☆ 4.7 Article

Recognition of geochemical anomalies using a deep autoencoder network

COMPUTERS & GEOSCIENCES (2016)

期刊

COMPUTERS & GEOSCIENCES

卷 86, 期 -, 页码 75-82

出版社

PERGAMON-ELSEVIER SCIENCE LTD

DOI: 10.1016/j.cageo.2015.10.006

关键词

Autoencoder network; Multivariate geochemical data; Geochemical exploration; Skarn-type iron deposits

类别

Computer Science, Interdisciplinary Applications Geosciences, Multidisciplinary

资金

National Natural Science Foundation of China [41522206]

向作者/读者索取更多资源

Protocol

Reagent

摘要

In this paper, we train an autoencoder network to encode and reconstruct a geochemical sample population with unknown complex multivariate probability distributions. During the training, small probability samples contribute little to the autoencoder network. These samples can be recognized by the trained model as anomalous samples due to their comparatively higher reconstructed errors. The southwestern Fujian district (China) is chosen as a case study area. A variety of learning rates, iterations, and the size of each hidden layer are constructing and training the deep autoencoder networks on all the geochemical samples. The reconstruction error (or, anomaly score) of each training sample is used to recognize multivariate geochemical anomalies associated with Fe polymetallic mineralization. By comparing the results obtained with a continuous restricted Boltzmann machine, we conclude that the autoencoder network can be trained to recognize multivariate geochemical anomalies. Most of the known skarn-type Fe deposits are located in areas with high reconstruction errors or anomaly scores in the anomaly map, indicating that these anomalies may be related to Fe mineralization. (C) 2015 Elsevier Ltd. All rights reserved.

作者

我是这篇论文的作者

点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7

评分不足

次要评分

新颖性

-

重要性

-

科学严谨性

-

评价这篇论文

推荐

Article Geology

Numerical simulation of ore formation within skarn-type Pb-Zn deposits: Implications for mineral exploration and the duration of ore-forming processes

Xunyu Hu, Guangxian Liu, Yuhua Chen, Yufeng Deng, Jinhui Luo, Kun Wang, Yongguo Yang, Yue Li

Summary: This study builds an integrated and simplified model of skarn-type Pb-Zn deposits and uses numerical simulation to describe the formation of mineralization. The results provide useful information for metallogenic research of skarn-type deposits and magmatichydrothermal systems. However, the method used in this research has limitations and future development is needed for more accurate calculations and testing data.

ORE GEOLOGY REVIEWS (2023)

添加到收藏夹

Article Energy & Fuels

Data augmentation for time series regression: Applying transformations, autoencoders and adversarial networks to electricity price forecasting

Sumeyra Demir, Krystof Mincev, Koen Kok, Nikolaos G. Paterakis

Summary: A model's expected generalization error is inversely proportional to its training set size, and artificially expanding the training set size can increase prediction accuracy. This study proposes using autoencoders, variational autoencoders, and Wasserstein generative adversarial networks for time series augmentation, which significantly improves regression accuracies.

APPLIED ENERGY (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Proximal to distal geochemical variations of the Ruwai polymetallic skarn deposit, Central Borneo, Indonesia: Insights from sulfides chemistry and implications to exploration

Arifudin Idrus, Cendi D. P. Dana, Chun -Kit Lai, Andrea Agangi, Ryohei Takahashi, Evin H. Rajagukguk

Summary: This study aims to investigate the geochemical characteristics of the largest polymetallic skarn deposit, the Ruwai deposit, in Borneo. The whole-rock geochemical analysis shows that the skarn is enriched in metals derived from magma, such as Ag, Nb, Co, La, Cu, V, Zr, and Ti. Additionally, elements like As, Pb, and Se are enriched in the skarn, indicating their significant contribution from the metalimestone. Moreover, the analysis of sulfides reveals certain trace metal content patterns that can be utilized as a tool to determine the center of the hydrothermal system in the deposit.

JOURNAL OF GEOCHEMICAL EXPLORATION (2023)

添加到收藏夹

Article Geology

Discriminate between magmatic- and magmatic-hydrothermal ore deposits using Fe isotopes

Yue Wang, Xiangkun Zhu, Chao Tang, Jingwen Mao, Zhaoshan Chang

Summary: The study reveals distinct characteristics of iron isotopes in magmatic and magmatic-hydrothermal origin iron deposits, indicating fractionation processes in magma immiscibility and hydrothermal fluid exsolution. This suggests that iron isotopes can effectively discriminate between mineral deposits of different origins.

ORE GEOLOGY REVIEWS (2021)

添加到收藏夹

Article Geology

Cobalt distribution and enrichment in skarn iron deposits: A case study of the Zhuchong skarn iron deposit, Eastern China

Xian Liang, Fang-Yue Wang, Long Zhang, Jun-Wu Zhang, Chang-Shuai Wei, Yu Fan, Xian-Zheng Guo, Tao-Fa Zhou, Ju-quan Zhang, Qing-Tian Lu

Summary: This study investigates the distribution and enrichment of Co in the Zhuchong iron deposit in the Middle-Lower Yangtze River Valley Metallogenic Belt in eastern China. The results highlight pyrite as the primary carrier of Co and reveal a temperature-dependent enrichment of Co in pyrite at Zhuchong.

ORE GEOLOGY REVIEWS (2023)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Data-driven design exploration method using conditional variational autoencoder for airfoil design

Kazuo Yonekura, Katsuyuki Suzuki

Summary: The study aims to achieve specific shape requirements in mechanical design using CVAE, exploring the relationship between shape and aerodynamic performance. The proposed method is validated through two numerical examples, demonstrating its effectiveness in reducing design time for real turbine design problems.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

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

Renguang Zuo, Ying Xu

Summary: This study proposes a hybrid deep learning model consisting of a one-dimensional convolutional neural network (1DCNN) and a graph convolutional network (GCN) to extract joint spectrum-spatial features from geochemical survey data for mineral exploration. The physically constrained hybrid model performs better in geochemical anomaly recognition compared to other models.

COMPUTERS & GEOSCIENCES (2024)

添加到收藏夹

Article Computer Science, Information Systems

Anomaly-PTG: A Time Series Data-Anomaly-Detection Transformer Framework in Multiple Scenarios

Gang Li, Zeyu Yang, Honglin Wan, Min Li

Summary: This study proposes a time-series anomaly detection framework for multiple scenarios that can capture both long-distance temporal correlations and potential relationships between features. By using parallel transformer GRU as the information extraction module and autoencoder for data reconstruction, the model achieves high detection rate and accuracy for rare anomalies.

ELECTRONICS (2022)

添加到收藏夹

Article Environmental Sciences

Barren ground depressions, natural H2 and orogenic gold deposits: Spatial link and geochemical model

Benjamin Malvoisin, Fabrice Brunet

Summary: A review of H2-rich gases in continental rocks found that they are mainly located near orogenic gold deposits. Two types of geomorphological features, barren ground depressions and small white spots, were observed near orogenic gold deposits. Point pattern analysis revealed that the white spots are self-organized, similar to vegetation patterns associated with termite mounds and fairy circles. A geochemical model was proposed to explain the relationship between orogenic gold deposits, H2 emanations, and geomorphological features.

SCIENCE OF THE TOTAL ENVIRONMENT (2023)

添加到收藏夹

Article Geosciences, Multidisciplinary

Predictive Geochemical Exploration: Inferential Generation of Modern Geochemical Data, Anomaly Detection and Application to Northern Manitoba

Julie E. Bourdeau, Steven E. Zhang, Christopher J. M. Lawley, Mohammad Parsa, Glen T. Nwaila, Yousef Ghorbani

Summary: Geochemical surveys follow a data lifecycle of generation, management, and usage. Currently, predictive analytics is mostly integrated into the usage stage. This study predicts elemental concentrations in lake sediment geochemical data and explores the integration of predictive analytics across the entire data lifecycle. The results demonstrate the potential of modernizing legacy geochemical data to support time-sensitive mineral exploration and propose a new framework called predictive geochemical exploration.

NATURAL RESOURCES RESEARCH (2023)

添加到收藏夹

Article Engineering, Electrical & Electronic

Mixed-type data generation method based on generative adversarial networks

Ning Wei, Longzhi Wang, Guanhua Chen, Yirong Wu, Shunfa Sun, Peng Chen

Summary: This paper proposes a mixed-type data generation model based on generative adversarial networks to synthesize fake data that have the same distribution as real data. The model is able to supplement the lack of training sets and increase the number of available samples. Experimental results show that the proposed method has better performance in preserving the intrinsic distribution compared to other deep learning-based generation algorithms.

EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Application of compositional data analysis in geochemical exploration for concealed deposits: A case study of Ashele copper-zinc deposit, Xinjiang, China

Chaojie Zheng, Panfeng Liu, Xianrong Luo, Meilan Wen, Wenbin Huang, Gang Liu, Xiaogui Wu, Zesu Chen, Stefano Albanese

Summary: The study effectively identified four prospecting prediction targets in the study area through the use of different statistical analysis techniques and data transformation methods on ore body exploration geochemical data.

APPLIED GEOCHEMISTRY (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Principal component analysis and K-means clustering as tools during exploration for Zn skarn deposits and industrial carbonates, Sala area, Sweden

Nils F. Jansson, Rodney L. Allen, Goran Skogsmo, Saman Tavakoli

Summary: This study applies PCA and K-means clustering for data dimension reduction and grouping of multivariate whole-rock lithogeochemical data, aiming to provide a non-biased classification method for dolomite samples useful in exploration vectoring. The results show that PCA can explain 79.69% of dataset variance with three principle components, while K-means clustering reflects relative contents of detrital, biogenic, and hydrothermal components in the marble protoliths. Spatial analysis reveals systematic distribution patterns relative to known deposits, offering an exploration guide.

JOURNAL OF GEOCHEMICAL EXPLORATION (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Infomax-based deep autoencoder network for recognition of multi-element geochemical anomalies linked to mineralization

Saeid Esmaeiloghli, Seyed Hassan Tabatabaei, Emmanuel John M. Carranza

Summary: In recent years, deep autoencoder networks (DANs) have shown great potential in recognizing multi-element geochemical anomalies related to mineralization. A new deep learning architecture called Info-DAN, which chains the information maximization (Infomax) processor to the training network of stacked autoencoders, was proposed to deal with the issues of redundant mutual information and mixed information of elemental concentration data. The Info-DAN technique was applied to stream sediment geochemical data for recognition of metal-vectoring geochemical anomalies, and the results showed that compared to a stand-alone DAN, Info-DAN revealed a stronger spatial correlation between ore-controlling fractures/faults and locations of known metal occurrences.

COMPUTERS & GEOSCIENCES (2023)

添加到收藏夹

Article Geology

In-situ texture and geochemistry of apatite from the Jinling and Zhangjiawa iron skarn deposits, eastern North China Craton: Implications for ore-forming processes and formation of high-grade ores

Ying-Hua Chen, Ting-Guang Lan, Wei Gao, Lei Shu, Yan-Wen Tang, Huan-Long Hu

Summary: Apatites are important for recording the magmatic-hydrothermal processes, and in this study, in-situ textural, geochronological, and geochemical analyses were conducted on apatite grains from representative Fe skarn deposits. The results show multiple generations of apatite and indicate fluid meta-somatism and metasomatism as the controlling factors for iron ore formation. The study also highlights the role of F and Cl contents, as well as oxygen fugacity, in Fe leaching and deposition.

ORE GEOLOGY REVIEWS (2023)

添加到收藏夹

暂无数据

Article Computer Science, Interdisciplinary Applications

An advanced median filter for improving the signal-to-noise ratio of seismological datasets

Yapo Abole Serge Innocent Oboue, Yunfeng Chen, Sergey Fomel, Wei Zhong, Yangkang Chen

Summary: Strong noise can disrupt the recorded seismic waves and negatively impact subsequent seismological processes. To improve the signal-to-noise ratio (S/N) of seismological data, we introduce MATamf, an open-source MATLAB code package based on an advanced median filter (AMF) that simultaneously attenuates various types of noise and improves S/N. Experimental results demonstrate the usefulness and advantages of the proposed AMF workflow in enhancing the S/N of a wide range of seismological applications.

COMPUTERS & GEOSCIENCES (2024)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Advection-based tracking and analysis of salinity movement in the Indian Ocean

Upkar Singh, P. N. Vinayachandran, Vijay Natarajan

Summary: The Bay of Bengal maintains its salinity distribution due to the cyclic flow of high salinity water and the mixing with freshwater. This paper introduces an advection-based feature definition and algorithms to track the movement of high salinity water, validated through comparison with observed data.

COMPUTERS & GEOSCIENCES (2024)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Automated mapping of bedrock-fracture traces from UAV-acquired images using U-Net convolutional neural networks

Bijal Chudasama, Nikolas Ovaskainen, Jonne Tamminen, Nicklas Nordback, Jon Engstro, Ismo Aaltonen

Summary: This contribution presents a novel U-Net convolutional neural network (CNN)-based workflow for automated mapping of bedrock fracture traces from aerial photographs acquired by unmanned aerial vehicles (UAV). The workflow includes training a U-Net CNN using a small subset of photographs with manually traced fractures, semantic segmentation of input images, pixel-wise identification of fracture traces, ridge detection algorithm and vectorization. The results show the effectiveness and accuracy of the workflow in automated mapping of bedrock fracture traces.

COMPUTERS & GEOSCIENCES (2024)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A novel finer soil strength mapping framework based on machine learning and remote sensing images

Ruizhen Wang, Siyang Wan, Weitao Chen, Xuwen Qin, Guo Zhang, Lizhe Wang

Summary: This paper proposes a novel framework to generate a finer soil strength map based on RCI, which uses ensemble learning models to obtain USCS soil classification and predict soil moisture, in order to improve the resolution and reliability of existing soil strength maps.

COMPUTERS & GEOSCIENCES (2024)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Intelligent terrain generation considering global information and terrain patterns

Zhanlong Chen, Xiaochuan Ma, Houpu Li, Xuwei Xu, Xiaoyi Han

Summary: Simulated terrains are important for landform and terrain research, disaster prediction, rescue and disaster relief, and national security. This study proposes a deep learning method, IGPN, that integrates global information and pattern features of the local terrain to generate accurate simulated terrains quickly.

COMPUTERS & GEOSCIENCES (2024)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Physics-Informed Neural Networks for solving transient unconfined groundwater flow

Daniele Secci, Vanessa A. Godoy, J. Jaime Gomez-Hernandez

Summary: Neural networks excel in various machine learning applications, but lack physical interpretability and constraints, limiting their accuracy and reliability in predicting complex physical systems' behavior. Physics-Informed Neural Networks (PINNs) integrate neural networks with physical laws, providing an effective tool for solving physical problems. This article explores recent developments in PINNs, emphasizing their application in solving unconfined groundwater flow, and discusses challenges and opportunities in this field.

COMPUTERS & GEOSCIENCES (2024)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

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

Renguang Zuo, Ying Xu

Summary: This study proposes a hybrid deep learning model consisting of a one-dimensional convolutional neural network (1DCNN) and a graph convolutional network (GCN) to extract joint spectrum-spatial features from geochemical survey data for mineral exploration. The physically constrained hybrid model performs better in geochemical anomaly recognition compared to other models.

COMPUTERS & GEOSCIENCES (2024)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.