Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Menu

Journal Browser

Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Environmental Remote Sensing".

Deadline for manuscript submissions: closed (15 May 2023) | Viewed by 28653

Share This Special Issue

Special Issue Editors

Dr. Rohitash Chandra

E-Mail Website
Guest Editor

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

Dr. Ehsan Farahbakhsh

E-Mail Website
Guest Editor

Department of Mining Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
Interests: mineral exploration; geoinformatics; machine learning; computer vision
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Biswajeet Pradhan

E-Mail Website
Guest Editor

Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), University of Technology Sydney, Sydney, NSW 2007, Australia
Interests: radar image processing remote sensing and GIS applications GIS for engineers forecasting disaster hazard; stochastic analysis and modelling; natural hazards; environmental engineering modelling; geospatial information systems; photogrammetry and remote sensing; unmanned aerial vehicles (UAVs).
Special Issues, Collections and Topics in MDPI journals

Dr. Amin Beiranvand Pour

E-Mail Website
Guest Editor

Institute of Oceanography and Environment (INOS), Universiti Malaysia Terengganu (UMT), Kuala Nerus, Terengganu, Malaysia
Interests: remote sensing; environment; satellite image processing; geological mapping; minerals; exploration geology; mining; exploration geophysics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Remote sensing enables us to observe our planet using different types of data representation with guidance from satellites. This technology has played a crucial role in resource assessment and environmental monitoring since several decades ago by providing multi- and hyperspectral images. According to the increasing demands for different minerals, particularly those applied in modern industries such as renewable energy and the importance of protecting our living environment from the side effects of mining, remote sensing is getting more and more attention. It has been always challenging to process remote sensing data due to computational complexities for detecting features of interest such as hydrothermal alteration zones and mine tailings mainly caused by noise and sparse information. However, there has been good progress in developing machine learning methods to facilitate processing and interpreting remote sensing data since the last decade. Deep learning which is a prominent non-parametric method of machine learning has been popular in the fields such as computer vision and also gaining momentum for processing remote sensing data due to unique challenges such as the curse of dimensionality and other specific domain constraints. Deep learning provides methods to jointly learn from raw input data, a series of features tailored for the task, as well as the optimum parameter values for the underlying classifier. It enables critical automated decision making for remote sensing data despite the common limitations of this kind of data. Deep learning has proven to be efficient for a variety of remote sensing image analysis tasks, particularly in land use and land cover but only a few studies are available in the fields such as lithological and alteration mapping. This special issue is focused on the challenges and recent advancements of deep learning in remote sensing, particularly its applications in resource assessment and environmental monitoring. Our focus is on papers that feature a synergy of remote sensing and deep learning with applications such as mineral prospecting and environmental management.

We aim at highlighting new solutions of deep learning for remote sensing data processing tasks and problems, and manuscript submissions are encouraged from a broad range of related topics, which may include but are not limited to the following:

Mineral exploration
Mineral prospectivity mapping
Alteration mapping
Lithological mapping
Mine tailings
Acid mine drainage
Erosion
Soil and water contamination
Air pollution

Dr. Rohitash Chandra
Dr. Ehsan Farahbakhsh
Prof. Dr. Biswajeet Pradhan
Dr. Amin Beiranvand Pour
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. Remote Sensing is an international peer-reviewed open access semimonthly 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 2700 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

Remote sensing
Deep learning
Image processing
Computer vision
Neural networks
Resource assessment
Environmental monitoring

Published Papers (7 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

28 pages, 26620 KiB

Open AccessArticle

Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers

by Imane Serbouti, Mohammed Raji, Mustapha Hakdaoui, Fouad El Kamel, Biswajeet Pradhan, Shilpa Gite, Abdullah Alamri, Khairul Nizam Abdul Maulud and Abhirup Dikshit

Remote Sens. 2022, 14(21), 5498; https://doi.org/10.3390/rs14215498 - 31 Oct 2022

Cited by 7 | Viewed by 2941

Abstract

In this era of free and open-access satellite and spatial data, modern innovations in cloud computing and machine-learning algorithms (MLAs) are transforming how Earth-observation (EO) datasets are utilized for geological mapping. This study aims to exploit the potentialities of the Google Earth Engine (GEE) cloud platform using powerful MLAs. The proposed method is implemented in three steps: (1) Based on GEE and Sentinel 2A imagery (spectral and textural features), that cover 1283 km² area, a variety of lithological maps are generated using five supervised classifiers (random forest (RF), support vector machine (SVM), classification and regression tree (CART), minimum distance (MD), naïve Bayes (NB)); (2) the accuracy assessments for each class are performed, by estimating overall accuracy (OA) and kappa coefficient (K) for each classifier; (3) finally, the fusion of classification maps is performed using Dempster–Shafer Theory (DST) for mapping lithological units of the northern part of the complex Paleozoic massif of Rehamna, a large semi-arid region located in the SW of the western Moroccan Meseta. The results were quantitatively compared with existing geological maps, enhanced color composite and validated by field survey investigation. In comparison of individual classifiers, the SVM yields better accuracy of nearly 88%, which was 12% higher than the RF MLA; otherwise, the parametric MLAs produce the weakest lithological maps among other classifiers, with a lower OA of approximately 67%, 54% and 52% for CART, MD and NB, respectively. Noticeably, the highest OA value of 96% is achieved for the proposed approach. Therefore, we conclude that this method allows geoscientists to update previous geological maps and rapidly produce more precise lithological maps, especially for hard-to-reach regions. Full article

(This article belongs to the Special Issue Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment)

► Show Figures

Graphical abstract

21 pages, 64979 KiB

Open AccessArticle

A New Method to Evaluate Gold Mineralisation-Potential Mapping Using Deep Learning and an Explainable Artificial Intelligence (XAI) Model

by Biswajeet Pradhan, Ratiranjan Jena, Debojit Talukdar, Manoranjan Mohanty, Bijay Kumar Sahu, Ashish Kumar Raul and Khairul Nizam Abdul Maulud

Remote Sens. 2022, 14(18), 4486; https://doi.org/10.3390/rs14184486 - 08 Sep 2022

Cited by 9 | Viewed by 3623

Abstract

Geoscientists have extensively used machine learning for geological mapping and exploring the mineral prospect of a province. However, the interpretation of results becomes challenging due to the complexity of machine learning models. This study uses a convolutional neural network (CNN) and Shapley additive explanation (SHAP) to estimate potential locations for gold mineralisation in Rengali Province, a tectonised mosaic of volcano-sedimentary sequences juxtaposed at the interface of the Archaean cratonic segment in the north and the Proterozoic granulite provinces of the Eastern Ghats Belt in Eastern India. The objective is to integrate multi-thematic data involving geological, geophysical, mineralogical and geochemical surveys on a 1:50 K scale with the aim of prognosticating gold mineralisation. The available data utilised during the integration include aero-geophysical (aeromagnetic and aerospectrometric), geochemical (national geochemical mapping), ground geophysical (gravity), satellite gravity, remote sensing (multispectral) and National Geomorphology and Lineament Project structural lineament maps obtained from the Geological Survey of India Database. The CNN model has an overall accuracy of 90%. The SHAP values demonstrate that the major contributing factors are, in sequential order, antimony, clay, lead, arsenic content and a magnetic anomaly in CNN modelling. Geochemical pathfinders, including geophysical factors, have high importance, followed by the shear zones in mineralisation mapping. According to the results, the central parts of the study area, including the river valley, have higher gold prospects than the surrounding areas. Gold mineralisation is possibly associated with intermediate metavolcanics along the shear zone, which is later intruded by quartz veins in the northern part of the Rengali Province. This work intends to model known occurrences with respect to multiple themes so that the results can be replicated in surrounding areas. Full article

(This article belongs to the Special Issue Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment)

► Show Figures

Graphical abstract

20 pages, 6333 KiB

Open AccessArticle

A Comparative Study of Convolutional Neural Networks and Conventional Machine Learning Models for Lithological Mapping Using Remote Sensing Data

by Hojat Shirmard, Ehsan Farahbakhsh, Elnaz Heidari, Amin Beiranvand Pour, Biswajeet Pradhan, Dietmar Müller and Rohitash Chandra

Remote Sens. 2022, 14(4), 819; https://doi.org/10.3390/rs14040819 - 09 Feb 2022

Cited by 29 | Viewed by 6848

Abstract

Lithological mapping is a critical aspect of geological mapping that can be useful in studying the mineralization potential of a region and has implications for mineral prospectivity mapping. This is a challenging task if performed manually, particularly in highly remote areas that require a large number of participants and resources. The combination of machine learning (ML) methods and remote sensing data can provide a quick, low-cost, and accurate approach for mapping lithological units. This study used deep learning via convolutional neural networks and conventional ML methods involving support vector machines and multilayer perceptron to map lithological units of a mineral-rich area in the southeast of Iran. Moreover, we used and compared the efficiency of three different types of multispectral remote-sensing data, including Landsat 8 operational land imager (OLI), advanced spaceborne thermal emission and reflection radiometer (ASTER), and Sentinel-2. The results show that CNNs and conventional ML methods effectively use the respective remote-sensing data in generating an accurate lithological map of the study area. However, the combination of CNNs and ASTER data provides the best performance and the highest accuracy and adaptability with field observations and laboratory analysis results so that almost all the test data are predicted correctly. The framework proposed in this study can be helpful for exploration geologists to create accurate lithological maps in other regions by using various remote-sensing data at a low cost. Full article

(This article belongs to the Special Issue Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment)

► Show Figures

Figure 1

16 pages, 37129 KiB

Open AccessArticle

Combining Deep Learning with Single-Spectrum UV Imaging for Rapid Detection of HNSs Spills

by Syed Raza Mehdi, Kazim Raza, Hui Huang, Rizwan Ali Naqvi, Amjad Ali and Hong Song

Remote Sens. 2022, 14(3), 576; https://doi.org/10.3390/rs14030576 - 25 Jan 2022

Cited by 7 | Viewed by 3371

Abstract

Vital transportation of hazardous and noxious substances (HNSs) by sea occasionally suffers spill incidents causing perilous mutilations to off-shore and on-shore ecology. Consequently, it is essential to monitor the spilled HNSs rapidly and mitigate the damages in time. Focusing on on-site and early processing, this paper explores the potential of deep learning and single-spectrum ultraviolet imaging (UV) for detecting HNSs spills. Images of three floating HNSs, including benzene, xylene, and palm oil, captured in different natural and artificial aquatic sites were collected. The image dataset involved UV (at 365 nm) and RGB images for training and comparative analysis of the detection system. The You Only Look Once (YOLOv3) deep learning model is modified to balance the higher accuracy and swift detection. With the MobileNetv2 backbone architecture and generalized intersection over union (GIoU) loss function, the model achieved mean IoU values of 86.57% for UV and 82.43% for RGB images. The model yielded a mean average precision (mAP) of 86.89% and 72.40% for UV and RGB images, respectively. The average speed of 57 frames per second (fps) and average detection time of 0.0119 s per image validated the swift performance of the proposed model. The modified deep learning model combined with UV imaging is considered computationally cost-effective resulting in precise detection accuracy and significantly faster detection speed. Full article

(This article belongs to the Special Issue Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment)

► Show Figures

Graphical abstract

20 pages, 15197 KiB

Open AccessArticle

Synergy of Remote Sensing Data for Exploring Hydrothermal Mineral Resources Using GIS-Based Fuzzy Logic Approach

by Mohamed Abdelkareem and Nassir Al-Arifi

Remote Sens. 2021, 13(22), 4492; https://doi.org/10.3390/rs13224492 - 09 Nov 2021

Cited by 13 | Viewed by 3038

Abstract

The Arabian Nubian Shield (ANS) contains a variety of gold deposits in the form of veins and veinlets formed by hydrothermal fluids. Characterizing potential areas of hydrothermal alteration zones therefore provides a significant tool for prospecting for hydrothermal gold deposits. In this study, we develop a model of exploration for hydrothermal mineral resources in an area located in the ANS, Egypt, using multiple criteria derived from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), Landsat-Operational Land Imager (OLI), and Sentinel-2 data and field work through GIS-based fuzzy logic approach. The hydrothermal alteration zones (HAZs) map extracted from combining mineral indices, spectral bands, and ratios is consistent with observed argillic alteration zones around the mineralized veins. Combining HAZs and lineament density led to identification of six zones based on their mineralization potential, and provides a tool for successful reconnaissance prospecting for future hydrothermal mineral deposits. The detected zones are labeled as excellent, very high, high, moderate, low, and very low, based on their potential for Au production, and the predictive excellent and very high zones cover about 1.6% of the study area. This model also shows that target prospective zones are quartz veins controlled by NNW-SSE trending fracture/fault zones all crosscutting Precambrian rocks of the ANS. Field observations and petrographic and X-ray diffraction analyses were performed to validate the mineral prospective map and revealed that quartz veins consist of gold–sulfide mineralization (e.g., gold, pyrite, chalcopyrite, and sphalerite). Consistency between the high potential hydrothermal alterations zones (HAZs) and the location of gold mineralization is achieved. Full article

(This article belongs to the Special Issue Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment)

► Show Figures

Figure 1

23 pages, 15463 KiB

Open AccessArticle

Large-Scale, Multiple Level-of-Detail Change Detection from Remote Sensing Imagery Using Deep Visual Feature Clustering

by Rasha S. Gargees and Grant J. Scott

Remote Sens. 2021, 13(9), 1661; https://doi.org/10.3390/rs13091661 - 24 Apr 2021

Cited by 6 | Viewed by 2420

Abstract

In the era of big data, where massive amounts of remotely sensed imagery can be obtained from various satellites accompanied by the rapid change in the surface of the Earth, new techniques for large-scale change detection are necessary to facilitate timely and effective human understanding of natural and human-made phenomena. In this research, we propose a chip-based change detection method that is enabled by using deep neural networks to extract visual features. These features are transformed into deep orthogonal visual features that are then clustered based on land cover characteristics. The resulting chip cluster memberships allow arbitrary level-of-detail change analysis that can also support irregular geospatial extent based agglomerations. The proposed methods naturally support cross-resolution temporal scenes without requiring normalization of the pixel resolution across scenes and without requiring pixel-level coregistration processes. This is achieved with configurable spatial locality comparisons between years, where the aperture of a unit of measure can be a single chip, a small neighborhood of chips, or a large irregular geospatial region. The performance of our proposed method has been validated using various quantitative and statistical metrics in addition to presenting the visual geo-maps and the percentage of the change. The results show that our proposed method efficiently detected the change from a large scale area. Full article

(This article belongs to the Special Issue Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment)

► Show Figures

Graphical abstract

37 pages, 35666 KiB

Open AccessArticle

Identification of Phyllosilicates in the Antarctic Environment Using ASTER Satellite Data: Case Study from the Mesa Range, Campbell and Priestley Glaciers, Northern Victoria Land

by Amin Beiranvand Pour, Milad Sekandari, Omeid Rahmani, Laura Crispini, Andreas Läufer, Yongcheol Park, Jong Kuk Hong, Biswajeet Pradhan, Mazlan Hashim, Mohammad Shawkat Hossain, Aidy M Muslim and Kamyar Mehranzamir

Remote Sens. 2021, 13(1), 38; https://doi.org/10.3390/rs13010038 - 24 Dec 2020

Cited by 25 | Viewed by 3966

Abstract

In Antarctica, spectral mapping of altered minerals is very challenging due to the remoteness and inaccessibility of poorly exposed outcrops. This investigation evaluates the capability of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite remote sensing imagery for mapping and discrimination of phyllosilicate mineral groups in the Antarctic environment of northern Victoria Land. The Mixture-Tuned Matched-Filtering (MTMF) and Constrained Energy Minimization (CEM) algorithms were used to detect the sub-pixel abundance of Al-rich, Fe³⁺-rich, Fe²⁺-rich and Mg-rich phyllosilicates using the visible and near-infrared (VNIR), short-wave infrared (SWIR) and thermal-infrared (TIR) bands of ASTER. Results indicate that Al-rich phyllosilicates are strongly detected in the exposed outcrops of the Granite Harbour granitoids, Wilson Metamorphic Complex and the Beacon Supergroup. The presence of the smectite mineral group derived from the Jurassic basaltic rocks (Ferrar Dolerite and Kirkpatrick Basalts) by weathering and decomposition processes implicates Fe³⁺-rich and Fe²⁺-rich phyllosilicates. Biotite (Fe²⁺-rich phyllosilicate) is detected associated with the Granite Harbour granitoids, Wilson Metamorphic Complex and Melbourne Volcanics. Mg-rich phyllosilicates are mostly mapped in the scree, glacial drift, moraine and crevasse fields derived from weathering and decomposition of the Kirkpatrick Basalt and Ferrar Dolerite. Chlorite (Mg-rich phyllosilicate) was generally mapped in the exposures of Granite Harbour granodiorite and granite and partially identified in the Ferrar Dolerite, the Kirkpatrick Basalt, the Priestley Formation and Priestley Schist and the scree, glacial drift and moraine. Statistical results indicate that Al-rich phyllosilicates class pixels are strongly discriminated, while the pixels attributed to Fe³⁺-rich class, Fe²⁺-rich and Mg-rich phyllosilicates classes contain some spectral mixing due to their subtle spectral differences in the VNIR+SWIR bands of ASTER. Results derived from TIR bands of ASTER show that a high level of confusion is associated with mafic phyllosilicates pixels (Fe³⁺-rich, Fe²⁺-rich and Mg-rich classes), whereas felsic phyllosilicates (Al-rich class) pixels are well mapped. Ground truth with detailed geological data, petrographic study and X-ray diffraction (XRD) analysis verified the remote sensing results. Consequently, ASTER image-map of phyllosilicate minerals is generated for the Mesa Range, Campbell and Priestley Glaciers, northern Victoria Land of Antarctica. Full article

(This article belongs to the Special Issue Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment)

► Show Figures

Journal Menu

Journal Browser

Synergy of Remote Sensing and Deep Learning for Mineral Resources and Environment

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (7 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI