BIG EARTH DATA PROCESSING USING MACHINE LEARNING FOR INTEGRATED MAPPING OF THE DEAD SEA FAULT, JORDAN

In this research, an integrated framework on the big Earth data analysis has been developed in context of geomorphology Jordan. The research explores correlation between several thematic datasets, including machine learning and multidisciplinary geospatial data. GIS mapping is widely used geological as most adequate technical tool for visualization analysis. applications encourage prospective modeling by visualizing aimed at prognosis mineral resources. However, automatization using processing provides speed accurate multisource massive datasets. This enabled application scripting programming cartographic techniques. study presents combined methods modeling. objective to analyze a factors affecting geomorphological shape Jordan with respects Dead Sea Fault evolution. methodology includes following three independent tools: 1) Generic Mapping Tools (GMT); 2) Selected libraries R language; 3) QGIS. Specifically, GMT program was topographic, seismic geophysical mapping, while QGIS geologic language geomorphometric Accordingly, workflow logically structured through these tools, representing different approaches processing. Data materials include datasets various resolution, spatial extent, origin formats. results presented layouts qualitative quantitative maps statistical summaries (histograms). novelty approach explained need close gap traditional which wider where crucial are precision handling, well effective achieved graphics. paper analyzes underlying processes formation landforms 3D selected fragment zone. extended description methodology, explanations code snippets from modules examples use ‘raster’ ‘tmap’. revealed strong settings affect patterns. Integrated based processed scripting. A thorough regional correlations geomorphological, tectonic contributed both development engineering introducing techniques studies special region 12 new model.