Search

Intelligent prospecting and prediction are important research foci in the field of mineral resource exploration. To solve the problem of the performance degradation of deep convolutional neural networks, enhancing the attention to target information and suppressing unnecessary feature information, this paper proposes a new prospecting prediction method based on a two-dimensional convolutional neural network (CNN2D). This method mainly uses known Cu deposits as the positive sample labels, adopts the sliding window method for data enhancement, and uses the window area as a unit to extract spatial variation features. It is important to supplement squeeze-and-excitation networks (SENets) to add an attention mechanism to the channel dimension, assign a weight value to each feature layer, and finally make prospecting predictions by matching the features of the known deposit window area and the features of the unknown window area. This method allows the neural network to focus on certain characteristic channels and realizes prospecting prediction in the case where there are few known deposits so that the deep learning method can be more effectively used for the prospecting prediction of mineralization. Based on geological data, geochemical exploration data of water system sediments, and aeromagnetic data, and via this method, this study carried out prospecting prediction of Cu deposits in the Zhunuo area of Tibet and predicted 12 favorable Cu prospecting prediction areas. Combined with previous research results and field exploration, the predicted result is consistent with the established mineralization and prospecting pattern and has good prospects for Cu deposit prospecting. [ABSTRACT FROM AUTHOR]

The cross section is the basic data for building 3D geological models. It is inefficient to draw a large number of cross sections to build an accurate model. This paper reports the use of multi-source and heterogeneous geological data, such as geological maps, gravity and aeromagnetic data, by a conditional generative adversarial network (CGAN) and implements an intelligent generation method of cross sections to overcome the problem of inefficient modeling data based on CGAN. Intelligent generation of cross sections and 3D geological modeling are carried out in three different areas in Liaoning Province. The results show that: (a) the accuracy of the proposed method is higher than the GAN and Variational AutoEncoder (VAE) models, achieving 87%, 45% and 68%, respectively; (b) the 3D geological model constructed by the generated cross sections in our study is consistent with manual creation in terms of stratum continuity and thickness. This study suggests that the proposed method is significant for surmounting the difficulty in data processing involved in regional 3D geological modeling. [ABSTRACT FROM AUTHOR]

[Display omitted] • Expression of geological map information in the form of knowledge graphs to shown regional geological characteristics and connections. • Using the knowledge embedding method to embed the geological map knowledge in order to show the mineralization characteristics. • Knowledge and geochemical data was aligned in space by knowledge embedding gridding to realize the forward integration of knowledge and data, and to realize bi-directional knowledge and data-driven mineral prospectivity. The knowledge graph in geological applications is highly regarded, and its usefulness requires the support of geological survey data. Therefore, this paper proposes a mineral prospectivity mapping (MPM) method that integrates geological map knowledge graphs with geochemical data. The geological map knowledge graph is used in the vectorized form as knowledge features in the training of the mineral prediction model. It is also used for knowledge-based ore-forming interpretation of prospective areas, achieving bidirectional application of knowledge in prediction and interpretation of prediction results. Unlike most knowledge graphs, the geological map knowledge graph represents spatial correlations and geological features in the form of "entity-relation-entity" triplets, with geological map units as entities and assigned geological attributes. Based on this, an MPM process driven by knowledge graph and data is proposed: (1) Convert the geological map knowledge graph into low-dimensional vectors using node2VEC. (2) Align geological knowledge with geochemical data spatially through knowledge embedding gridization, achieving a forward fusion of knowledge and data. (3) Collect the integrated data using window sampling as the training dataset for DenseNet to train the mineral prospection model. A case study was conducted to demonstrate the advantages of the method for producing a potential map linked to gold mineralization in the Rao Feng area, Shaanxi Province, China. The results show that the prospective areas with knowledge graph embedding and geochemical data are better and delineate six unmineralized prospective areas. Ore-forming interpretations based on knowledge graph information were conducted on the prospective areas, demonstrating strong consistency between the ore-forming geological features of the prediction areas and known mineral deposits. [ABSTRACT FROM AUTHOR]

[Display omitted] • In the case of a small number of known deposits and mineral occurrences, the prospecting prediction model based on the Siamese network can extract effective features without relying on prior knowledge to realize supervised prospecting prediction. • On the basis of sliding window data enhancement, this paper generates paired sample data sets by randomly combining deposit samples and non-deposit samples, which can further enhance the data and improve the generalization ability and prediction accuracy of the model to a certain extent. • Compared with the prediction results of the weight of evidence method and the convolutional neural network, the prediction results of the Siamese network are better, and 7 new gold prospecting areas have been discovered in Zhangjiakou, Hebei Province, China. Supervised neural networks constitute an important research area for the intelligent prediction of locations for prospecting mineral deposits. Accurate training of a supervised neural network requires many training samples, something that is often difficult to obtain. This paper reports the use of geological, geochemical, and geophysical data by a Siamese network to overcome the problem of insufficient training samples, and implements a supervised deep learning prospecting prediction method based on the Siamese network. Intelligent prediction for gold deposits prospecting is carried out for the Chongli mineral concentrate area in Zhangjiakou, Hebei Province, China, and compared with the weight of evidence method and convolutional neural network model. The results show that:(a) the performance of the Siamese network model is no less than that of the convolutional neural network (CNN) model and better than that of the weight of evidence (WOE) method; (b) the gold prospective areas differentiated by the established models are strongly consistent with geological and metallogenic characteristics in the study area. This study suggests Siamese network model as an effective mineral prospectivity modeling tool. This method is also suitable for prospecting prediction using geoscience data in other areas. [ABSTRACT FROM AUTHOR]

High-resolution geological mapping is an important supporting condition for mineral and energy exploration. However, high-resolution geological mapping work still faces many problems. At present, high-resolution geological mapping is still generated by expert interpretation of survey lines, compasses, and field data. The work in the field is constrained by the weather, terrain, and personnel, and the working methods need to be improved. This paper proposes a new method for high-resolution mapping using Unmanned Aerial Vehicle (UAV) and deep learning algorithms. This method uses the UAV to collect high-resolution remote sensing images, cooperates with some groundwork to anchor the lithology, and then completes most of the mapping work on high-resolution remote sensing images. This method transfers a large amount of field work into the room and provides an automatic mapping process based on the Simple Linear Iterative Clustering-Convolutional Neural Network (SLIC-CNN) algorithm. It uses the convolutional neural network (CNN) to identify the image content and confirms the lithologic distribution, the simple linear iterative cluster (SLIC) algorithm can be used to outline the boundary of the rock mass and determine the contact interface of the rock mass, and the mode and expert decision method is used to clarify the results of the fusion and mapping. The mapping method was applied to the Taili waterfront in Xingcheng City, Liaoning Province, China. In this study, the Area Under the Curve (AUC) of the mapping method was 0.937. The Kappa test result was k = 0.8523, and a high-resolution geological map was obtained. [ABSTRACT FROM AUTHOR]

The automatic identification of rock type in the field would aid geological surveying, education, and automatic mapping. Deep learning is receiving significant research attention for pattern recognition and machine learning. Its application here has effectively identified rock types from images captured in the field. This paper proposes an accurate approach for identifying rock types in the field based on image analysis using deep convolutional neural networks. The proposed approach can identify six common rock types with an overall classification accuracy of 97.96%, thus outperforming other established deep-learning models and a linear model. The results show that the proposed approach based on deep learning represents an improvement in intelligent rock-type identification and solves several difficulties facing the automated identification of rock types in the field. [ABSTRACT FROM AUTHOR]

Understanding the temporal and spatial evolution of the North China Craton (NCC) basement, formed by amalgamation, is a crucial issue in global geosciences. The Huozhou complex is situated at the core of the Trans-North China Orogen (TNCO) in the NCC and comprises a considerable number of Palaeoproterozoic granitic gneisses, providing valuable insights into the tectonic evolution of the TNCO. In this study, comprehensive field geological surveys, petrology, chronology, geochemistry, and Hf isotope analysis were conducted to investigate the genesis and tectonic context of the Xingtangsi and Zhengnangou granitic gneisses and elucidate the TNCO's tectonic evolution. The Xingtangsi granite gneiss yielded a magmatic zircon age of 2495±34 Ma, implying its Palaeoproterozoic or Archean origin, as previously suggested. Its protolith was I-type peraluminous granite, primarily generated through the partial melting of pre-existing continental crust materials with a small quantity of mantle-derived magma. The Zhengnangou granitic gneiss's protolith was A-type granite, and its magmatic zircon age was 2,190±11 Ma, indicating its Palaeoproterozoic origin rather than Archean. TDM1(Ma) for the Zhengnangou granitic gneiss ranged from 2,424 to 2,498 Ma, TDM2(Ma) varied from 2563 to 2684 Ma, and the εHf(t) value ranged from 1.3 to 3.3. These results suggest that it was primarily derived from newly formed crustal materials without any mantle-derived addition. Integrating our data with the literature, the ∼2.5 Ga magmatic activity in the Huozhou area may have formed in the tectonic setting of the continental arc, and ∼2.2 Ga A-type granite may have formed in a post-collisional extensional environment. [ABSTRACT FROM AUTHOR]

The Central Asian Orogenic Belt (CAOB) is the world's largest accretionary orogenic belt, and its formation is related to the closure of the Paleo-Asian Ocean (PAO). However, the closure time and style of the PAO remain controversial. To address these issues, this paper presents zircon U-Pb dating, whole-rock geochemistry and zircon Lu-Hf isotope analyses of the volcanic rocks in the Faku-Kaiyuan area on the northern margin of the North China Craton. The results show that the Bachagou andesites formed in the Early Permian (287 ± 2 Ma), while the Chaijialing andesites and dacites formed in the Late Permian (253.3 ± 3.7 Ma) and Middle Triassic (244.3 ± 1.3 Ma), respectively. The Bachagou andesites and Chaijialing andesites are enriched in LILEs and LREEs and depleted in HFSEs and HREEs, indicating that they formed in the active continental margins. The Chaijialing dacites show similar geochemical signatures to adakite and formed in a syn-collisional setting. Geochemistry and isotopic analysis indicates that the Bachagou andesites were derived from a partial melting of the mantle wedge that was metasomatized by subduction fluids. The Chaijialing andesites were generated from a metasomatized mantle by slab-derived and sediment fluids. The Chaijialing dacites formed by a partial melting of thickened lower crust. Combined with previous research results, we can conclude that the Eastern PAO closed by a scissor-like movement from west to east during the Late Permian–Middle Triassic. [ABSTRACT FROM AUTHOR]

The Trans-North China Orogen is a major Neoarchean Paleoproterozoic collisional orogenic belt above the North China Craton, formed due to prolonged and complex processes. Even though many Neoarchean-Paleoproterozoic magmatic and metamorphic activities have been reported, due to the Huozhou Complex's small outcropping range, little attention has been paid to the origin of various igneous rocks of the Huozhou Complex in the center of the Trans-North China Orogen. The Huozhou Complex, located south of the Lüliang, Wutai, and Hengshan complexes, is an important window into the Early Precambrian structure and evolution of the North China Craton. Its magma and metamorphism are crucial to understanding the development of the structural evolution of the Trans-North China Orogen. The Huozhou metamorphic complex area exposes a range of Precambrian metamorphic rocks, among which the most extensively dispersed is felsic biotite plagioclase gneiss. In this study comprehensive geological field survey, micropetrology, chronology, geochemistry, and Hf isotope analysis were carried out for the Qinggangping and Anziping gneiss in the north of the Huozhou Complex. The results show that the magmatic zircon age of the Qinggangping gneiss is 2196 ± 14 Ma, and its protolith is I-type granite, formed by partial melting of igneous rocks in the absence of weathering. Its source is mainly the juvenile crust from depleted mantle dating 2431–2719 Ma, with a small amount of mantle-derived material. The Anziping gneiss has a metamorphic zircon age of 1931 ± 13 Ma with an S-type granite protolith belonging to peraluminous granite. The Anziping gneiss is formed by recycling pre-existing crustal components at 2613–2848 Ma. A minor quantity of mantle-derived magma is also introduced to the crust simultaneously. The samples of Qinggangping gneiss and Anziping gneiss show the characteristics of obvious negative Nb, Ti, and P elements in the spider diagram of primitive mantle standardization. This implies that the rocks have the characteristics of magmatic rocks in an island arc or subduction environment, which could have formed in the tectonic environment of the continental margin arc. [ABSTRACT FROM AUTHOR]

The characterization of the concentration, chemical speciation and source of heavy metals in soils is an imperative for pollution monitoring and the potential risk assessment of the metals to animal and human health. A total of 154 surface horizons and 53 underlying horizons of grassland soil were collected from the Baicheng–Songyuan area in Jilin Province, Northeast China, in which the concentrations and chemical fractionations of As, Cd, Cr, Cu, Hg, Ni, Pb, and Zn were investigated. The mean concentrations of heavy metals in grassland topsoil were 7.2, 0.072, 35, 16.7, 0.014, 15.2, 18.3 and 35 mg kg − 1 for As, Cd, Cr, Cu, Hg, Ni, Pb and Zn, respectively, and those averaged contents were lower than their China Environmental Quality Standard values for the Soils, implying that heavy metal concentrations in the studied soils were of the safety levels. The mobility sequence of the heavy metals based on the sum of the soluble, exchangeable, carbonate-bound and humic acid-bound fractions among the seven fractions decreased in the order of Cd 50.4%) > Hg (39.8%) > Cu (26.5%) > As (19.9%) > Zn (19.1%) > Ni (15.9%) > Pb (14.1%) > Cr (4.3%), suggesting Cd and Hg may pose more potential risk of soil contamination than other metals. Multivariate statistical analysis suggested that As, Cr, Cu, Ni, Pb, Zn, Cd and Hg had the similar lithogenic sources, however, Cd and Hg were more relevant to organic matter than other heavy metals, which was confirmed by the chemical speciation analysis of the metals. The study provides a base for local authority in the studied area to monitor the long term accession of heavy metals into grassland soil. [ABSTRACT FROM AUTHOR]

It is useful in the clarifications of pore spaces at different scales in reservoir evaluations, and also helpful to exploit shale oil resources. The analysis of pores and fractures can be used to evaluate the reconstruction effects of pyrolysis in reservoirs. The existing analysis methods mainly adopt single scale data to study pores of certain sizes, which does not fully reflect the pore structures of oil shale. In this study, experiments regarding gas adsorption, SEM, MICP, NMR, and CT were conducted for the purpose of evaluating the effects of pyrolysis on the oil shale from the Wangqing. It was proposed to divide the pore spaces (0.1–106 nm) into seven levels for comparison purposes according to the order of magnitude, and then to evaluate the applicability of each method. The pyrolysis was observed to have caused the porosity of oil shale to markedly increase, and the sizes of the pores were found to change from mainly nano to co-developed micro-nano pores. The results indicated that a single pore detection method has its limitations since it is difficult to obtain multi-scale pore information. In order to understand the pore structures of oil shale, it is necessary to integrate multiple methods. • The pore structure of multi-scale oil shale is analyzed comprehensively. • The influence of pyrolysis on the pore structure of oil shale was evaluated. • The application effect of different measurement methods to oil shale is compared. [ABSTRACT FROM AUTHOR]