of shale gas fields. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Ocean-floor hydrogen accumulation model and global distribution SUO Yanhui, JIANG Zhaoxia, LI Sanzhong, WU Lixin Earth Science Frontiers    2024, 31 (4): 175-182.   DOI: 10.13745/j.esf.sf.2024.6.98 Abstract （1316）   HTML （24）    PDF（pc） （1836KB）（348）       Knowledge map    Save Hydrogen energy is a clean, efficient, and zero-carbon energy source. The formation, transportation, and accumulation of natural hydrogen are closely related to plate tectonics. As the only rocky planet in the solar system known to have plate tectonics and liquid water, Earth has unique geological hydrogen generation pathways such as degassing, serpentinization, and water radiolysis. The ocean-floor, which occupies two-thirds of the Earth’s surface, has great potential for natural hydrogen generation through serpentinization, due to the extensive exposure of oceanic crust or mantle along or around microplate boundaries and ocean-floor fissures. Microplate boundaries, submarine plateaus, ocean floor fracture zones, micro-mantle blocks, and non-volcanic passive continental margins are favorable targets for exploring ocean-floor natural hydrogen. The northeastern continental margin of the South China Sea is also worthy of attention. However, it is difficult to establish a unified ocean-floor hydrogen accumulation model due to the significant differences and diversity in the formation, migration, and storage conditions of natural hydrogen in different tectonic settings. The predicted hydrogen sites, whether they can form reservoirs, how they form reservoirs, and the related exploitation and utilization technologies need to be explored in the future. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Tectonic fracturing and fracture initiation in shale reservoirs—research progress and outlooks DING Wenlong, WANG Yao, ZHANG Ziyou, LIU Tianshun, CHENG Xiaoyun, GOU Tong, WANG Shenghui, LIU Tingfeng Earth Science Frontiers    2024, 31 (5): 1-16.   DOI: 10.13745/j.esf.sf.2024.6.11 Abstract （1314）   HTML （36）    PDF（pc） （7879KB）（321）       Knowledge map    Save Shale oil and gas development has gained significant progress in China with the contineous research and technological advancements in unconventional oil and gas. Extensive production practices demonstrate that natural fracture development in shale reservoirs is a crucial factor influencing oil and gas enrichment, high production and stable yield, for fractures not only improve reservoir properties but also facilitate subsequent reservoir modification during hydrollic fracturing. The formation stages of tectonic fractures and fracture initiation holds significant importance for revealing the oil and gas enrichment patterns and preservation condition. Early studies on shale reservoir fractures mainly focused on fracture classification/identification/characterization, main controlling factors of fracture development, and fracture distribution prediction and modelling, with less attention to the determination of fracture formation stages, main controlling factors of fracture initiation, mechanism of fracture opening and closing, and quantitative characterization of fracture openness—this restricts the efficient exploration and development of shale oil and gas in China. This paper highlights research progress addressing the above gaps, particularly the delineation of fracturing stages, dating of filling veins, and quantification of fracture openness based on comprehensive literature review. The classification methods for fracturing stages can be divided into two categories: qualitative geological analysis and geochemical tracing of fracture fillings. These methods however have practical limitations, where only the relative sequence of fracturing stages can be obtained, and the results are affected by the accuracy of basic geological data such as burial/thermal histories. Most of the fissure veins in fractures are carbonate minerals and quartz. With the advent of high precision in situ U-Pb microprobe dating technology, it is possible to determine the absolute ages of different veins while avoiding the problem of multiple solutions to fluid activity periods due to differences in interpreting thermal/burial histories. The initiation of tectonic fractures is controlled by many factors, not only by rocks’ intrinsic properties but also the current crustal stress and formation-fluid pressure. The petrological characteristics of fibrous fillings widely distributed in fractures record the crystal growth process. Such special crystal morphology provides the evidence of multi-stage tectonic fracturing, revealing a fracture evolutionary process with multiple fracture opening and closing. At present, fracture openness is characterized using the fracture apature parameter or inferred by the fracture initiation pressure obtained by calculation and experiment. Based on the analysis of the above results, this paper points out the key problems and development trends in the study of the fracturing stages and initiation of tectonic fractures in shale reservoirs, aiming to enrich and improve the theory and research methodology for shale oil and gas reservoirs, and provide an important scientific basis for the study of structural preservation conditions and enrichment mechanism of shale oil and gas in China. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

InterfaceGrid: Gridding representation of 3D geological models for complex geological structures NIU Lujia, SHI Chengyue, WANG Zhangang, ZHOU Yongzhang Earth Science Frontiers    2024, 31 (4): 129-138.   DOI: 10.13745/j.esf.sf.2024.5.7 Abstract （1312）   HTML （18）    PDF（pc） （3722KB）（405）       Knowledge map    Save 3D structural geological models are a digital representation of geological structures and geological body (object) boundaries in geological space. With the increasing demands for raster and vector integration and spatial query and analysis of geological data, the construction of integrated spatial data model for unified expression of geological structures has become one of the basic problems of 3D geological information science. To address the problem of expressing complex geological structures by regular grids, PillarGrid, Stack-Based Representation of Terrains (SBRT), etc., this study proposes the InterfaceGrid data model to fully consider that the distribution of geological structures/attributes underground exhibit strong non-uniformity, discontinuity, spatially multi-scaled, and show longitudinal stratification and multi-attribute field coupling. By design, this InterfaceGrid data model can uniformly describe 3D geological structures and realize the vector raster integration expression of complex geological structures. In this paper, the formal expression framework of InterfaceGrid is constructed based on GeoAtom theory; the construction process of the InterfaceGrid model is described; and the data update and spatial query algorithms are designed based on the InterfaceGrid model. The volume visualization and online browsing of geological grid are realized using GPU ray casting and adaptive sampling strategy. Compared with SBRT, InterfaceGrid can more truly describe the geological boundaries and improve the accuracy of 3D structural geological models. The application of InterfaceGrid in the 3D grid construction of the global lithosphere verifies the applicability of InterfaceGrid in the organization and management of large-scale geological data. Compared with PillarGrid, the data volume is reduced by about 1/3 in InterfaceGrid, making it more suitable for the data-intensive geoscience network applications. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Contribution ratio and distribution patterns of multiple oil sources in the Yanchang Formation of the Ordos Basin: A study utilizing machine learning and interpretability techniques SU Kaiming, XU Yaohui, XU Wanglin, ZHANG Yueqiao, BAI Bin, LI Yang, YAN Gang Earth Science Frontiers    2024, 31 (3): 530-540.   DOI: 10.13745/j.esf.sf.2023.9.56 Abstract （1243）   HTML （11）    PDF（pc） （6942KB）（176）       Knowledge map    Save The Yanchang Formation within the Ordos Basin hosts multiple sets of potential source rocks, all exhibiting similar biomarker properties. The conventional method of oil-source correlation has proven ineffective, leading to longstanding debates within the field. In response to these challenges, this study introduces a novel deep learning-based scheme for oil-source comparison, leveraging artificial intelligence methods for research in this domain. The study presents the following key findings and insights: (1) Development of a deep neural network model for identifying the oil source type of unknown samples by utilizing 42 biomarker parameters from a diverse set of mudstone and shale samples representing different oil groups within the Yanchang Formation as training data. The model achieved identification accuracies of 83.0% for Chang 7 mudstone and 79.6% for Chang 8-Chang 10 mudstone, successfully distinguishing the primary source rocks of the Yanchang Formation from hydrocarbon generation products. (2) Application of the model to analyze the oil source classification of numerous sandstone and oil samples. The study calculated the contribution ratios of various source rocks to each oil group within the Yanchang Formation, summarizing their distribution patterns. (3) Conducting sensitivity analysis of the model using the permutation feature importance (PFI) algorithm, revealing differences in biomarkers between the two main source rocks of the Yanchang Formation. These findings contribute to advancing artificial intelligence techniques and technologies in the field of petroleum molecular geochemistry, offering valuable insights for future research and applications. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Key issues in three-dimensional predictive modeling of mineral prospectivity YUAN Feng, LI Xiaohui, TIAN Weidong, ZHOU Guanqun, WANG Jinju, GE Can, GUO Xianzheng, ZHENG Chaojie Earth Science Frontiers    2024, 31 (4): 119-128.   DOI: 10.13745/j.esf.sf.2024.5.9 Abstract （1238）   HTML （23）    PDF（pc） （3871KB）（904）       Knowledge map    Save Three-dimensional predictive modeling of mineral prospectivity is an important approach to deep mineral exploration. Although significant advancements have been made in the methodology and application of this approach, several key scientific and technological issues remain unresolved concerning the insufficiencies of multi-scale 3D predictive modeling methodology, uncertainty analysis and optimization of prediction results, mining of key factors in 3D mineralization prediction, and dedicated 3D deep learning models and methodologies tailored for 3D predictive modeling of mineral prospectivity. Focusing on these key issues, this paper conducts a comprehensive review of current research progress in the field, and proposes potential solutions and research directions to address these issues. Future developments in this field include methods for deep mining of 3D predictive information; applicable 3D deep learning models and training methods for enhanced predictive modeling; uncertainty analysis and optimization methods for improving the reliability and accuracy of 3D mineralization prediction; and a methodological framework for multi-scale predictive modeling so as to effectively guide deep mineral exploration at the levels of orebodies, ore fields, and ore deposits. Resolving these key issues will further develop and refine the theoretical and methodological frameworks of 3D mineralization prediction, significantly improve the efficiency of deep mineral exploration, and ultimately facilitate breakthrough in mineral deposit discovery in the deep earth. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Pollution Characteristics, Ecological risk and source apportionment of heavy metals in sediments of the Pearl River Basin TU Chunlin, HE Chengzhong, MA Yiqi, YIN Linhu, TAO Lanchu, YANG Minghua Earth Science Frontiers    2024, 31 (3): 410-419.   DOI: 10.13745/j.esf.sf.2023.2.47 Abstract （1217）   HTML （24）    PDF（pc） （2813KB）（190）       Knowledge map    Save The enrichment of heavy metals in sediments poses a serious threat to the aquatic environment of the Pearl River Basin. Exploring heavy metal pollution in the sediments of the Pearl River Basin is crucial for preventing and controlling such pollution and for supporting the scientific management of the aquatic environment. Data on the contents of heavy metals (As, Cd, Pb, Cr, Cu, and Zn) in the sediments of the Pearl River Basin published from 2009 to 2022 were collected. Through mathematical statistical analysis, correlation analysis, and positive matrix factorization (PMF) modeling, we discussed the distribution characteristics and pollution sources of heavy metals in the sediments of the Pearl River Basin. We also evaluated the pollution degree and ecological risk of heavy metals based on the geo-accumulation index and potential ecological risk index. The results revealed that the average content of As, Cd, Pb, Cr, Cu, and Zn in the sediments of the Pearl River Basin were 49.29, 2.76, 63.97, 67.44, 48.72, and 186.60 mg·kg-1, respectively. Among them, As, Cd, Pb, and Zn exceeded the average values of stream sediments in southern China, while Cu and Cr were close to the average values of stream sediments in southern China. The pollution of Cd and As in the sediments of the Pearl River Basin is the most serious, with Cd classified as mild to moderate degree and As mainly at a slight degree, while the other four heavy metals showed no pollution. The order of single-factor hazard index of heavy metals in sediments was: Cd>As>Pb>Cu>Zn>Cr, with Cd showing a serious damage level throughout the Pearl River Basin, contributing 70.73% to 93.73% of the ecological risk index. The damage level of As in the Xijiang River, Nanbeipan River, and Pearl River Delta was moderate, while the damage level of other heavy metals such as Pb, Cr, Cu, and Zn was slight. The results of the PMF analysis indicated that the main sources of heavy metals in sediments were the combined pollution sources of mining activities and agricultural activities, coal and industrial activities, atmospheric deposition and traffic pollution sources, and natural sources, with contributions of 21%, 17%, 35%, and 27%, respectively. The first three were all anthropogenic sources, with a cumulative contribution of 73%. Cd and As were mainly derived from mining activities, industrial activities, and agricultural activities. Pb was primarily derived from traffic pollution and mining activities. Cr mainly originated from natural sources, while Cu and Zn were influenced by all four sources. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Variability in spatiotemporal groundwater nitrate concentrations in the northeast Ganfu Plain HE Jiahui, MAO Hairu, XUE Yang, LIAO Fu, GAO Bai, RAO Zhi, YANG Yang, LIU Yuanyuan, WANG Guangcai Earth Science Frontiers    2024, 31 (3): 360-370.   DOI: 10.13745/j.esf.sf.2023.2.84 Abstract （1192）   HTML （11）    PDF（pc） （5117KB）（154）       Knowledge map    Save Groundwater in the Ganfu Plain exhibits high NO3- concentrations, yet few studies have investigated the seasonal variations and influencing factors of groundwater chemistry, particularly NO3- concentrations. In this study, groundwater samples were collected in the northeast region of the Ganfu Plain during both dry and wet seasons. The study aimed to explore the spatiotemporal variations in groundwater chemistry, focusing on NO3- concentrations, and the sources of NO3- in groundwater using hydrochemical diagrams, Self-Organizing Map (SOM), spatial autocorrelation analysis, and an inverse geochemical model. The results indicate that the primary groundwater types in the study area are Cl·NO3-Ca and HCO3-Ca. Human activities emerge as the key factor driving spatial variations in groundwater chemistry. Regions with elevated NO3- concentrations and significant seasonal variations are predominantly located in the lower reaches of Nanchang. Conversely, areas with lower NO3- concentrations and seasonal variations are primarily situated in the western and southeastern mountainous regions and the lower reaches of the Ganjiang River Delta. The spatial distribution and seasonal variability of groundwater NO3- concentrations in the study area are influenced by groundwater runoff conditions, redox environments, and land use patterns. Industrial and domestic sewage are identified as the main sources of NO3- in groundwater, with the impact of fertilizers on NO3- concentrations also warranting consideration. The results from the inverse geochemical model provide quantitative insights into the effects of water-rock interactions and human activities on groundwater quality during groundwater movement processes. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

The thermal status of China’s land areas and heat-control factors WANG Guiling, LIN Wenjing Earth Science Frontiers    2024, 31 (6): 1-18.   DOI: 10.13745/j.esf.sf.2024.10.13 Abstract （1165）   HTML （44）    PDF（pc） （10722KB）（510）       Knowledge map    Save The thermal state of a region is crucial for understanding the main source of geothermal heat flow in the region, which help to solve the basic problem of regional heat source, and provide a basis for the study of the regional geothermal resources. Based on the regional geothermal measurements and deep borehole temperature logging carried out in China in recent years, this paper analyzes the crust-to-mantle heat flow ratio in China’s land area and divides the land area into four geothermal zonal types, namely high-temperature geothermal zone with a crustal heat source, medium- and low-temperature geothermal zone with a mantle heat source, low-temperature geothermal equilibrium zone with a crust-mantle heat source, and medium- and high-temperature geothermal equilibrium zone with a crust-mantle heat source. On this basis, typical geothermal zones—such as the northeastern Tibetan Plateau, the Tengchong area, the southeastern coastal area, and the North China Basin—are selected to systematically analyze the basin-scale regional thermal state and its main controlling factors, such as the characteristics of the regional geothermal field, the distribution of heat flow, and the crustal-mantle thermal structure. The paper summarizes the deep and shallow geologic factors affecting the regional thermal state—including crust-mantle architecture, tectono-thermal events, stratigraphic lithology, fracture structure, etc.—and establishes multilevel controlling factors of regional thermal states, providing a scientific basis for the geothermal resource exploration and heat source condition analysis in different regions. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Characteristics of deep karst fracture-cavity reservoir formation controlled by multi-phase faults matching in the northern Tarim Basin LI Fenglei, LIN Chengyan, REN Lihua, ZHANG Guoyin, GUAN Baozhu Earth Science Frontiers    2024, 31 (4): 219-236.   DOI: 10.13745/j.esf.sf.2023.9.5 Abstract （1144）   HTML （14）    PDF（pc） （23578KB）（208）       Knowledge map    Save Investigating the correlation between multi-phase tectonic activity and deep reservoir formation is crucial for oil and gas exploration endeavors. Utilizing seismic data from the Halahatang, Jinyue, and Fuman oilfields, coupled with an analysis of field geological outcrop faults, various seismic fine interpretation methods were employed to delineate faults within the study area. Building upon an understanding of the Middle Cambrian Yuertusi source rock and the characteristics of the Caledonian, Hercynian, and Himalayan accumulation stages, faults controlling oil accumulation were classified into four stages: Early Caledonian, Middle and Late Caledonian, Late Hercynian, and Himalayan. Further analysis of the inheritance relationship, source characteristics, and adjustment effects of multi-stage fractures, along with an assessment of various types of karst fracture-cavity reservoir development, led to discussions on the variations in karst fracture-cavity reservoirs under the influence of strike-slip faults in the study area. Key findings include: (1) Identification of primary factors influencing oil and gas reservoirs, including intra-source faults from the early Caledonian normal fault system facilitating hydrocarbon expulsion from Cambrian source rocks, and outer source faults formed during the late Caledonian enabling communication with source rocks for oil and gas migration and accumulation. Four source rocks-linking models were established based on this understanding. (2) Recognition of three main hydrocarbon generation periods in the study area: late Caledonian, Hercynian, and Himalayan, with inherited development of northwest strike-slip fractures into the Permian during the Late Hercynian period, impacting Garridonian reservoirs, and destruction and adjustment of early oil and gas reservoirs by northeast strike-slip fault systems inherited to the Neogene during the Himalayan period. Three modes of oil and gas remigration were established. (3) Establishment of six types of strike-slip fault control grades based on fracture matching relationships, along with classification of Middle and Late Caledonian strike-slip fault zones in the study area. A mining status map revealed a high matching degree between differential reservoir-controlling faults and oil and gas production. (4) Joint control of reservoirs by strike-slip faults and karstification in the study area, with an established matching relationship between the multi-stage fault system and various types of karst fracture-cavity reservoirs. This understanding has been successfully applied to well location exploration in the study area, yielding favorable results and providing guidance for the exploration and development of karst fracture-cavity reservoirs controlled by strike-slip faults. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Geochemical characteristics and genesis of lithium rich clay rocks in the Pudi area of northwestern Guizhou ZHANG Qidao, LI Dezong, LI Zhiwei, WANG Donghui, YU Yifan, ZHU Xingqiang, CAI Quanyu, LI Ming Earth Science Frontiers    2024, 31 (4): 258-280.   DOI: 10.13745/j.esf.sf.2023.11.20 Abstract （1142）   HTML （22）    PDF（pc） （11592KB）（257）       Knowledge map    Save The Permian Liangshan Formation in the Pudi area of northwest Guizhou Province directly overlays the Cambrian Loushanguan Formation, exhibiting abnormal lithium enrichment in its clay rocks. Studying the enrichment mechanism provides valuable insights for lithium resource development and evaluation in clay rocks, as well as understanding lithium accumulation mechanisms. Various analytical methods including LA-ICP-MS, mapping, AMICS, XRD, SEM, along with U-Pb chronology, are employed to elucidate the elemental geochemistry, provenances, and occurrence states of lithium enrichment in clay rocks. Results reveal lithium-rich clay rocks primarily in the middle and lower sections of the Permian Liangshan Formation, with their occurrence controlled by the karst unconformity surface of the underlying Loushanguan Formation dolomite. Enriched elements such as Li, Ga, V, Nb, Zr, and F are identified, while Ba and Sr are relatively depleted. Light rare earth elements (La, Ce, Nd) predominate, with Y as the main heavy rare earth element. Lithium-rich clay rocks comprise terrestrial deposits with characteristics of terrestrial, transitional, and marine phases, formed in an oxidized environment under a tropical-subtropical warm and humid climate. The zircon age spectrum exhibits five peaks at 2.5 Ga, 1.4 Ga, 980 Ma, 780 Ma, and 530 Ma, with the main peaks at 980 Ma, 780 Ma, and 530 Ma. Lithium in the clay rocks mainly occurs within kaolinite, indicating multiple sources, with impure dolomite of the Cambrian Loushanguan Formation likely being the primary source. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Research on paths to realize the values of ecological products in national parks based on the geological and nature environmental settings of the China National Parks MA Junjie, CHENG Jie, LIU Xiaohong, SUN Hongyan Earth Science Frontiers    2024, 31 (3): 458-469.   DOI: 10.13745/j.esf.sf.2024.1.50 Abstract （1139）   HTML （6）    PDF（pc） （2744KB）（171）       Knowledge map    Save Establishing National Parks in China is a crucial initiative for biodiversity conservation. It is essential to maximize the value of ecological products within them, benefit society, and promote a sustainable cycle of natural resource conservation and utilization to ensure the high-quality and sustainable development of these parks. Therefore, studying the pathways for realizing the value of ecological products is significant. This paper analyzes the geological settings, environmental conditions, and natural resources of the first batch of five National Parks in China (Three Rivers Source, Giant Panda, Northeast China Tiger and Leopard, Wuyishan, and Hainan Tropical Rainforest National Parks) and discusses the relationship between natural resources and ecological products in these parks. The ecological products are categorized as natural, semi-natural, and artificial based on human interference. Using land and water resources as examples, the paper explores the main factors influencing the value of ecological products and the various types of ecological products that natural resources can be transformed into. Additionally, based on the characteristics of ecological products, the paper presents three levels of pathways and methods for realizing their value and discusses the differences in value realization pathways for ecological products in national parks with diverse geological and natural backgrounds. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Rock and mineral thin section identification based on deep learning ZHANG Lijun, LU Wenhao, ZHANG Jiandong, PENG Guangxiong, BU Jiancai, TANG Kai, XIE Jiancheng, XU Zhibin, YANG Haiyan Earth Science Frontiers    2024, 31 (3): 498-510.   DOI: 10.13745/j.esf.sf.2023.6.7 Abstract （1119）   HTML （31）    PDF（pc） （3815KB）（435）       Knowledge map    Save Rock-mineral microscopic image identification is one of the basic means of rock and mineral identification, which is of great significance to the exploration of geological resources. Thin-section microscopic images are generally carried out in the laboratory. This work is tedious and time-consuming, requires a lot of human resources, and the accuracy is limited by the experience of the expert. Deep learning intelligent image recognition algorithm can extract the deep features of microscopic images by convolutional neural network, to achieve the purpose of fast and accurate classification and recognition of microscopic images. In this study, the PyCharm platform is used as the deep learning framework, and the data set that can be applied to the classification and recognition of rock-mineral microscopic images is made based on six data sets such as the teaching rock slice dataset of Nanjing University and the Carboniferous limestone microscopic image dataset of South North China on the China Science Data Network. We design a VGG convolutional neural network model. The model can analyze the feature information in the deep layer of the whole rock slice image and the single mineral image respectively, to achieve the purpose of identifying rock slices. The test results show that with the increase of model training times, the loss function between the predicted value and the real value is decreasing, and the recognition accuracy is increasing. After 50 and 30 cycles of training, the loss function and recognition accuracy of the model have been basically convergent. The recognition success rate of the model for the microscopic image test set is higher than 90%, indicating that the model has a good feature extraction effect for the image and can complete the task of rock-mineral microscopic image recognition. Through the research of this paper, it can be realized that deep learning has high efficiency and accuracy for dealing with such tasks as rock and mineral identification. Developing relevant models and applying them to front-end software can speed up the speed of mineral resources exploration and has important application significance for production practice. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Online monitoring of CO2 using IoT for assessment of leakage risks associated with geological sequestration MA Jianhua, LIU Jinfeng, ZHOU Yongzhang, ZHENG Yijun, LU Kefei, LIN Xingyu, WANG Hanyu, ZHANG Can Earth Science Frontiers    2024, 31 (4): 139-146.   DOI: 10.13745/j.esf.sf.2024.5.15 Abstract （1119）   HTML （12）    PDF（pc） （2487KB）（1437）       Knowledge map    Save Geological sequestration can be used to reduce CO2 emission without much effect on economic growth. It has become an indispensable technical approach to achieving dual-carbon goals. However, geological sequestration carries significant environmental risks from CO2 leakage at storage sites. To ensure the safety and efficacy of carbon sequestration it is critical that potential leaks can be identified through continuous monitoring. In this regard, the Internet of Things (IoT) is ideal due to its large-scale, continuous monitoring, and intelligent analysis capabilities, yet this technology has not been widely implemented. This paper outlines the basis for sensor selection and sensor node deployment, proposes the design idea for underlying sensor technology, and establishes an IoT CO2 monitoring system for storage sites. Specifically, infrared CO2 sensor is selected as the primary sensor and laser CO2 sensor as the secondary sensor, along with FT-IR patrol monitoring; a combination of real-time optimization of mobile deployment, random deployment, and fixed deployment is used in sensor node deployment; a mix of cluster topology and mesh topology is used in high-risk areas, and star topology and tree topology are used in edge areas connected to the main area. As technology advances, sensor mass production and sensor miniaturization will lead to more efficient and scalable sensor networks, and IoT monitoring technology will play a crucial role in continuous monitoring of carbon storage sites. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Intelligent application of knowledge graphs in mineral prospecting: A case study of porphyry copper deposits in the Qin-Hang metallogenic belt ZHANG Qianlong, ZHOU Yongzhang, GUO Lanxuan, YUAN Guiqiang, YU Pengpeng, WANG Hanyu, ZHU Biaobiao, HAN Feng, LONG Shiyao Earth Science Frontiers    2024, 31 (4): 7-15.   DOI: 10.13745/j.esf.sf.2024.5.2 Abstract （1117）   HTML （37）    PDF（pc） （5269KB）（625）       Knowledge map    Save The mineral exploration knowledge graph (MEKG) is a component of Earth system-mineralization system-mining system correlation graphs, which represents an intersection between Earth science and data science and provides a novel approach for the prediction and evaluation of mineral resources. The conventional mineral exploration methods suffer from information asymmetry/inefficiency/inaccuracy, thus have limitations in effective utilization of geological data. To address this issue, we collect knowledge data relating to porphyry copper ore in the Qin-Hang mineralization belt using both primary and literature data sources, and construct a MEKG with automated knowledge extraction and reasoning using natural language processing (NLP) techniques. Briefly, the MEKG model represents the entities and attributes of porphyry copper ore and their relationships in the Qin-Hang mineralization belt; based on this framework, NLP techniques are used to semantically correlate and reason over the knowledge graph, enabling automated knowledge extraction and reasoning. In addition, we develop a Q&A and visualization system that allows users to query entities/attributes and their relationships to obtain relevant information and visualize the data structure and data relationship. This study demonstrates the effectiveness and accuracy of knowledge-based intelligent applications in porphyry copper ore exploration in the Qin-Hang belt through experimentation and testing. Compared with traditional methods, this application provides more comprehensive and accurate mining suggestions in a short time to aid geological exploration decision-making. Also this study can serve as reference for other mineral exploration fields. In the future, we aim to further enhance the performance and functionality of this knowledge model by broadening the graph algorithm applications and recommendation systems, so as to meet the needs of mineral explorations under different scenarios and expand the model’s application potential to other related fields. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Ontology-guided knowledge graph construction for mineral prediction YE Yuxin, LIU Jiawen, ZENG Wanxin, YE Shuisheng Earth Science Frontiers    2024, 31 (4): 16-25.   DOI: 10.13745/j.esf.sf.2024.5.4 Abstract （1115）   HTML （13）    PDF（pc） （5732KB）（435）       Knowledge map    Save Knowledge graph construction is an effective means of acquiring and representing knowledge in data-driven research, however, existing knowledge graphs have many problems and limitations in mineral resource prediction. Firstly, relevant studies are few while existing knowledge graphs lack spatiotemporal semantics, which limits the effective representation and analysis of the spatiotemporal characteristics of mineral resources. Secondly, existing graph construction methods emphasize text extraction at the data level, but lack ontology construction involving complex logical relationships and lack effective association between ontology and data layers. As a result, existing knowledge graphs lack in-depth and sufficient semantic information to meet the requirement of mineral resource prediction in expressing complex geoscience concepts and relationships. To address this issue, this study takes an ontology-guided approach to construct a knowledge graph suitable for mineral prediction tasks. We first construct the initial domain ontology on the basis of in-depth understanding of mineral prediction theories and methods; we then integrate the domain ontology with selected mature geological time ontology and geographical space ontology to expand the initial ontology—by embedding spatiotemporal semantics we can effectively express the spatiotemporal characteristics of mineral resources. We also pay attention to the association between ontology and data layers—by establishing rich semantic relationships we can achieve effective inter-node connection and information sharing in the knowledge graph. Experimental results show that the knowledge graph outperformed other existing graphs in terms of knowledge richness and confidence. This study provides a methodology for multi-ontology based knowledge graph construction for mineral prediction, thereby promoting further development of this field. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Machine-readable expression of unstructured geological information and intelligent prediction of mineralization associated anomaly areas in Pangxidong District, Guangdong, China WANG Kunyi, ZHOU Yongzhang Earth Science Frontiers    2024, 31 (4): 47-57.   DOI: 10.13745/j.esf.sf.2024.5.5 Abstract （1104）   HTML （16）    PDF（pc） （6558KB）（448）       Knowledge map    Save The application of big data mining and machine learning algorithms in mineralization prediction has become an important research trend, but unstructured geological data cannot be directly mined—first they need to be converted to machine-readable expressions. In this study of the Pangxidong ore district in western Guangdong Province, the unstructured geological information such as stratigraphy, lithology, faults are converted into machine-readable format, and two machine learning algorithms, namely, One-Class Support Vector Machine and Auto-Encoder Network, are applied to mine the geochemical test data of stream sediments as well as the comprehensive geological information on faults, stratigraphy, etc. to extract the features of mineralization anomalies and ultimately achieve intelligent delineation of the anomaly areas. Through combined application of One-Hot Encoder and the weighted variable method for spatially weighted principal component analysis, the structural transformation of the unstructured geological information is realized, and geological information is maximally preserved for data mining. It is demonstrated that the application of One-Class Support Vector Machine and Auto-Encoder Network can effectively solve the problem of data imbalance, as the numbers of ore and non-ore spots in the study area are seriously unbalanced. The prediction results generated using the integrated, synthesized multi-source geological data are relatively consistent with the observed spatial distribution of Pb-Zn deposits and the actual geological structure in the study area, indicating the two algorithms can effectively identify potential prospecting targets and ore deposits. Compared with traditional geochemical prospecting methods, the intelligent prediction method can process and integrate multi-source geological information about the ore-forming processes and identify mineralization anomaly areas. This method is applicable in prospecting areas without prior ore discovery, thereby improving the efficiency of ore prospecting and increasing the possibility of finding ore deposits. Table and Figures | Reference | Related Articles | Metrics | Comments（0）