AI-Based GIS for Pinpointing Mineral Deposits

A special issue of Minerals (ISSN 2075-163X). This special issue belongs to the section "Mineral Exploration Methods and Applications".

Deadline for manuscript submissions: closed (17 March 2023) | Viewed by 9832

Special Issue Editors

EarthByte Group, School of Geosciences, University of Sydney, Sydney, NSW 2006, Australia
Interests: multidimensional mineral prospectivity modelling; geological remote sensing; data science in mineral exploration
Special Issues, Collections and Topics in MDPI journals
School of Mathematics and Statistics, University of New South Wales, Sydney, NSW 2052, Australia
Interests: deep learning; remote sensing; mineral exploration; environmental and climate sciences
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

With a dwindling in the number of grassroots exploration opportunities, modern-day exploration campaigns are mostly focused on exploring deep-seated, blind, or even covered mineral deposits. However, discovering such mineral deposits is a challenge, given that these are marked by intricate geochemical, geophysical, and geological patterns. Artificial intelligence (AI)-based techniques can help in extracting the subtle patterns in geoscientific data that are linked to the mineralization of the type being sought. In essence, two- and three-dimensional geochemical, geological, and geophysical signatures that are spatially, temporally, and perhaps genetically linked to mineralization should be considered for mineral exploration.

In addition, individual surveys only reveal limited information on mineralization, meaning that mineralization-related signatures outlined by individual surveys should be combined for pinpointing mineral deposits. Developing an AI-aided 4D-geographical information system (GIS), namely a system enabling the analysis, visualization, and integration of 2D- and 3D-based big data concerning their spatial–temporal association with mineralization, is required to discover deep-seated mineral deposits.

Notwithstanding the advancements in geomatics and AI-based algorithms, be they machine- or deep-learning techniques, little has been done to apply these methods in mineral exploration. There is, therefore, a tangible knowledge in the aspects mentioned above that merits further consideration. This Special Issue seeks to cover this knowledge gap by collecting papers on the following topics:

  • Machine- and deep-learning-based geochemical and geophysical pattern recognition for mineral exploration
  • Machine- and deep-learning-based mineral prospectivity mapping (MPM)
  • Novel algorithms for MPM
  • Quantification of uncertainty in 2D/3D-based MPM

Dr. Mohammad Parsa
Dr. Ehsan Farahbakhsh
Dr. Rohitash Chandra
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Minerals is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • geographic information system
  • mineral prospectivity mapping
  • anomaly detection
  • machine learning
  • deep learning
  • uncertainty

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

23 pages, 60457 KiB  
Article
Multi-Dimensional Data Fusion for Mineral Prospectivity Mapping (MPM) Using Fuzzy-AHP Decision-Making Method, Kodegan-Basiran Region, East Iran
by Ali Shabani, Mansour Ziaii, Mehrdad Solimani Monfared, Adel Shirazy and Aref Shirazi
Minerals 2022, 12(12), 1629; https://0-doi-org.brum.beds.ac.uk/10.3390/min12121629 - 17 Dec 2022
Cited by 9 | Viewed by 1769
Abstract
Analyzing and fusing information layers of exploratory parameters is a crucial stride for increasing the accuracy of pinpointing mineral potential zones in the reconnaissance stage of mineral exploration. Remote sensing, geophysical, geochemical, and geology data were analyzed and fused for identify metallic mineralization [...] Read more.
Analyzing and fusing information layers of exploratory parameters is a crucial stride for increasing the accuracy of pinpointing mineral potential zones in the reconnaissance stage of mineral exploration. Remote sensing, geophysical, geochemical, and geology data were analyzed and fused for identify metallic mineralization in the Kodegan-Basiran region (East Iran). Landsat 7 Enhanced Thematic Mapper Plus (ETM+), aeromagnetic data, geological data, and geochemical stream sediment samples were utilized. The study area contains some copper indices and mines. Thus, the main focus of this study was identifying the zones with high potential for metallic copper mineralization. A two-stage methodology was implemented in this study: First, extraction of the exploratory parameters related to metallic mineralization and second is data fusion by the hybrid fuzzy-analytic hierarchy process (Fuzzy-AHP) method. Hydrothermal alterations and iron oxides in the area were mapped by applying the optimum index factor (OIF), band ratio (BR), and least squared fit (LS-Fit) to ETM+ data. Intrusive masses were positioned as one of the effective parameters in identifying metallic mineralization zones using the gradient tensor method to assess aeromagnetic data. In order to determine the threshold concentration and the location of mineralization anomalies, the K-means clustering algorithm, vertical geochemical zonality (Vz) index, as well as concentration-area (C-A) multi fractal and singularity analysis were implemented on the geochemical data. In conclusion, the potential zones of metallic mineralization in the Kodegan-Basiran region were displayed in a mineral prospectivity map (MPM) derived from the Fuzzy-AHP decision-making method. Finally, to validate the prospectivity map of metallic mineralization, a control area was selected and surveyed by collecting mineralogical, petrological, and stream sediment samples. Field works confirmed the mineralization of Cu and Fe sulfides, oxides, and hydroxides. The high potential areas identified in the MPM can be considered as targets for future Cu exploration in the Kodegan-Basiran area. Full article
(This article belongs to the Special Issue AI-Based GIS for Pinpointing Mineral Deposits)
Show Figures

Figure 1

32 pages, 6210 KiB  
Article
Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’Ivoire
by Kassi Olivier Shaw, Kalifa Goïta and Mickaël Germain
Minerals 2022, 12(11), 1453; https://0-doi-org.brum.beds.ac.uk/10.3390/min12111453 - 17 Nov 2022
Viewed by 3089
Abstract
This study aimed to model the prospectivity for placer deposits using geomorphic and landscape parameters. Within a geographic information system (GIS), spatial autocorrelation analysis of 3709 geochemical samples was used to identify prospective and non-prospective targets for columbite-tantalite (Nb-Ta) placer deposits of Hana-Lobo [...] Read more.
This study aimed to model the prospectivity for placer deposits using geomorphic and landscape parameters. Within a geographic information system (GIS), spatial autocorrelation analysis of 3709 geochemical samples was used to identify prospective and non-prospective targets for columbite-tantalite (Nb-Ta) placer deposits of Hana-Lobo (H-L) Geological Complex (West- Central Côte d’Ivoire, West Africa). Based on mineralization system analysis, hydrologic, geomorphologic and landscape parameters were extracted at the locations of the identified targets. Supervised automatic classification approaches were applied, including Random Forest (RF), K-Nearest Neighbors (KNN) and Support Vector Machines (SVM) to find a prospectivity model complex enough to capture the nature of the data. Metrics such as cross-validation accuracy (CVA), Receiver Operating Characteristic (ROC) curves, Area Under Curve (AUC) values and F-score values were used to evaluate the performance and robustness of output models. Results of applying machine-learning algorithms demonstrated that predictions provided by the final RF and KNN models were very close (κ = 0.56 and CVA = 0.69; κ = 0.54 and CVA = 0.68, respectively) and those provided by the SVM models were slightly lower with κ = 0.46 and CVA = 0.63. Independent validation results confirmed the slightly higher performance of both KNN and RF prospectivity models, compared to final SVM. Sensitivity analyses of both KNN and RF prospectivity models for medium and high-grade Nb-Ta deposits show a prediction rate of up to 90%. Full article
(This article belongs to the Special Issue AI-Based GIS for Pinpointing Mineral Deposits)
Show Figures

Figure 1

20 pages, 5195 KiB  
Article
A Correction Method of Positioning for Deep-Sea Camera Data
by Yue Zhao, Shijuan Yan, Gang Yang, Chuanshun Li, Dewen Du, Jun Ye, Xiangwen Ren, Qiukui Zhao and Xinyu Shi
Minerals 2022, 12(9), 1135; https://0-doi-org.brum.beds.ac.uk/10.3390/min12091135 - 07 Sep 2022
Viewed by 1063
Abstract
The deep-sea camera is the most intuitive and effective detection tool for seabed investigation, and the accuracy of camera positioning can ensure its data value. A bundled ultra-short baseline (USBL) positioning system is generally employed to realize the spatial positioning of an underwater [...] Read more.
The deep-sea camera is the most intuitive and effective detection tool for seabed investigation, and the accuracy of camera positioning can ensure its data value. A bundled ultra-short baseline (USBL) positioning system is generally employed to realize the spatial positioning of an underwater camera. The influence of the underwater acoustic environment and other factors cause USBL positioning data to become unstable, leading to abnormalities, or missing data, which creates difficulties for camera positioning. In order to solve the problem, this paper selects the seabed camera data of the “XunMei” mineralization area acquired from the China south Atlantic voyage. Moreover, the USBL positioning data, combined with high-precision terrain, bathymetry, and ship-borne GPS positioning data, were analyzed and mined comprehensively. In order to eliminate the abnormal data, a four-dimensional anomaly culling model of USBL positioning data is established based on the time and space scales through the ArcGIS tool. Then, modeling, simulation, and interpolation prediction are performed for the positioning data after anomaly elimination to achieve the geographic location correction of the hydrothermal sulfide near-bottom camera and its data. This method has achieved good results in practical applications. The corrected water depth profile of the camera survey line is compatible with the high-precision terrain detected at different times in the same area. The characteristics of the corrected video images are compatible with the sample characteristics of the TV grab sampling position. A set of high-quality positioning data (sampling test 5000 points) not participating in the correction model is compared with the corrected USBL data at the same position. The following results are obtained: in the case of a confidence interval of 95%, the correlation coefficient is 1, the significance is 0, there is no significant difference between the corrected data after the simulation and its original positioning data (not participating in the model), and the correction error is below 5 m. This shows that the problem of locating a submarine camera and its data can be solved using the proposed four-dimensional anomaly elimination model established based on the USBL positioning data, high precision terrain, bathymetry and GPS data, and the corresponding cubic polynomial least-squares correction model. Full article
(This article belongs to the Special Issue AI-Based GIS for Pinpointing Mineral Deposits)
Show Figures

Figure 1

16 pages, 145950 KiB  
Article
Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, Brazil
by Victor Silva dos Santos, Erwan Gloaguen, Vinicius Hector Abud Louro and Martin Blouin
Minerals 2022, 12(8), 941; https://0-doi-org.brum.beds.ac.uk/10.3390/min12080941 - 26 Jul 2022
Cited by 3 | Viewed by 2418
Abstract
Mineral prospectivity mapping (MPM), like other geoscience fields, is subject to a variety of uncertainties. When data about unfavorable sites to find deposits (i.e., drill intersections to barren rocks) is lacking in MPM using machine learning (ML) methods, the synthetic generation of negative [...] Read more.
Mineral prospectivity mapping (MPM), like other geoscience fields, is subject to a variety of uncertainties. When data about unfavorable sites to find deposits (i.e., drill intersections to barren rocks) is lacking in MPM using machine learning (ML) methods, the synthetic generation of negative datasets is required. As a result, techniques for selecting point locations to represent negative examples must be employed. Several approaches have been proposed in the past; however, one can never be certain that the points chosen are true negatives or, at the very least, optimal for training. As a consequence, methodologies that account for the uncertainty of the generation of negative datasets in MPM are needed. In this paper, we compare two criteria for selecting negative examples and quantify the uncertainty associated with this process by generating 400 potential maps for each of the three ML methods utilized (200 maps for each criterion), which include random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNC). The results showed that applying a geological constraint to the creation of negative datasets reduced prediction uncertainty and improved overall model performance but produced larger areas of very high probability (i.e., >0.9) when compared to using only the spatial distribution of known deposits and occurrences as a constraint. SHAP values were used to find approximations for the importance of features in nonlinear methods, and kernel density estimations were used to examine how they varied depending on the negative dataset used to train the ML models. Prospectivity models for magmatic-hydrothermal gold deposits were generated using data from the shuttle radar terrain mission, gamma-ray, magnetic lineaments, and proximity to dykes. The Juruena Mineral Province, situated in Northern Mato Grosso, Brazil, represented the case study for this work. Full article
(This article belongs to the Special Issue AI-Based GIS for Pinpointing Mineral Deposits)
Show Figures

Figure 1

Back to TopTop