☆ 4.7 Article

A physically constrained hybrid deep learning model to mine a geochemical data cube in support of mineral exploration

COMPUTERS & GEOSCIENCES (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Geosciences, Multidisciplinary

Mineral Prospectivity Mapping Using Deep Self-Attention Model

Bojun Yin et al.

Summary: Multi-source data integration is effective for improving mineral prospectivity mapping accuracy. A deep self-attention model was used in this study to integrate multiple evidence layers and consider their correlations and spatial heterogeneity. A case study in the Suizao district, Hubei Province, China, demonstrated the advantages of the model in producing potential maps for gold mineralization.

NATURAL RESOURCES RESEARCH (2023)

添加到收藏夹

Article Geochemistry & Geophysics

Geochemical survey data cube: A useful tool for lithological classification and geochemical anomaly identification

Ying Xu et al.

CHEMIE DER ERDE-GEOCHEMISTRY (2023)

添加到收藏夹

Article Geosciences, Multidisciplinary

Graph Deep Learning Model for Mapping Mineral Prospectivity

Renguang Zuo et al.

Summary: Mineral prospectivity mapping aims to reduce search areas for mineral deposits. Pixel-wise models lack consideration of spatial associations, while image-based models capture spatial patterns but require regular input data. Graph-based models, employed in this study, effectively capture mineralization information and spatial interrelations between minerals and prospecting information.

MATHEMATICAL GEOSCIENCES (2023)

添加到收藏夹

Article Geosciences, Multidisciplinary

Revealing Geochemical Patterns Associated with Mineralization Using t-Distributed Stochastic Neighbor Embedding and Random Forest

Zixian Shi et al.

Summary: The hybrid model combining t-SNE and RF can effectively recognize geochemical anomalies associated with gold mineralization. Compared with PCA, t-SNE can better identify hidden information in complex and nonlinear geochemical survey data and reduce information redundancy, thus improving the efficiency of RF for processing multidimensional geochemical survey data. The high-probability areas obtained by t-SNE + RF have a strong spatial correlation with known gold deposits, which can provide critical clues for further prospecting in the study area.

MATHEMATICAL GEOSCIENCES (2023)

添加到收藏夹

Article Geosciences, Multidisciplinary

Deep Reinforcement Learning for Mineral Prospectivity Mapping

Zixian Shi et al.

Summary: Machine learning algorithms, including supervised and unsupervised learning ones, are widely used in mineral prospectivity mapping. Reinforcement learning (RL) is a type of machine learning algorithm that differs from supervised and unsupervised learning models in that the learning process is performed interactively by the agent and environment. A deep RL framework was constructed for mineral prospectivity mapping, and a case study in northwest Hubei Province, China, demonstrated its effectiveness in identifying high-potential areas for gold prospecting.

MATHEMATICAL GEOSCIENCES (2023)

添加到收藏夹

Article Geosciences, Multidisciplinary

Metallogenic-Factor Variational Autoencoder for Geochemical Anomaly Detection by Ad-Hoc and Post-Hoc Interpretability Algorithms

Zijing Luo et al.

Summary: This study utilized the SHAP framework combined with VAE to construct a reliable and interpretable DML model. It selected suitable elemental associations related to mineralization by sorting the importance of elements. The metallogenic-factor VAE model constructed based on the metallogenic model in Hubei Province exhibited satisfactory interpretability and performance, providing critical clues for future mineral exploration.

NATURAL RESOURCES RESEARCH (2023)

添加到收藏夹

Article Geosciences, Multidisciplinary

An Interpretable Graph Attention Network for Mineral Prospectivity Mapping

Ying Xu et al.

Summary: This study proposes an interpretable graph attention network (GAN) to map the mineral potential for Fe polymetallic mineralization in southwestern Fujian Province of China. By adding prior domain knowledge, an interpretable GAN is constructed. In the training process, a soft geological constraint is achieved by adding a penalty term to the GAN's loss function based on a nonlinear relationship between prospectivity density and distance to controlling features. Furthermore, a hidden layer is added to implement a hard geological constraint based on ore-forming controlling features. A comparative study shows that the interpretable GAN improves the probability in areas with high mineralization potential and increases result interpretability.

MATHEMATICAL GEOSCIENCES (2023)

添加到收藏夹

Article Geochemistry & Geophysics

The graph attention network and its post-hoc explanation for recognizing mineralization-related geochemical anomalies

Ying Xu et al.

Summary: Deep learning algorithms have emerged as a cutting-edge technology for analyzing geochemical survey data and identifying patterns related to mineralization. Graph-based models have the potential to capture spatial information and effectively measure the relationships between metallogenic information and geochemical survey sites. This study used a graph attention network (GAT) to identify geochemical anomalies associated with gold mineralization in western Henan Province, China.

APPLIED GEOCHEMISTRY (2023)

添加到收藏夹

Article Geosciences, Multidisciplinary

A New Generation of Artificial Intelligence Algorithms for Mineral Prospectivity Mapping

Renguang Zuo et al.

Summary: We propose new generation AI algorithms for mineral prospectivity mapping that prioritize interpretability and domain cognitive consistency. These algorithms allow for the integration of geological and expert knowledge, offer transparency in information transfer, extract new prospecting information, and improve mineral exploration targeting. Essential strategies are also proposed to strengthen the MPM workflow.

NATURAL RESOURCES RESEARCH (2023)

添加到收藏夹

Article Geosciences, Multidisciplinary

A Physically Constrained Variational Autoencoder for Geochemical Pattern Recognition

Yihui Xiong et al.

Summary: This study introduces a physically constrained VAE architecture for identifying geochemical patterns associated with tungsten polymetallic mineralization. By incorporating physical and geological constraints, the accuracy and consistency of geochemical pattern recognition are improved.

MATHEMATICAL GEOSCIENCES (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

Robust Feature Extraction for Geochemical Anomaly Recognition Using a Stacked Convolutional Denoising Autoencoder

Yihui Xiong et al.

Summary: The study utilized a stacked convolutional denoising autoencoder (SCDAE) to recognize multivariate geochemical anomalies related to mineralization and optimized network parameters through experiments. Results showed that the SCDAE exhibited reduced sensitivity to various levels of stochastic disturbances and enhanced ability to recognize geochemical anomalies.

MATHEMATICAL GEOSCIENCES (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

Mineral Prospectivity Mapping via Gated Recurrent Unit Model

Bojun Yin et al.

Summary: This study utilized a GRU model for mineral prospectivity mapping in the Baguio District of Philippines, incorporating data augmentation and building total permutations of evidence layers for training samples. The results demonstrated the excellent performance of GRU in MPM, with delineated high-anomaly areas closely related to known mineral deposits.

NATURAL RESOURCES RESEARCH (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A geologically-constrained deep learning algorithm for recognizing geochemical anomalies

Chunjie Zhang et al.

Summary: In this study, a geologically-constrained deep learning algorithm was proposed to extract multivariate geochemical anomalies associated with W polymetallic mineralization. The algorithm used fractal analysis to quantify the spatial distribution of known mineral deposits and used this prior knowledge as a geological constraint for delineating geochemical anomalies. Comparative studies showed that the geologically-constrained deep learning algorithm produced more reasonable and interpretable results that were consistent with the regional metallogenic law.

COMPUTERS & GEOSCIENCES (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Recognition and incorporation of mineralization-efficient fault systems to produce a strengthened anisotropic geochemical singularity

Saeid Ghasemzadeh et al.

Summary: This study proposed a strengthened singularity mapping technique that incorporates efficient fault systems to identify geochemical anomalies. The use of this enhanced spatially weighted model improves the effectiveness of mineral exploration compared to existing methods.

JOURNAL OF GEOCHEMICAL EXPLORATION (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

A Geologically Constrained Variational Autoencoder for Mineral Prospectivity Mapping

Renguang Zuo et al.

Summary: In this study, a geologically constrained variational autoencoder (VAE) was proposed to map prospectivity for gold mineralization in the Baguio District of the Philippines. The geologically constrained VAE can enhance the probabilities in areas with high potential for mineralization and increase the interpretability of the obtained results compared to traditional VAE methods.

NATURAL RESOURCES RESEARCH (2022)

添加到收藏夹

Article Environmental Sciences

Application and Evaluation of Deep Neural Networks for Airborne Hyperspectral Remote Sensing Mineral Mapping: A Case Study of the Baiyanghe Uranium Deposit in Northwestern Xinjiang, China

Chuan Zhang et al.

Summary: This study utilized deep neural network models to identify and map minerals in hyperspectral remote sensing images. By comparing with other methods, it demonstrated the effectiveness of deep learning in improving mineral identification ability in remote sensing images, especially for spectrally similar minerals. The introduction of spatial information in the 1D and 2D CNN model improved the discrimination accuracy for minerals with similar spectral characteristics.

REMOTE SENSING (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

Mineral Exploration Using Subtle or Negative Geochemical Anomalies

Renguang Zuo

Summary: This study demonstrates the identification of subtle geochemical anomalies and the significance of negative geochemical anomalies through two case studies. Opportunities and challenges in evaluating subtle geochemical anomalies associated with mineralization, and benefits of mapping negative anomalies are discussed.

JOURNAL OF EARTH SCIENCE (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Knowledge discovery of geochemical patterns from a data-driven perspective

Bojun Yin et al.

Summary: This study focuses on data-driven knowledge discovery of geochemical patterns in mineral exploration, specifically exploring the spatial correlation and elemental associations related to Au-Sb mineralization. The results of using various data-driven procedures, such as LISA, PCA, and DAN, show promising potential for identifying geochemical anomalies and providing clues for further mineral exploration.

JOURNAL OF GEOCHEMICAL EXPLORATION (2021)

添加到收藏夹

Review Geochemistry & Geophysics

The processing methods of geochemical exploration data: past, present, and future

Renguang Zuo et al.

Summary: Geochemical exploration data is crucial in mineral exploration for discovering unknown mineral deposits. Advanced methods for processing and identifying geochemical anomalies have been developed, with a focus on distribution laws of geochemical elements concentrations. Future trends point towards the use of deep learning algorithms for mining and extracting targets associated with mineralization.

APPLIED GEOCHEMISTRY (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Graph Convolutional Networks for Hyperspectral Image Classification

Danfeng Hong et al.

Summary: This article thoroughly investigates the applications of Convolutional Neural Networks (CNNs) and Graph Convolutional Networks (GCNs) in hyperspectral image classification. By developing a new minibatch GCN (miniGCN) to train and infer large-scale GCNs, as well as exploring fusion strategies for different types of HS features, the study achieves good classification performance.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

添加到收藏夹

Article Geology

Recognition of multivariate geochemical anomalies associated with mineralization using an improved generative adversarial network

Chunjie Zhang et al.

Summary: In this study, the ALAD algorithm, which combines the advantages of deep variational autoencoder and generative adversarial network, significantly improved the detection performance of geochemical anomalies. By conducting experiments to identify geochemical anomalies related to mineralization, a well-designed network structure was able to achieve high spatial consistency with discovered mineralization locations.

ORE GEOLOGY REVIEWS (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Recognition of geochemical anomalies using a deep variational autoencoder network

Zijing Luo et al.

APPLIED GEOCHEMISTRY (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Recognizing multivariate geochemical anomalies for mineral exploration by combining deep learning and one-class support vector machine

Yihui Xiong et al.

COMPUTERS & GEOSCIENCES (2020)

添加到收藏夹

Article Geochemistry & Geophysics

Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model for Hyperspectral Image Classification

Cheng Deng et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Deep learning and process understanding for data-driven Earth system science

Markus Reichstein et al.

NATURE (2019)

添加到收藏夹

Article Geosciences, Multidisciplinary

Mapping Geochemical Anomalies Through Integrating Random Forest and Metric Learning Methods

Ziye Wang et al.

NATURAL RESOURCES RESEARCH (2019)

添加到收藏夹

Review Geosciences, Multidisciplinary

Deep learning and its application in geochemical mapping

Renguang Zuo et al.

EARTH-SCIENCE REVIEWS (2019)

添加到收藏夹

Article Geology

Mapping geochemical anomalies related to Fe-polymetallic mineralization using the maximum margin metric learning method

Ziye Wang et al.

ORE GEOLOGY REVIEWS (2019)

添加到收藏夹

Article Geosciences, Multidisciplinary

Big Data Analytics of Identifying Geochemical Anomalies Supported by Machine Learning Methods

Renguang Zuo et al.

NATURAL RESOURCES RESEARCH (2018)

添加到收藏夹

Article Geosciences, Multidisciplinary

Geochemical modeling of orogenic gold deposit using PCANN hybrid method in the Alut, Kurdistan province, Iran

Mohammadjafar Mohammadzadeh et al.

JOURNAL OF AFRICAN EARTH SCIENCES (2018)

添加到收藏夹

Article Geochemistry & Geophysics

Identification of geochemical anomalies via local RX anomaly detector

Yihui Xiong et al.

JOURNAL OF GEOCHEMICAL EXPLORATION (2018)

添加到收藏夹

Article Geochemistry & Geophysics

A spatially weighted singularity mapping method applied to identify epithermal Ag and Pb-Zn polymetallic mineralization associated geochemical anomaly in Northwest Zhejiang, China

Fan Xiao et al.

JOURNAL OF GEOCHEMICAL EXPLORATION (2018)

添加到收藏夹

Article Geochemistry & Geophysics

Learning and Transferring Deep Joint Spectral-Spatial Features for Hyperspectral Classification

Jingxiang Yang et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data

Anuj Karpatne et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2017)

添加到收藏夹

Article Geochemistry & Geophysics

Comparing compositional multivariate outliers with autoencoder networks in anomaly detection at Hamich exploration area, east of Iran

Hamid Moeini et al.

JOURNAL OF GEOCHEMICAL EXPLORATION (2017)

添加到收藏夹

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Recognition of geochemical anomalies using a deep autoencoder network

Yihui Xiong et al.

COMPUTERS & GEOSCIENCES (2016)

添加到收藏夹

Review Geosciences, Multidisciplinary

Spatial analysis and visualization of exploration geochemical data

Renguang Zuo et al.

EARTH-SCIENCE REVIEWS (2016)

添加到收藏夹

Review Geosciences, Multidisciplinary

Tectonic architecture and multiple orogeny of the Qinling Orogenic Belt, Central China

Yunpeng Dong et al.

GONDWANA RESEARCH (2016)

添加到收藏夹

Article Geochemistry & Geophysics

Identifying geochemical anomalies associated with Au-Cu mineralization using multifractal and artificial neural network models in the Ningqiang district; Shaanxi, China

Jiangnan Zhao et al.

JOURNAL OF GEOCHEMICAL EXPLORATION (2016)

添加到收藏夹

Article Multidisciplinary Sciences

A nonlinear controlling function of geological features on magmatic-hydrothermal mineralization

Renguang Zuo

SCIENTIFIC REPORTS (2016)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Fuzzification of continuous-value spatial evidence for mineral prospectivity mapping

Mahyar Yousefi et al.

COMPUTERS & GEOSCIENCES (2015)

添加到收藏夹

Article Geochemistry & Geophysics

Application of staged factor analysis and logistic function to create a fuzzy stream sediment geochemical evidence layer for mineral prospectivity mapping

Mahyar Yousefi et al.

GEOCHEMISTRY-EXPLORATION ENVIRONMENT ANALYSIS (2014)

添加到收藏夹

Article Geosciences, Multidisciplinary

Geology, isotope geochemistry, and ore genesis of the Yindonggou Ag-Au(-Pb-Zn) deposit, Hubei Province, China

Su-Wei Yue et al.

GEOLOGICAL JOURNAL (2014)

添加到收藏夹

Article Geosciences, Multidisciplinary

Triassic tectonics and mineral systems in the Qinling Orogen, central China

Yan-Jing Chen et al.

GEOLOGICAL JOURNAL (2014)

添加到收藏夹

Article Geochemistry & Geophysics

Singularity mapping and spatially weighted principal component analysis to identify geochemical anomalies associated with Ag and Pb-Zn polymetallic mineralization in Northwest Zhejiang, China

Fan Xiao et al.

JOURNAL OF GEOCHEMICAL EXPLORATION (2012)

添加到收藏夹

Article Geochemistry & Geophysics

Singularity theory and methods for mapping geochemical anomalies caused by buried sources and for predicting undiscovered mineral deposits in covered areas

Qiuming Cheng

JOURNAL OF GEOCHEMICAL EXPLORATION (2012)

添加到收藏夹

Review Geology

Mapping singularities with stream sediment geochemical data for prediction of undiscovered mineral deposits in Gejiu, Yunnan Province, China

Qiuming Cheng

ORE GEOLOGY REVIEWS (2007)

添加到收藏夹

Article Geochemistry & Geophysics

Geologic framework and tectonic evolution of the Qinling orogen, central China

QR Meng et al.

TECTONOPHYSICS (2000)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.