Minerals

Research

20 pages, 4712 KiB

Open AccessArticle

Enhancing Deep Learning and Computer Image Analysis in Petrography through Artificial Self-Awareness Mechanisms

by Paolo Dell’Aversana

Minerals 2024, 14(3), 247; https://doi.org/10.3390/min14030247 - 28 Feb 2024

Cited by 2 | Viewed by 1320

In this paper, we discuss the implementation of artificial self-awareness mechanisms and self-reflection abilities in deep neural networks. While the current limitations of research prevent achieving cognitive capabilities on par with natural biological entities, the incorporation of basic self-awareness and self-reflection mechanisms in [...] Read more.

In this paper, we discuss the implementation of artificial self-awareness mechanisms and self-reflection abilities in deep neural networks. While the current limitations of research prevent achieving cognitive capabilities on par with natural biological entities, the incorporation of basic self-awareness and self-reflection mechanisms in deep learning architectures offers substantial advantages in tackling specific problems across various scientific fields, including geosciences. In the first section, we outline the foundational architecture of our deep learning approach termed Self-Aware Learning (SAL). The subsequent part of the paper highlights the practical benefits of this machine learning methodology through synthetic tests and applications addressed to automatic classification and image analysis of real petrological data sets. We show how Self-Aware Learning allows enhanced accuracy, reduced overfitting problems, and improved performances compared to other existing methods. Full article

(This article belongs to the Special Issue Digital Geosciences and Mineral Exploration)

► Show Figures

Figure 1

18 pages, 14600 KiB

Open AccessEditor’s ChoiceArticle

CoDA-Based Geo-Electrochemical Prospecting Prediction of Uranium Orebodies in Changjiang Area, Guangdong Province, China

by Rui Tang, Li Sun, Fei Ouyang, Keyan Xiao, Cheng Li, Yunhui Kong, Miao Xie, Yixiao Wu and Yaxin Gao

Minerals 2024, 14(1), 15; https://doi.org/10.3390/min14010015 - 21 Dec 2023

Viewed by 1305

Abstract

In order to achieve a breakthrough in the exploration of uranium orebodies in the Changjiang area of Guangdong province in China, the geo-electrochemical exploration method is used for mineral resource prediction. The logarithmically and isometric log-ratio (ilr) transformations are applied to the geo-electrochemical [...] Read more.

In order to achieve a breakthrough in the exploration of uranium orebodies in the Changjiang area of Guangdong province in China, the geo-electrochemical exploration method is used for mineral resource prediction. The logarithmically and isometric log-ratio (ilr) transformations are applied to the geo-electrochemical data in this study area to extract geochemical anomalies. The relationship between element associations and mineralization is revealed through descriptive statistical analysis and further biplot analysis. Then, the energy spectrum density–area fractal model (S-A model) is used to identify geochemical backgrounds and anomalies. The results show that: (i) the logarithmically and ilr-transformed data are more uniform, and they more or less obey the rules of normal distribution; (ii) the biplot shows that the ilr-transformed data eliminates the closure effect, and the robust principal component analysis (RPCA) has a better indicative significance for element associations—PC1 reveals the mineralization element association dominated by U and the multiple periods of hydrothermal activity; (iii) the S-A method could extract the local anomalies from different geochemical backgrounds, which indicates mineralization is more reliable. Finally, four favorable prospecting targets are delineated based on the geological and geochemical indicators. Full article

(This article belongs to the Special Issue Digital Geosciences and Mineral Exploration)

► Show Figures

Figure 1

23 pages, 12142 KiB

Open AccessArticle

Prediction of Au-Polymetallic Deposits Based on Spatial Multi-Layer Information Fusion by Random Forest Model in the Central Kunlun Area of Xinjiang, China

by Yuepeng Zhang, Xiaofeng Ye, Shuyun Xie, Jianbiao Dong, Oraphan Yaisamut, Xuwei Zhou and Xiaoying Zhou

Minerals 2023, 13(10), 1302; https://doi.org/10.3390/min13101302 - 8 Oct 2023

Cited by 1 | Viewed by 1361

Abstract

In recent years, there has been a growing emphasis on combining intelligent prospecting algorithms, such as random forest, with extensive geological and mineral data for the purpose of quantitatively predicting exploration geochemistry. This approach holds significant importance for enhancing the accuracy of target [...] Read more.

In recent years, there has been a growing emphasis on combining intelligent prospecting algorithms, such as random forest, with extensive geological and mineral data for the purpose of quantitatively predicting exploration geochemistry. This approach holds significant importance for enhancing the accuracy of target delineation. The central Kunlun area in Xinjiang possesses highly favorable ore-forming geological conditions, offering excellent prospects for mineral exploration. However, the depletion of shallow deposits coupled with a decade-long gap in geological exploration have presented increasing challenges in the quest to discover substantial metal resources. Consequently, there is now a severe shortage of reserve assets in the region, prompting an urgent need for the implementation of new theories, methods, and technologies in mineral resource investigation and evaluation efforts. The researchers used geological and regional geochemical data to construct a random forest metallogenic discriminant model for predicting the mineralization of gold polymetallic minerals in the central Kunlun area of Xinjiang and delineating the metallogenic target area. Two different sampling methods were compared to quantitatively predict gold polymetallic mineral resources. The results indicate that the selected training samples offer higher prediction accuracy and reliability by fully capturing the complex information of the original data. The random forest model using select training samples has valuable applications in metallogenic prospect prediction and potential division due to its ability to consider the actual exploration cost and identify small areas with high potential and a high proportion of ore. This study significantly improves prediction accuracy, reduces exploration risk, and expands the use of machine learning algorithms in mathematical geology in the central Kunlun area of Xinjiang. Full article

(This article belongs to the Special Issue Digital Geosciences and Mineral Exploration)

► Show Figures

Figure 1

20 pages, 5729 KiB

Open AccessArticle

Prediction of Au-Associated Minerals in Eastern Thailand Based on Stream Sediment Geochemical Data Analysis by S-A Multifractal Model

by Oraphan Yaisamut, Shuyun Xie, Punya Charusiri, Jianbiao Dong and Weiji Wen

Minerals 2023, 13(10), 1297; https://doi.org/10.3390/min13101297 - 7 Oct 2023

Cited by 1 | Viewed by 1535

Abstract

Conducted within the scope of geochemical exploration in eastern Thailand, this study aims to detect geochemical anomalies and potential mineral deposits. The objective was to interpret intricate spatial dispersion patterns and concentration levels of deposit pathfinder elements, specifically arsenic (As), copper (Cu), and [...] Read more.

Conducted within the scope of geochemical exploration in eastern Thailand, this study aims to detect geochemical anomalies and potential mineral deposits. The objective was to interpret intricate spatial dispersion patterns and concentration levels of deposit pathfinder elements, specifically arsenic (As), copper (Cu), and zinc (Zn), using a comprehensive array of stream sediment geochemistry data. Methodologies involved integrating multifractal properties and traditional statistics, facilitated by the GeoDAS and ArcGIS platforms as instrumental analytical tools. In total, 5376 stream sediment samples were collected and evaluated, leading to the development of an in-depth geochemical map. The results indicated distinct geological units marked by substantially elevated average values of the aforementioned elements. Identification of geochemical anomalies was achieved through the spatial distribution method and the subsequent application of the spectrum-area (S-A) multifractal model. An intriguing link was found between high As concentrations and gold deposits in the area, suggesting As as a viable pathfinder element for gold mineralization. The anomaly maps, generated from the stream sediment data, spotlighted potential zones of interest, offering valuable guidance for future mineral exploration and geological inquiries. Nonetheless, it is vital to recognize that the increased values noted in these maps may be influenced by regional geological factors, emphasizing the necessity for a diverse set of analytical methods for accurate interpretation. This study’s significance lies in its pioneering use of the S-A multifractal model in geochemical data analysis. This innovative approach has deepened our comprehension of geochemical dispersion patterns and improved the precision of mineral exploration. Full article

(This article belongs to the Special Issue Digital Geosciences and Mineral Exploration)

► Show Figures

Figure 1

22 pages, 18111 KiB

Open AccessArticle

A New Anisotropic Singularity Algorithm to Characterize Geo-Chemical Anomalies in the Duolong Mineral District, Tibet, China

by Jie Tang, Wenlei Wang and Changjiang Yuan

Minerals 2023, 13(7), 988; https://doi.org/10.3390/min13070988 - 24 Jul 2023

Cited by 4 | Viewed by 2018

Abstract

With the increasing exploitation of mineral resources by humans, exploring non-traditional areas for hidden resources such as deep earth and sediment-covered regions has become a significant challenge in the field of mineral exploration. Geochemical data, as a crucial information carrier of geological bodies, [...] Read more.

With the increasing exploitation of mineral resources by humans, exploring non-traditional areas for hidden resources such as deep earth and sediment-covered regions has become a significant challenge in the field of mineral exploration. Geochemical data, as a crucial information carrier of geological bodies, serves as one of the direct and effective sources for quantitative analysis of regional geological evolution and mineralization prediction studies. It plays an indispensable role in geographic information system (GIS)-based mineral exploration. Due to the neglect of spatial distribution characteristics and the variability of statistical features with spatial metrics in traditional statistical methods, this paper employs fractal/multifractal and the local singularity analysis to identify geochemical anomalies from background and characterize geochemical distributions associated with porphyry Cu-Au mineralization in the Duolong mineral district, Tibet, China. A novel algorithm for estimating the singularity index, which takes anisotropy into consideration, is proposed and practically applied to the Duolong district. By comparing with the isotropic singularity index, this new method objectively identifies anisotropic geochemical signatures and investigates non-linear behaviors of ore-forming elements, making it more practical and effective in geo-anomaly extraction. Furthermore, the current method is capable of indicating variations in geochemical distributions at different scales through directional arrows marking analytical windows. The summed-up direction of these multi-scale vectors effectively demonstrates migration trends of ore materials at each location within the study area. The new method can pinpoint the location of ore-forming element accumulation and migration directions, unlocking valuable insights from complex datasets. This promises to revolutionize our understanding of how minerals are formed and distributed within the Earth’s crust. Full article

(This article belongs to the Special Issue Digital Geosciences and Mineral Exploration)

► Show Figures

Figure 1

18 pages, 7396 KiB

Open AccessArticle

Uranium-Bearing Layers of Sandstone Type Uranium Deposits Identification and Three-Dimensional Reconstruction in the Northern Ordos Basin, North-Central China

by Yulei Tan, Laijun Lu, Chen Yang, Jia Zhao and Yan Ding

Minerals 2023, 13(6), 834; https://doi.org/10.3390/min13060834 - 20 Jun 2023

Cited by 3 | Viewed by 1737

Abstract

Sandstone type uranium is the most valuable and has the most potential for mining among the known uranium deposits. In the process of forming, the hydrolytic migration and enrichment of uranium require special basin sedimentary environment and tectonic background. Therefore, the mineralization process [...] Read more.

Sandstone type uranium is the most valuable and has the most potential for mining among the known uranium deposits. In the process of forming, the hydrolytic migration and enrichment of uranium require special basin sedimentary environment and tectonic background. Therefore, the mineralization process of sandstone type uranium deposits has certain layering characteristics and distribution rules in the underground vertical depth space. It is important to mine the spatial distribution characteristics of vertical uranium-bearing layers, and thus, reconstruct the three-dimensions of uranium orebodies. In this paper, according to the metallogenic law and distribution characteristics of sandstone type uranium in the underground vertical space, a nonlinear uranium-bearing layers identification (NULI) method of sandstone type uranium is proposed by using different types, resolutions and scales of borehole data. Then, the depth of uranium mineralization for the Daying uranium deposit within northern Ordos Basin is identified accurately and the spatial distribution characteristics of the uranium-bearing layer on the exploration line are obtained. Finally, the occurrence mode of the underground uranium orebodies are presented by using three-dimensional reconstruction analysis. It provides a basis for the prediction, exploration and mining of sandstone type uranium deposits within the Ordos Basin. Full article

(This article belongs to the Special Issue Digital Geosciences and Mineral Exploration)

► Show Figures

Figure 1

14 pages, 7637 KiB

Open AccessArticle

Application and Significance of the Wavelet–Fractal Method on the Data of the Induced Polarization Method in the Graphite Deposits of Datong, China

by Yuqi Liang, Qinglin Xia, Mengyu Zhao, Rui Bi and Jiankang Liu

Minerals 2023, 13(6), 760; https://doi.org/10.3390/min13060760 - 31 May 2023

Cited by 2 | Viewed by 1414

Abstract

Wavelet transformation has been widely used in geophysical and geochemical exploration, and the fractal feature of wavelet coefficients has recently stood out from many wavelet threshold methods. We introduced the wavelet–fractal method to analyze the polarizability and resistivity of graphite deposits. Due to [...] Read more.

Wavelet transformation has been widely used in geophysical and geochemical exploration, and the fractal feature of wavelet coefficients has recently stood out from many wavelet threshold methods. We introduced the wavelet–fractal method to analyze the polarizability and resistivity of graphite deposits. Due to the unique nature of graphite-bearing gneiss, characterized by high polarizability and low resistivity, we concluded that the polarizability background mode is better suited to depict the morphology of the graphite-bearing formation, with the resistivity background mode serving as complementary information for verification. Symlets5 is regarded as the optimal mother wavelet to indicate the characteristics of graphite ore by means of comparison and analysis. The polarizability anomalies showed two different linear forms: the direction of the measuring line and the strike of the ore bodies. According to the data of drill holes on the profile, we inferred that the high values of the anomaly mode can be used to delineate the target area where the graphite is enriched. Combining the application of both modes, we used the wavelet–fractal method for the quantitative prediction and effective selection of a potential area with a high grade. The approach used in this current study can be extended to the prospecting of other graphite deposits or sedimentary–metamorphic deposits containing conductive minerals, where geochemical and geophysical data are available. Full article

(This article belongs to the Special Issue Digital Geosciences and Mineral Exploration)

► Show Figures

Figure 1

20 pages, 24260 KiB

Open AccessArticle

CNN2D-SENet-Based Prospecting Prediction Method: A Case Study from the Cu Deposits in the Zhunuo Mineral Concentrate Area in Tibet

by Ke Ding, Linfu Xue, Xiangjin Ran, Jianbang Wang and Qun Yan

Minerals 2023, 13(6), 730; https://doi.org/10.3390/min13060730 - 27 May 2023

Cited by 5 | Viewed by 1697

Abstract

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 [...] Read more.

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. Full article

(This article belongs to the Special Issue Digital Geosciences and Mineral Exploration)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Digital Geosciences and Mineral Exploration

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI