Textural and knowledge-based lithological classification of remote sensing data in Southwestern Prieska sub-basin, Transvaal Supergroup, South Africa

Abstract

TM data and other medium spatial resolution satellite data are used in geological and lithologicalmineralogical classification on regular basis, although their usefulness is limited because of relatively coarse spectral resolution. In this contribution, we provide an example for the application of TM data for classification of rocks and minerals within the Neoarchean sedimentary and volcanic basin of Griqualand West, South Africa. An improved methodology is introduced that results in significantly higher classification accuracy. The TM multispectral image and Principal Component analysis (PCA) image of the test area were individually combined with textural features and then classified individually using a Maximum-Likelihood supervised classification (MLC). Subsequently, the two classified images were integrated, compared and re-classified in a knowledge-based system (KBS) using the generalized supplementary geological map on 1:250000 scale. With this method, the accuracy was improved from 54.3% to 83.2%, when compared to the former supervised classification.The method integrates the spectral and textural features, greatly contributing to the precision of the lithological classification, mapping and prospecting, in extensive areas where field work is limited by time and cost constrains.1

Co-Orbital Sentinel 1 and 2 for LULC Mapping with Emphasis on Wetlands in a Mediterranean Setting Based on Machine Learning

“…Previous studies have indicated the improvement of accuracy in classifying land cover when knowledge rules are used [31][32][33]. In our study, post classification results achieved very high accuracy and indicated the efficiency of this method in producing a high-accuracy LULC map (Figure 9).…”

“…Finally, the differences in the spatial resolution between the combined datasets and the image processing implemented to unify this spatial resolution could be another source of misclassifications reported herein. Previous studies have indicated the improvement of accuracy in classifying land cover when knowledge rules are used [31][32][33]. In our study, post classification results achieved very high accuracy and indicated the efficiency of this method in producing a high-accuracy LULC map ( Figure 9).…”

Application of remotely sensed data in detecting zinc-lead bearing mineralized zones in Westkunlun Huoshaoyun area

“…In addition, mineralized limestone spectra show high reflectance in band 6 (OLI) and 4 (ASTER), and a weak absorption at 2200 nm, which coincides with bands 7 of OLI and 6 of ASTER, possibly due to the weak gypsum and clay alteration [20,26]. The spectral signature extracted from the ASTER data, which is also characterized by a deep absorption at 2330 nm (band 8), can be related to the presence of carbonate minerals [12,24] After examining different combinations of ratios, two Color Components (CCs) RGB (for each sensor) were chosen to better discriminate the existing lithological units and mineralized zones [9,27,28,29]. In CC1 (6/5, 7/6, 4/7) of OLI, the mudstone-sandstone is distinguished by a yellow-orange color, and it appears purple in CC3 [(6 + 8)/4; 8/4; 5/3] of ASTER, and it appears light blue-green in CC2 (5/4, 6/5, 7/2) of OLI.…”

“…The sandstone-to-mudstone, which is rich of mica and clay minerals, is mapped by the ratios (6/5 of OLI) and (5/3 of ASTER), since its spectra show high reflectance in band 6 of OLI and band 5 of ASTER, against an absorption at 860 nm (band 5 of OLI) and 800 nm (band 3 of ASTER), corresponding to the near infrared region. This type of absorption is also due to the presence of iron oxides [22][23][24]. In comparison with other spectra, conglomerate shows a high reflectance in band 4 of OLI and band 3 of ASTER, and intense absorption of Al-OH type at 2200 nm (band 7 of OLI and band 6 of ASTER) due to mica or clay minerals [9,23,25], hence the ratios of (4/7 of OLI) and (3/6 of ASTER) are used to map this rock unit.…”

Lithological Classification Using Sentinel-2A Data in the Shibanjing Ophiolite Complex in Inner Mongolia, China

“…Although it is not new to use remote sensing technique for lithological classification in geological investigation [2,22,23], many studies are limited, due to the coarse spatial/spectral resolutions of multispectral data, causing difficulties in accurately classifying rock units [22]. As a solution, multiple ancillary data with texture information, such as airborne geophysical data [24], DEM [25], and geomorphic feature [2], can be integrated with multispectral imagery for improved lithological classifications [22].…”