An estimation of regional geologic structures from the geomorphology to characterize the Wadi systems, southeast Sinai, Egypt

2016 ◽  
Vol 4 (3) ◽  
pp. T323-T336
Author(s):  
Okechukwu Livinus Obiegbu ◽  
Andreas Laake ◽  
Peter Brabham

Complex regional geologic structural controls have generated a lot of interest in the engineering, oil, and gas industries within the past few years. Digital elevation models (DEMs), multispectral remote sensing images using ArcGIS software, in combination with data cube and geomorphologic characterization, provide important markers that aid in spatial information analysis for the study area. We have validated the characterization and classification of DEMs using spatial statistics by mineral spectroscopy of multispectral remote sensing data. Our characterization was initiated by a joint interpretation of DEMs and multispectral remote sensing data in association with stratigraphic and geologic information. We have combined Landsat ETM+ images from visible (VIS), near-infrared (NIR), and mid-infrared (MID IR) to create red-green-blue (RGB) images, superimposed with high-spectral-resolution 15 m panchromatic band 8. Principal component analysis (PCA) further enhanced the image results. To characterize the geomorphology and near surface, specific bands used included RGB Landsat 742 and 321 data sets, whereas false-color Landsat RGB images (742 and 432) provided spatial data in delineating areas of lineations and fault systems. The tectonic lineaments extracted from the escarpments of the DEM and magnetic data provided structures related to tectonic forces to better understand the major faults, lineations, and geomorphology. Results of this study showed a strikingly reliable interpretative result of these faults that controlled the low-lying areas. These faults and lineations are high-permeability zones that can be saturated by water during active rainfall and flash-flood periods thereby disrupting the equilibrium of various fault zones in the area and raising tectonic activities within the active fault system. Such saturation presents a major environmental hazard for the study area. Generally, the use of Landsat data combined with PCA indicates promising evidence of possible plays within the huge sedimentary deposits and raised concerns about safety and hazard issues.

2019 ◽  
Vol 225 ◽  
pp. 77-92 ◽  
Author(s):  
Christine I.B. Wallis ◽  
Jürgen Homeier ◽  
Jaime Peña ◽  
Roland Brandl ◽  
Nina Farwig ◽  
...  

2015 ◽  
Vol 113 ◽  
pp. 1-13 ◽  
Author(s):  
Gerald Blasch ◽  
Daniel Spengler ◽  
Christian Hohmann ◽  
Carsten Neumann ◽  
Sibylle Itzerott ◽  
...  

Author(s):  
M. Papadomanolaki ◽  
M. Vakalopoulou ◽  
S. Zagoruyko ◽  
K. Karantzalos

In this paper we evaluated deep-learning frameworks based on Convolutional Neural Networks for the accurate classification of multispectral remote sensing data. Certain state-of-the-art models have been tested on the publicly available SAT-4 and SAT-6 high resolution satellite multispectral datasets. In particular, the performed benchmark included the <i>AlexNet</i>, <i>AlexNet-small</i> and <i>VGG</i> models which had been trained and applied to both datasets exploiting all the available spectral information. Deep Belief Networks, Autoencoders and other semi-supervised frameworks have been, also, compared. The high level features that were calculated from the tested models managed to classify the different land cover classes with significantly high accuracy rates <i>i.e.</i>, above 99.9%. The experimental results demonstrate the great potentials of advanced deep-learning frameworks for the supervised classification of high resolution multispectral remote sensing data.


Sign in / Sign up

Export Citation Format

Share Document