Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha Basin,Asir Region,Saudi Arabia

The current study aimed at evaluating the capabilities of seven advanced machine learning techniques(MLTs),including,Support Vector Machine(SVM),Random Forest(RF),Multivariate Adaptive Regression Spline(MARS),Artificial Neural Network(ANN),Quadratic Discriminant Analysis(QDA),Linear Discriminant Analysis(LDA),and Naive Bayes(NB),for landslide susceptibility modeling and comparison of their performances.Coupling machine learning algorithms with spatial data types for landslide susceptibility mapping is a vitally important issue.This study was carried out using GIS and R open source software at Abha Basin,Asir Region,Saudi Arabia.First,a total of 243 landslide locations were identified at Abha Basin to prepare the landslide inventory map using different data sources.All the landslide areas were randomly separated into two groups with a ratio of 70%for training and 30%for validating purposes.Twelve landslide-variables were generated for landslide susceptibility modeling,which include altitude,lithology,distance to faults,normalized difference vegetation index(NDVI),landuse/landcover(LULC),distance to roads,slope angle,distance to streams,profile curvature,plan curvature,slope length(LS),and slope-aspect.The area under curve(AUC-ROC)approach has been applied to evaluate,validate,and compare the MLTs performance.The results indicated that AUC values for seven MLTs range from 89.0%for QDA to 95.1%for RF.Our findings showed that the RF(AUC=95.1%)and LDA(AUC=941.7%)have produced the best performances in comparison to other MLTs.The outcome of this study and the landslide susceptibility maps would be useful for environmental protection.

Assessment of Main Parameters of Extreme Earthquakes in Red Sea, West Coast of Saudi Arabia

The negative effects of natural disasters on human life exist from the foot and did not occur at a specific time but found since the creation of mankind. Humans coexist with extreme events all the time, only when the intensity of the event becomes greater than a certain level there is a resulting disaster. Small earthquakes occur all of the time with no adverse effects. Only large earthquakes cause disasters. Statistical analysis reveals that larger events occur less frequently than small events. Through the large number of seismic events, we find that at the end of the year may have a series of seismic events with different values depending on the strength of activity whether it is high or low on Richter scale and the assessment is only for the greatest value in a year even if recurring this value and the volume of dangerous increases and the frequency of their occurrence according to an ongoing activity, major disasters result from a small number of events and sustained results in a large and devastating event, and can be represented by these results and amounts On a log-scale which points are almost on a straight line and a clear indication of the evaluation event. Through previous data analysis we can understand the following events behavior for coordination and guidance on the development of evacuation plans on the expected future and use a Weibull equation to estimate the frequency of the event and the return again as a percentage for each event and the probability of the occurrence of a particular earthquake to some degree on the Richter scale in the sea during any period. Past records of earthquakes at the West Coast of the Kingdom of Saudi Arabia (Red Sea) for years 1913-2016 are used to predict future conditions concerning the annual frequency, the return period, the percentage probability for each event, and the probability of a certain-magnitude earthquake occurring in the region during any period.

Detecting and Distinguishing Ophiolite Rocks via Multispectral Remote Sensing in Bi’r Umq, Southeast Al Madinah Al Munawarrah, Saudi Arabia

The objective of this work is to show the contribution of multispectral remote sensing data to detect and distinguish the ophiolite rocks of Bi’r Umq and their geologic setting, southeast of Al Madinah Al Munawarrah in Saudi Arabia. This work includes detailed fieldwork lab studies, as well as processing operations, were performed on The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER 2006, 2007) and Satellite Pour L’Observation de la Terre SPOT 5 (2005) images of the study region. Among the processing techniques applied are band ratio, histogram stretching, the combination of spectral bands, image fusion. The techniques used permitted a clearly show that the ultramafic rocks are distinct from other rock units and contain important economic minerals. This research also illustrates the tectonic parameters and that the remains of the oceanic crust are exposed and juxtaposed to the rocks of the continental crust of the Arabian Shield. The results of the spatial data processing revealed a good positive concordance with the results of the field investigations.

Earthquake Disaster Management Approach: The Case of Al-Ais, Medina Area in Saudi Arabia

The research tackles earthquakes as one of the most dangerous natural disasters. It defines disasters in general, which in turn include earthquakes, how to manage them, stages of their evolution, and their classification among other kinds of disasters such as hurricanes, floods, drought, desertification, etc. Afterwards, it tackles the impacts of disasters on man, buildings and infrastructure. It defines also the codes and laws existing in the Kingdom of Saudi Arabia to confront and treat the impacts of earthquakes in their different stages (before, during and after) and the authorities involved in managing them. Then, it moves to study the case of Al-Ais Earthquake, and identifies the points of deficiency in dealing with such a disaster. Moreover, the research tackles some global experiences in how to handle the situation, reaching to the presentation of a conceptual approach to confront disasters of earthquakes in their various stages.

Development of a simple method for determining the influence radius of a pumping well in steady-state condition

Influence radius of a pumping well is a crucial parameter for hydrogeologists and engineers. Knowing the radius of influence for a designed drawdown enables one to calculate the pumping rate required to layout a project foundation that may need lowering of groundwater level to a certain depth due to dewatering operation. In addition, this is important for hydrogeologists to determine ground water contamination flow paths and contributing recharge area for domestic water supply and aquifer management purposes. Empirical formulas that usually neglect vital parameters to determine the influence radius accurately have been traditionally utilized due to lack of adequate methods. In this study, a physically based method, which incorporates aquifer hydraulic gradient for determining the influence radius of a pumping well in steady-state flow condition, was developed. It utilizes Darcy and Dupuit laws to calculate the influence radius, where Darcy’s law and Dupuit equation, in steady-state condition, represent the inflow and the outflow of the pumping well, respectively. In an untraditional manner, this method can be also used to determine aquifer hydraulic conductivity as an alternative to other pumping test methods with high degree of accuracy. The developed method is easy to use;where a simple mathematical calculator may be used to calculate the influence radius and the pumping rate or hydraulic conductivity. By comparing the results from this method with the MODFLOW numerical model outputs with different simulated scenarios, it is realized that this method is much superior and more advantageous than other commonly used empirical methods.

Petrogenesis and Tectonic Implications of the Jabal Hadb Ad Dayheen Granitic Complex, Central Arabian Shield

The Jabal Hadb Ad Dayheen granitic complex in central Saudi Arabia is an alkaline granitic ring complex associated with a collapsed caldera. It mainly consists of monzogranite in the center, biotite-hornblende porphyritic granite, and biotite-aegirine-riebeckite granite, intruded by some felsic and mafic dikes. The petrological and geochemical characteristics show that the granitic suites consist of metalminous-peralkaline A-type granites. The secondary ion mass spectrometry(SIMS) zircon U-Pb analysis yielded ^(206)Pb/^(238)U ages of 613.3 ± 8.1 – 603.8 ± 3.8, 602.4 ± 3.8, 596 ± 5.6 Ma for biotitehornblende porphyritic granite, microgranite, and biotite-aegirine-riebeckite granite, respectively. The trace element characteristics and positive ε_(Hf)(t) values(3.2–12.2) indicate that the granitic rocks of the Dayheen Ring Complex are mainly derived from the juvenile crust with the involvement of mantlederived materials. Combined with the regional tectonic evolution, the formation of the Dayheen Ring Complex mainly covered four periods:(1) subduction initiation and formation of arc terranes(870–620 Ma)—volcanic craters formed during this period provided the channel for alkaline complex intrusion;(2) collision between East and West Gondwana continents and formation of the north East African Orogen(640–613 Ma)—monzogranite stock at the center of the ring complex emplaced during this period;(3) post-collision extension and collapse(613–602 Ma)—red metaluminous biotite-hornblende porphyritic granite and microgranite sheets in the rim of the Dayheen Ring Complex emplaced during this period;(4) within-plate extension(602 – 545 Ma) —white peralkaline biotite-aegirine-riebeckite granite and plenty of felsic and mafic dikes in the rim mainly formed during this period. The granitic rocks of the Dayheen Ring Complex mainly formed during the transitional stage of post-collison to within-plate extension after the collision between East and West Gondwana continents, and part of them formed during the early stage of the within-plate extension. U, Th, Zr, Nb, and rare earth element mineralization mainly formed during the early stage of the last period, having a close relationship with the intrusion of white peralkaline biotite-aegirine-riebeckite granite.

Approaches for Delineating Landslide Hazard Areas Using Different Training Sites in an Advanced Artificial Neural Network Model

The current paper presents landslide hazard analysis around the Cameron area, Malaysia, using advanced artificial neural networks with the help of Geographic Information System (GIS) and remote sensing techniques. Landslide locations were determined in the study area by interpretation of aerial photographs and from field investigations. Topographical and geological data as well as satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. Ten factors were selected for landslide hazard including: 1) factors related to topography as slope, aspect, and curvature; 2) factors related to geology as lithology and distance from lineament; 3) factors related to drainage as distance from drainage; and 4) factors extracted from TM satellite images as land cover and the vegetation index value. An advanced artificial neural network model has been used to analyze these factors in order to establish the landslide hazard map. The back-propagation training method has been used for the selection of the five different random training sites in order to calculate the factor's weight and then the landslide hazard indices were computed for each of the five hazard maps. Finally, the landslide hazard maps (five cases) were prepared using GIS tools. Results of the landslides hazard maps have been verified using landslide test locations that were not used during the training phase of the neural network. Our findings of verification results show an accuracy of 69%, 75%, 70%, 83% and 86% for training sites 1, 2, 3, 4 and 5 respectively. GIS data was used to efficiently analyze the large volume of data, and the artificial neural network proved to be an effective tool for landslide hazard analysis. The verification results showed sufficient agreement between the presumptive hazard map and the existing data on landslide areas.