Lithological mapping for complex geological formations with mixed classifiers using Landsat 8 data

In this study, the satellite data of ASTER and Landsat 8 OLI were used for the discrimination of lithological units covering the Khyber range. Of the 24 tested band combinations, the most suitable include 632 and 468 of ASTER and 754 and 147 of OLI in the RGB sequence. The data were also tested with two conventional machine learning algorithms (MLAs), namely maximum likelihood classification (MLC) and support vector machine (SVM), for lithological mapping. Principal component analysis (PCA), minimum noise fraction (MNF), band ratios, and color composites in combination with available lithological maps and field data were utilized for training sample collection for the MLC and SVM models to classify the lithological units. The accuracy assessment of SVM and MLC was performed using a confusion matrix, which revealed a higher accuracy of 74.8419% and 72.1217% for ASTER and an accuracy of 58.4833% and 60.0257% for OLI, respectively. The results indicate that ASTER imagery is more suitable for lithological discrimination in the study area due to its high spectral resolution in the VNIR to SWIR range. The experiment revealed that the SVM classification offered the highest overall accuracy of nearly 75% and the kappa coefficient value of 0.7 on ASTER data. This demonstrates the effectiveness of SVM classification in exploring lithological mapping in dry to semi-arid regions.

Tree species’ composition of forests is essential in forest management and nature conservation. We aimed to identify the tree species structure of a floodplain forest area using a hyperspectral image. We proposed an efficient novel strategy including the testing of three dimension reduction (DR) methods: Principal Component Analysis, Minimum Noise Fraction (MNF) and Indipendent Component Analysis with five machine learning (ML) algorithms (Maximum Likelihood Classifier, Support Vector Classification, Support Vector Machine, Random Forest and Artificial Neural Network) to find the most accurate outcome; altogether 300 models were calculated. Post-classification was applied by combining the multiresolution segmentation and filtering. MNF was the most efficient DR technique, and at least 7 components were needed to gain an overall accuracy (OA) of > 75%. Forty-five models had > 80% OAs; MNF was 43, and the Maximum Likelihood was 19 times among these models. Best classification belonged to MNF with 10 components and Maximum Likelihood classifier with the OA of 83.3%. Post-classification increased the OA to 86.1%. We quantified the differences among the possible DR and ML methods, and found that even > 10% worse model can be found using popular standard procedures related to the best results. Our workflow calls the attention of careful model selection to gain accurate maps.

Comparison of Landsat OLI, ASTER, and Sentinel 2A data in lithological mapping : A Case study of Rich area (Central High Atlas, Morocco)

The copper belt of Anti-Atlas is recognized with several mineral occurrences of Cu, Zn, Mn, Ag, Au, and iron. We used ASTER and OLI in lithological and mineral detection and mapping. The lithological mapping was performed using principal components analysis (PCA), minimum noise fraction (MNF), and two classifiers: maximum likelihood (ML) and support vector machine (SVM). The hydrothermally altered zones were detected based on ASTER VNIR/SWIR bands by the integration of Ninomiya indices and constrained energy minimization (CEM) algorithm. In our study area, the enhanced band combinations of ASTER MNF1, PC4, and PC2 and OLI MNF1, PC5, and PC3 were applied for lithological discrimination. The OLI and ML classification shows the best lithological mapping accuracy with an overall accuracy of 91.74% and a 0.90 Kappa coefficient, followed by SVM with an overall accuracy of 88.82% and a 0.86 Kappa coefficient using the same sensor. The hydrothermal alteration mapping reveals alunite, chlorite, calcite, epidote, illite, kaolinite, montmorillonite, muscovite, and pyrophyllite minerals, principally in phyllic and argillic altered areas. The adopted methodology for lithological and mineralogical mapping can be used in other regions with similar criteria to the study area.

Artificial intelligence (AI)-based multispectral remote sensing has been the best supporting tool using limited resources to enhance the lithological mapping abilities with accuracy, supported by ground truthing through traditional mapping techniques. The availability of the dataset, choice of algorithm, cost, accuracy, computational time, data labeling, and terrain features are some crucial considerations that researchers continue to explore. In this research, support vector machine (SVM) and artificial neural network (ANN) were applied to the Sentinel-2 MSI dataset for classifying lithologies having subtle compositional differences in the Kohat Basin’s remote, inaccessible regions within Pakistan. First, we used principal component analysis (PCA), minimum noise fraction (MNF), and available maps for reliable data annotation for training SVM and (ANN) models for mapping ten classes (nine lithological units + water). The ANN and SVM results were compared with the previously conducted studies in the area and ground truth survey to evaluate their accuracy. SVM mapped ten classes with an overall accuracy (OA) of 95.78% and kappa coefficient of 0.95, compared to 95.73% and 0.95 by ANN classification. The SVM algorithm was more efficient concerning computational efficiency, accuracy, and ease due to available features within Google Earth Engine (GEE). Contrarily, ANN required time-consuming data transformation from GEE to Google Cloud before application in Google Colab.

Integration of spectral, spatial and morphometric data into lithological mapping: A comparison of different Machine Learning Algorithms in the Kurdistan Region, NE Iraq

Lithological discrimination using ASTER and Sentinel-2A in the Shibanjing ophiolite complex of Beishan orogenic in Inner Mongolia, China

Accurate and reliable lithological mapping through satellite-borne remote sensing data and image classification approaches has a critical role since it can automatically and promptly identify lithological units over large areas. Most available Pixel-Object Based comparative classification studies have been applied to land use land cover (LULC) studies; however, this research aims to evaluate and compare the performance of these digital classification methods in the field of geological mapping in semi-arid areas, by integrating spectral bands and neo-bands, particularly the Minimum noise fraction (MNF) and the principal component analysis (PCA), of Sentinel-2A satellite imagery, to map the southern of Skhour Rehamna which is located at the western Moroccan Meseta. The analysis results from two different methods, namely, pixel-based image analysis (PBIA) with k-nearest neighbour (K-NN) and Random Forest (RF) machine learning algorithms (MLAs), and Geographic Object-Based Image Analysis (GEOBIA) were assessed and compared. PBIA method involved selection of training areas whether it was k-NN or RF MLAs, and produced lithological maps that exhibit “salt and pepper” effects as well as problems associated to delineating accurate lithological boundaries, while GEOBIA approach involved multi-resolution segmentation step where scale, shape and compactness parameters should be adjusted as accurate as possible, in order to segment the image into homogeneous and meaningful regions so that the resulted samples were classified using Standard Nearest Neighbour algorithm. Therefore, the resulting lithological maps were assessed by comparing both techniques using confusion matrix, overall accuracy (OA) and Kappa coefficient (K). The results show that the GEOBIA approach had higher overall agreement (83.46% OA and 0.76 K) than RF (81.92% OA and 0.72 K) and k-NN (80.79% OA and 0.70 K) PBIA approaches. Overall, the results clearly indicate the potential of GEOBIA technique for lithological mapping applications to produce more realistic maps.

— Lithological mapping is a crucial factor in identifying and mapping the spatial distribution of minerals. It aids in accurately defining the most promising primary prospects for local exploration. The differentiation of rock units across a wider region is likely to be attributed to remotely sensed satellite data. Therefore, the research focuses on utilizing remote sensing methods to create a geological map for a specific area in Salem district, Tamil Nadu, by employing HYPERION and ASTER satellite images. Various techniques, such as Band Ratio (BR), Spectral Angle Mapper (SAM), Minimum Noise Fraction (MNF), Mixture Tuned Mapped Filtering (MTMF), Spectral Feature Fitting (SFF), and Support Vector Machines (SVMs), are utilized to classify lithological units, which are crucial for data analysis. The outcomes of these methods will be compared to field-mapped geological boundaries to assess accuracy. In the final phase, a highly precise geological map is produced by combining remote sensing data with on-site investigations. The application of these approaches holds significant potential for enhancing geological mapping and mineral exploration in hard-to-reach areas.

Multispectral satellite data allow experts to discriminate rock units based on their spectral signature characteristics. Here, Sentinel-2, ASTER and the Landsat-8 Operational Land Imager (OLI) were assessed for lithological mapping by using a random forest (RF) classifier for a study area located in Xitieshan, Northwest China. The classification accuracy of Sentinel-2 was 60.71%, which was 5.24% and 4.77% higher than the accuracies for ASTER and the Landsat-8 OLI, respectively. Three image enhancement techniques, namely, principal component analysis (PCA), independent component analysis (ICA) and minimum noise fraction (MNF), were used with grey-level cooccurrence matrices (GLCMs) to increase the quality of the input datasets. The ICA could discriminate between rock unit datasets better than the other approaches. In contrast, GLCM performed poorly when used independently. The overall classification accuracies were 60.71%, 62.63%, 64.34%, 65.21% and 58.87% for the 10 bands of Sentinel-2, PCA, MNF, ICA and GLCM, respectively. Then, five datasets were combined as a single group and applied in RF classification. Sentinel-2 obtained an overall accuracy of 73.96% and performed better than the other single-dataset approaches used in this study. Furthermore, the classification result of RF was achieved better performance than that of the support vector machine algorithm (SVM). During feature selection processing, ReliefF, the most successful pre-processing algorithm, was employed to preliminarily perform feature screening. Then, the optimal dataset was selected on the basis of the importance ranking of RF. A total of 20 more important predictors were selected from 114 original features using the ReliefF-RF model. These predictors were used in the lithological mapping, and an overall accuracy of 77.63% was reached.

Lithological and lineament mapping using remote sensing is a fundamental step in various geological studies, as it forms the basis for the interpretation and validation of the results obtained. There were two objectives for this study, applied in the Imini-Ounilla-Asfalou district, South High Atlas of Marrakech region: first, lithological mapping by satellite image processing techniques such as ASTER L1B (hight spectral and spatial resolution), namely Principal Component Analysis (PCA), Minimum Noise Fraction (MNF), as well as the application of three types of supervised classification, namely Spectral Angle Mapper (SAM), Maximum Likelihood (ML) and Minimum Distance (MD), on the visible/near-infrared (VNIR) and short-wave infrared (SWIR) spectral bands of our ASTER image; second, an analysis of the distribution of lineaments by automatic extraction using a Global Digital Elevation Model (GDEM) and the PC1 image derived from the PCA transformation applied to the satellite image. The best results are highlighted by the delineation of new facies in relation to the existing map; after confirmation in the field, all of these facies, which include Eocene, Triassic and Jurassic formations, are represented on the new map. The results of lineaments showed that each of them systematically shows a similarity in terms of concentration and orientation, with four preferential oriented systems: NE-SW, E-W, NNE-SSW and NW-SE. The lineaments mainly follow those of the major fault zones, with high concentrations in the northeast and southwest parts of the study area.

Different types of remote sensing data are commonly used as inputs for lithological classification schemes, yet determining the best data source for each specific application is still unresolved, but critical for the best interpretations. In addition, various classifiers (i.e., artificial neural network (ANN), maximum likelihood classification (MLC), and support vector machine (SVM)) have proven their variable efficiencies in lithological mapping, yet determining which technique is preeminent is still questionable. Consequently, this study aims to test the potency of Earth observing-1 Advanced Land Imager (ALI) data with the frequently utilized Sentinel 2 (S2), ASTER, and Landsat OLI (L8) data in lithological allocation using the widely accepted ANN, MLC, and SVM, for a case study in the Um Salatit area, in the Eastern Desert of Egypt. This area has a recent geological map that is used as a reference for selecting training and testing samples required for machine learning algorithms (MLAs). The results reveal (1) ALI superiority over the most commonly used S2, ASTER, and L8; (2) SVM is much better than MLC and ANN in executing lithologic allocation; (3) S2 is strongly recommended for separating higher numbers of classes compared to ASTER, L8, and ALI. Model overfitting may negatively impact S2 results in classifying small numbers of targets; (4) we can significantly enhance the classification accuracy, to transcend 90% by blending different sensor datasets. Our new approach can help significantly in further lithologic mapping in arid regions and thus be fruitful for mineral exploration programs.

Lithological Discrimination and Mapping using ASTER SWIR Data in the Udaipur area of Rajasthan, India

• Carbonatite complex in SGT offers high REE exploration potential. • EO-1 Hyperion data used for REE-fertile lithology mapping. • Applied SDM with PCA, ICA, MNF, BRC, and SVM methods. • ICA gave highest separability (JM > 1.9); SVM accuracy 85.56%. • Combines spectroscopy and ML for complex terrain mineral targeting. The Proterozoic alkaline carbonatite complex, lies along the Samalpatti shear zone, is linked to a post-collisional rift setting in the Southern Granulitic Terrain (SGT), provides a geologically intriguing and economically prospective terrain for rare earth element (REE) exploration. This study involves a multiproxy approach by integrating the hyperspectral remote sensing, machine learning, and field validation techniques to delineate the REE fertile lithology units using the EO-1 Hyperion imagery. The pre-processed dataset was subjected to noise reduction and dimensionality reduction using spectral dispersion matching (SDM) methods. SDM was performed in 3 steps; initially, noise reduction algorithms such as principal component analysis (PCA), independent component analysis (ICA), minimum noise fraction (MNF), and band ratio combinations (BRC) were applied to enhance data quality. This was followed by correlation-based feature selection using support vector machines (SVM), focusing on spectral behaviour. Subsequently, mineralogical characteristics were integrated and validated to emphasize their spectrochemical properties. Among the reduction algorithms, ICA achieved the highest spectral class separability, as confirmed by Jeffries–Matusita distance analysis, with values >1.9 for key lithological pairs. The correlation-based feature selection was performed with a radial basis function (RBF) kernel, yielding an overall accuracy of 85.56% and a Kappa coefficient of 0.80. The multiproxy approach using SDM highlights the efficacy of imaging spectroscopy combined with advanced classification techniques in complex lithological terrains and offers a scalable framework for mineral exploration targeting REE-fertile zones.

Mapping lithological units of an area using remote sensing data can be broadly grouped into pixel-based (PBIA), sub-pixel based (SPBIA) and object-based (GEOBIA) image analysis approaches. Since it is not only the datasets adequacy but also the correct classification selection that influences the lithological mapping. This research is intended to analyze and evaluate the efficiency of these three approaches for lithological mapping in semi-arid areas, by using Sentinel-2A data and many algorithms for image enhancement and spectral analysis, in particular two specialized Band Ratio (BR) and the Independent component analysis (ICA), for that reason the Paleozoic Massif of Skhour Rehamna, situated in the western Moroccan Meseta was chosen. In this study, the support vector machine (SVM) that is theoretically more efficient machine learning algorithm (MLA) in geological mapping is used in PBIA and GEOBIA approaches. The evaluation and comparison of the performance of these different methods showed that SVM-GEOBIA approach gives the highest overall classification accuracy (OA $\approx ~93$ %) and kappa coefficient (K) of 0, 89, while SPBIA classification showed OA of approximately 89% and kappa coefficient of 0, 84, whereas the lithological maps resulted from SVM-PBIA method exhibit salt and pepper noise, with a lower OA of 87% and kappa coefficient of 0, 80 comparing them with the other classification approaches. From the results of this comparative study, we can conclude that the SVM-GEOBIA classification approach is the most suitable technique for lithological mapping in semi-arid regions, where outcrops are often inaccessible, which complicates classic cartographic work.