Geodata fusion and deep learning-based improved lithological mapping: A case study from the autonomous district of Yamoussoukro

With the rapid development of deep learning in recent years, the field of remote sensing image processing has gradually started to use some deep learning algorithms to achieve intelligent and fast processing of images, and the results have improved to a certain extent compared to traditional methods. The U-Net convolutional neural network was proposed used in medical image segmentation in 2015. Based on the previous work, we transferred the U-Net to remote sensing image segmentation to realize the pixel level semantic segmentation of remote sensing image end-to-end. Through U-Net training and learning on GF-2 remote sensing image, the overall accuracy of training sets is 93.83%, while the overall accuracy of the test data is 82.27%, the kappa coefficient is 0.7721, and the Mean intersection Over Union (MiOU) is 0.6405. The results showed that the experiment has high segmentation accuracy and generalization ability.

Lithological mapping is important parameters for interpretation, identification and mapping of minerals. Lithological mapping in the study area defines the characteristics of nature of rock types and their association and formation. In this research study Landsat 8 OLI remote sensing data used for lithological mapping of Jahajpur region of Bhilwara super group. The task of lithological mapping completed by analogical and numerical analysis of digital image processing method which involves several digital image processing techniques such as natural band combination, false color composite, principal component analysis, band ratio and minimum noise fraction. The observed result is verified and validated by field survey and published geological survey of India geological map. The observe result have shown complete correlation and similarity with established map.

This study focused on evaluating the efficiency and complementarity of image enhancement techniques for lithological discrimination and mapping in the upper parts of Benue Trough using Landsat 8 data. To achieve this, image enhancement techniques such optimum index factor, band ratio, principal component analysis, and minimum noise fraction were applied on Landsat 8 OLI data covering parts of the Upper Benue Trough. False colour composites (FCC) were created from three most informative derivatives of these image enhancements. The FCCs were compared in terms of their capability to differentiate different lithological units in the study area by comparing the FCCs with existing geological map. The results show that the FCC created from band ratios provided the highest amount of information, while those created based on optimum index factor provided the least amount of information with respect to lithological discrimination. Additionally, it was observed that the FCCs created from the derivatives of band ratio, principal component analysis and minimum noise fraction provide complementarity. Thus, the three FCCs from these three enhancement methods were fused into a single image, which further aided lithological discrimination. By combining the outputs from three image enhancement techniques, most of the sedimentary and crystalline rocks in the study area were successfully delineated. The method adopted in this study particularly the fusion of outputs from band ratio, principal component analysis and minimum noise fraction represents a novel approach that is suitable for lithological mapping in remote areas, particularly arid and semi-arid terrains with considerable rock exposure.

Lithological and alteration mineral mapping for alluvial gold exploration in the south east of Birao area, Central African Republic using Landsat-8 Operational Land Imager (OLI) data

The Wadi Samra–Wadi Kid district in southeastern Sinai, Egypt, has undergone extensive investigation involving remote sensing analysis, field geology studies, petrography, and geochemistry. The main aim of this study is the integration between remote sensing applications, fieldwork, and laboratory studies for accurate lithological mapping for future mineral exploration in the study region. The field relationships between these coincident rocks were studied in the study area. Landsat-8 (OLI) data that cover the investigated area were used in this paper. The different rock units in the study area were studied petrographically using a polarizing microscope, in addition to major and trace analysis using ICP-OES tools. The Operational Land Imager (OLI) images were used with several processing methods, such as false color composite (FCC), band ratio (BR), principal component analysis (PCA), and minimum noise fraction (MNF) techniques for detecting the different types of rock units in the Wadi Kid district. This district mainly consists of a volcano-sedimentary sequence as well as diorite, gabbro, granite, and albitite. Geochemically, the metasediments are classified as pelitic graywackes derived from sedimentary origin (i.e., shales). The Al2O3 and CaO contents are medium–high, while the Fe2O3 and TiO2 contents are very low. Alkaline minerals are relatively low–medium in content. All of the metasediment samples are characterized by high MgO contents and low SiO2, Fe2O3, and CaO contents. The granitic rocks appear to have alkaline and subalkaline affinity, while the subalkaline granites are high-K calc-alkaline to shoshonite series. The alkaline rocks are classified as albitite, while the calc-alkaline series samples vary from monzodiorites to granites. The outcomes of this study can be used for prospecting metallic and industrial mineral exploration in the Wadi Kid district.

Introduction. Detecting oil spills is a critical task in monitoring the marine ecosystem, protecting it, and minimizing the consequences of emergency situations. The development of fast and accurate methods for detecting and mapping oil spills at sea is essential for prompt assessment and response to emergencies. High-resolution aerial photography provides researchers with a tool for remote monitoring of water discoloration. Artificial intelligence technologies contribute to improving and automating the interpretation and analysis of such images. This study aims to develop approaches for identifying oil spilled on water surfaces using neural networks and machine learning techniques.Materials and Methods. Algorithms capable of automatically identifying marine oil spills were developed using computer image analysis and machine learning methods. The U-Net convolutional neural network was employed for image segmentation tasks. The neural network architecture was designed using the PyTorch library implemented in Python. The AdamW optimizer was chosen for training the network. The neural network was trained on a dataset comprising 8,700 images.Results. The performance of oil spill detection on water surfaces was evaluated using metrics such as IoU, Precision, Recall, Accuracy, and F1 score. Calculations based on these metrics demonstrated identification accuracy of approximately 83–88%, confirming the efficiency of the algorithms used.Discussion and Conclusion. The U-Net convolutional network was successfully trained and demonstrated high accuracy in detecting marine oil spills on the given dataset. Future work will focus on developing algorithms using more advanced neural network models and image augmentation methods.

Remote sensing applications for earth studies such as lithological discrimination, geological mapping and potential mineral exploration have shown great success worldwide. Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) Level-1B image includes visible and near-infrared (VNIR) and shortwave infrared (SWIR) bands that have been analysed to discriminate lithology features in meta-sedimentary terrains of Aravalli Supergroup in Udaipur area of Rajasthan, India. The area comprises various types of geological settings and rock types composed of economic valuable deposits of lead, zinc, copper, micas and marbles; they show spectral reflectance distinctly in bands of VNIR and SWIR. The unique spectral signature reflected by lithological unit shows effectiveness in lithological mapping. The reflectance spectra of various rock types, namely, phyllitic dolomite, siliceous dolomite, metagreywacke, quartzite and gneiss, were collected in situ using spectroradiometer and used as reference of ASTER image for the preparation of spectral signature of different lithological units. The image is applied to analysis atmospheric correction using Fast Line-of-sight Atmospheric Analysis of Hypercubes (FLAASH) and empirical line calibration techniques to convert pixel radiance values into reflectance. A minimum noise fraction (MNF) transform is applied to identify the inherent variance of spectral reflectance and effectively discriminates various lithological units. The different types of lithological units are clearly discriminated using MNF method. Spectral Angle Mapper (SAM) classification is an effective tool for differentiating rock types and its distinct mineralogical composition from associated terrains. Spectral Angle Mapper (SAM) classification uses field-derived spectral signature to demarcate various lithological features with its spatial extent. The result shows different lithological units under Aravalli Supergroup, Banded Gneissic Complex and intrusive formations that are composed of meta-arkose, conglomerate, phyllite, mica schist, dolomite, metagreywacke and migmatites in various locations. The extracted geological features using ASTER image show strong resampling with the district resource map and validated using ground truth verification. The overall accuracy of SAM-classified map of lithological units is 73.39% and Kappa coefficient of 0.59. Mapping the lithological features using ASTER image, data coupled with MNF and SAM techniques provides relatively accurate result, and this study may be used for discrimination of lithological units with its spatial characteristics.

Lithological studies and geological unit mappings are generally applicable to many fields of natural resource management. Relatively suitable aquifers have been formed in complex formations in northwest Shahrood due to the presence of carbonate rocks as well as erosion and tectonic forces in the region. This study aims to identify and separate the calcareous formations that can form karst aquifers in the study area. As a result of erosion and tectonic forces, the rocks of the region exhibit spectral fluctuations, making it difficult for mapping geological formations using multispectral images. Therefore, Landsat 8 satellite-based images were processed by adopting the minimum noise fraction (MNF), independent component analysis (ICA), and band ratio (BR). The indices of calcareous formations and shale formations were created by the BR through the spectral behavior of pure pixels. Moreover, the support vector machine (SVM) and maximum likelihood (ML) were employed for classification. The SVM classifier proved more capable of classification than the ML classifier, and the transform ICA outperformed the MNF in the separation of formations. The lithological maps were extracted using the SVM with an overall accuracy (OA) of 68.04%. Furthermore, a method decision tree (DT) was employed to improve the classification accuracy. The DT classifier was then utilized to reclassify lithological maps that were classified by SVM and ML through morphological characteristics and indices of formations The DT classifier improved the lithological map accuracy by 10%. The boundaries of calcareous formations were extracted from non-calcareous formations with an accuracy of 93%, and the regional constructions were separated with an accuracy of ∼80 % . Finally, the lithological map was developed with a kappa of 0.734 and an OA of 78.59%.

Traditional geological mapping is often time-consuming, labor-intensive, and restricted by rugged terrain. This study addresses these challenges by proposing a novel methodology for automated lithological identification in the Ququleke area of the eastern Kunlun Mountains, which pioneers the integration of portable UAV oblique photogrammetry with a Coordinate Attention-enhanced DeepLabV3+ (CA-DeepLabV3+) semantic segmentation framework for geological mapping. Using a DJI Mavic 3M quadcopter, high-resolution oblique photogrammetric orthophotos were captured to build a pixel-level lithology dataset containing four classes: sandstone, diorite, marble, and Quaternary sediments. The CA-DeepLabV3+ model, adapted from the DeepLabV3+ encoder–decoder framework, integrates a lightweight MobileNetV2 backbone and a Coordinate Attention mechanism to strengthen spatial position encoding and fine-scale feature extraction, crucial for detailed lithological discrimination. Experimental evaluation demonstrates that the proposed model achieves an overall accuracy of 97.95%, mean accuracy of 97.80%, and mean intersection over union of 95.71%, representing a 5.48% improvement in mean intersection over union (mIoU) over the standard DeepLabV3+. These results indicate that combining UAV oblique photogrammetry with the CA-DeepLabV3+ network enables accurate lithological mapping in complex terrains. The proposed method provides an efficient and scalable solution for geological mapping and mineral resource exploration, highlighting the potential of low-altitude UAV remote sensing for field-based geological investigations.

The Neoproterozoic basement complex of Egypt outcrops in the Eastern Desert (ED) and southern Sinai, and is regarded to represent the northwestern continuation of the Arabian–Nubian Shield (ANS). The area west of Berenice has been given little attention, although it represents the key to understanding the geologic history of the South Eastern Desert and the entire ED. The present work is an integrated study using remote sensing (Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data imagery) and field-structural data to assess their utility in lithologic mapping and in detecting alteration mineral zones with considerable accuracy. A false-color-composite image, color-ratio composite image, decorrelation stretch, mafic index (MI), and quartz index (QI) were used to discriminate and map the various rock units. Correlation of False-color images of the ASTER band combination (7, 3, 1) with previous lithological mapping studies of the study area allow preliminary discrimination of different lithologies and drawing a base map. Subsequently, ASTER band ratios tested (4/1, 3/1, 12/14) and (4/7, 4/6, 4/10) with the ground truth data were used to refine the base map and construct the digital detailed geologic map. Petrographically, the investigated rock samples show kaolinite, chlorite, and epidote in alteration zones. The spectral angle mapper (SAM)-supervised classification using reference spectra of the USGS spectral library was used for detecting alteration zones. For verification, total accuracy assessment was carried out to evaluate the band combination and band ratios used in the lithologic mapping. That reached to 85.01% for band ratio 4/1, 3/1, 12/14 in RGB.

Geological mapping of the Central Cairo-Suez District of Egypt, using space-borne optical and radar dataset

Land use and land cover mapping using Landsat-8 and Sentinel-2 data in Al Qunfudhah coast, western Saudi Arabia: A comparative study

In the field of mineral exploration, it is strikingly evident that radioactive-bearing mineralization predominantly resides within granitic intrusions and along structural discontinuities. Consequently, the comprehensive mapping of lithological features emerges as a crucial means of accurately guiding the identification of these mineralizations. The present research is dedicated to enhancing the characterization of granitic rocks located within Egypt’s Central Eastern Desert (El-Missikat and El-Erediya regions). These areas have garnered attention due to their notably high concentrations of radioactive mineralizations, prompting the need for a more in-depth investigation. Despite the study area’s importance for potential radioactive mineral deposits, examining the geological map reveals notable challenges and inconveniences. Our research aims to address these issues using remote sensing data and machine learning algorithms (MLAs). We used image processing techniques, including false-color composites (FCCs), principal component analysis (PCA), and independent component analysis (ICA) to identify eight lithological targets and generate reference maps for the study area.The widely used support vector machine (SVM) was trained with informative image combinations, showing reasonable lithological allocations, especially when it fed with FCC 12-6-2 in RGB. Our study found that incorporating dimensionality-reduction techniques like PCA and ICA with FCCs significantly boosted accuracy by over 15%. Using Sentinel-2 imagery and SVM, we created a novel lithological map for the challenging study area, pinpointing mineralization-rich zones, particularly those linked to shear zones within granitic rocks. This map enhances progress in characterizing rock units, and we strongly advocate the use of dimensionality-reduction techniques, such as PCA and ICA, to feed MLAs. These techniques play a crucial role in producing precise, unbiased lithological maps for complex terrains, aiding in the localization of valuable mineral deposits.

In the domains of geological study, natural resource exploitation, geological hazards, sustainable development, and environmental management, lithological mapping holds significant importance. Conventional approaches to lithological mapping sometimes entail considerable effort and difficulties, especially in geographically isolated or inaccessible regions. Incorporating geological surveys and satellite data is a powerful approach that can be effectively employed for lithological mapping. During this process, contemporary RS-enhancing methodologies demonstrate a remarkable proficiency in identifying complex patterns and attributes within the data, hence facilitating the classification of diverse lithological entities. The primary objective of this study is to ascertain the lithological units present in the western section of the Sohag region. This objective will be achieved by integrated Landsat ETM+ satellite imagery and field observations. To achieve our objectives, we employed many methodologies, including the true and false color composition (FCC&TCC), the minimal noise fraction (MNF), principal component analysis (PCA), decoration stretch (DS), and independent component analysis (ICA). Our findings from the field investigation and the data presented offer compelling evidence that the distinct lithological units can be effectively distinguished. A recently introduced geology map has been incorporated within the research area. The sequence of formations depicted in this map is as follows: Thebes, Drunka, Katkut, Abu Retag, Issawia, Armant, Qena, Abbassia, and Dandara. Implementing this integrated technique enhances our comprehension of geological units and their impacts on urban development in the area. Based on the new geologic map of the study area, geologists can improve urban development in the regions by detecting building materials “aggregates”. This underscores the significance and potential of our research in the context of urban development.

This study employs data of the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) sensor to delineate and map the distribution of sedimentary lithologies in the semi-arid region of Kohat Plateau, Pakistan. False color composites (FCC) and various image transformation and enhancement techniques including the principal component analysis (PCA), minimum noise fraction (MNF), and band rationing (BR) were used successfully to differentiate four lithological classes. These lithologies include chemically/biochemically formed beds of the marine environment and detrital sequences of marginal marine to the riverine environment. FCC from original reflectance data, PCA, and BR techniques displayed more prominent lithological variation. To map the lithology and show the potential of ASTER data, field spectrometry over the barren lithologies was carried out. The end-member spectra from field spectrometry shows strong agreement with the pixels spectra from ASTER scene. The Spectral Angle Mapper (SAM) mapping method was then used to produce a classified lithological map, where the image pixels spectra proved more suitable reference, in comparison to the end-member spectra. The accuracy of the classified lithological map was evaluated based on field-based point data, which resulted an overall accuracy of 70% and a Kappa coefficient value of 0.679. Carbonates and evaporites showed relatively higher user and producer accuracies which are attributed to their topographic behavior and weathered scree over the adjacent rock unit. The final lithological map provided a clearer picture of surface geology where the existing geological maps lacked lithological continuity.