Search

The primary objective of these studies was to quantitatively assess the ground deformation velocities and rates and their natural and man-made controlling factors as the potential risks along the seismically active 70 km section of buried Baku-Tbilisi-Ceyhan Oil, South Caucasus Gas, Western Route Oil and South Caucasus Pipeline Expansion Gas pipelines in Azerbaijan using Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) technique. PS-InSAR analysis showed that the continuous subsidence was prevailing in the kilometer range of 13-70 of pipelines crossing two active seismic faults. The ground uplift deformations were observed in the pipeline kilometer range of 0-13. The minimum and maximum vertical ground movement velocities were observed to be −21.3 mm/y and 14.1 mm/y along 70 km section of pipelines with 250 m buffer zone. Both of these sites were observed at the range of seismic faults. The spatial distribution of sites with ground deformation velocity less than −15 mm/y and more than 15 mm/y was diverse and random all along 70 km of pipelines without any cumulative spatial patterns. Based on the lower mean, variation and standard deviation of pixel values, the seismic fault in the kilometer range of 21-31 revealed its higher vulnerability to subsidence processes rather than the Seismic Fault in the kilometer range of 46-54. The ground deformation velocities within the range of Seismic Fault KP21-31 revealed the minimum and maximum values of −19.74 mm/y and 14.1 mm/y, respectively whereas at the Seismic Fault KP46-54, the minimum and maximum values were −17.07 mm/y and 9.29 mm/y, respectively. Encouraging level of agreement with the regression coefficients of 0.92 and 0.96 for known subsiding sites at KP28 + 500 and KP52 + 750 and 0.97 and 0.96 for known uplifting sites at KP04 + 900 and KP35 + 050 respectively was observed between the high-precision GPS and PS-InSAR measurements. The diverse spatial distribution and variation of ground movement processes along pipelines demonstrated that general geological and geotechnical understanding of the study area is not sufficient to find and mitigate all the critical sites of subsidence and uplifts for the pipeline operators. The prediction of the potential subsidence or uplift locations based on the field visual verifications holds a lot of uncertainties without broad and detailed scale airborne and satellite space observation technologies. The justification of the budget for the geotechnical maintenance activities along long-range oil and gas pipelines requires sophisticated prioritization and planning of the remediation sites and clear quantitative and qualitative risk assessment proving the activeness of these sites and effectiveness of the remediation measures. This means that the PS-InSAR – based approach outlined in this paper is a significant improvement over current ground-based monitoring practices or can significantly contribute them in the initial phase of risk assessment and prioritization. [ABSTRACT FROM AUTHOR]

The ground deformation phenomena are the result of the application of natural stress (tectonic) or anthropogenic stress (overexploitation of groundwater, embankment) on the soil. The land deformation may cause several impacts on the environment and human life. A good understanding of the deformation behaviour of the soil is essential to mitigate risks on the infrastructure and environment. In this study, a radar interferometry is carried out to analyse the mobility of an urban and suburban area of Greater Tunis region. The interferometric synthetic aperture radar (SAR) technique has been proven to be an effective methodology for detecting and monitoring soil displacement with millimetre accuracy and also, improving our understanding of the current deformations in the study area. Indeed, the application of differential SAR interferometry made it possible to determine the origin of the surface deformations related to natural or anthropic phenomena. In this paper, the interferometric method of small baseline subset (SBAS) developed by Berardino et al. 2002has been chosen, in order to monitor the spatial and temporal pattern of the deformation phenomena in Greater Tunis region. The analysis of Envisat ASAR (2003–2007, descending satellite orbit) and Sentinel 1B (2016–2018, ascending satellite orbit) SAR data allowed us to create deformation velocity maps associated with line of sight displacement time series. The results obtained by this method showed the existence of subsidence phenomenon in the urban areas (Tunis City) as well as in the rural areas (Mornag plain). In the first site (Tunis City), the subsidence rate reaches up to 13.98 mm/year and 19 mm/year during 2003–2007 and 2016–2018, respectively. The ground deformation that is detected around the region of Tunis Lake and Sebkhet Essijoumi, is probably due to the nature of the highly compressible and thickness alluvial deposits and whose substratum depth sometimes reaches more than 60 m. In the second studied site, ground subsidence was identified in the whole plain of Mornag. Indeed, the comparison between piezometric data and time series deformations shows that the trend of soil subsidence is coherent with the dynamic change in groundwater levels. Furthermore, the analysis of velocity deformation, geological data and hydrogeological information allows us to associate all the detected settlement patterns to groundwater overexploitation and compressible alluvium all over the plain. This overexploitation of groundwater in Mornag plain is mainly caused by the expansion of agricultural and industrial activities and the decrease in annual rainfall in recent years (from 2003 to 2018). [ABSTRACT FROM AUTHOR]

Machine learning models are regarded as efficient and popular models for natural disaster susceptibility prediction. However, few studies have focussed on the applications of the latest popular machine learning models in collapse susceptibility assessment (CSA). This paper proposes a 3S (RS, GPS and GIS) technology-based support vector machine (SVM) to map collapse susceptibility in the Nantian area of China. The 3S technology-based back-propagation neural network (BPNN) and radial basis function neural network (RBFNN) models are also proposed for comparison. First, 44 recorded collapses are identified through field investigation, and fourteen collapse-related causal factors are acquired using 3S technology. Second, among these recorded collapses and randomly selected 'non-collapses', 70% of the collapse and non-collapse grid cells are used to train the three models, while the remaining 30% are used to test the models. Third, the collapse susceptibility maps of the Nantian area are produced using the three models. Finally, the prediction accuracies of these models are evaluated. The results indicate that the SVM model has the highest prediction accuracy, while the RBFNN model has the lowest prediction accuracy for CSA. In addition, the distribution characteristics of collapse susceptibility in the Nantian area are produced well by all three models. [ABSTRACT FROM AUTHOR]

In this paper, an ensemble method, which demonstrated efficiency in GIS based flood modeling, was used to create flood probability indices for the Damansara River catchment in Malaysia. To estimate flood probability, the frequency ratio (FR) approach was combined with support vector machine (SVM) using a radial basis function kernel. Thirteen flood conditioning parameters, namely, altitude, aspect, slope, curvature, stream power index, topographic wetness index, sediment transport index, topographic roughness index, distance from river, geology, soil, surface runoff, and land use/cover (LULC), were selected. Each class of conditioning factor was weighted using the FR approach and entered as input for SVM modeling to optimize all the parameters. The flood hazard map was produced by combining the flood probability map with flood-triggering factors such as; averaged daily rainfall and flood inundation depth. Subsequently, the hydraulic 2D high-resolution sub-grid model (HRS) was applied to estimate the flood inundation depth. Furthermore, vulnerability weights were assigned to each element at risk based on their importance. Finally flood risk map was generated. The results of this research demonstrated that the proposed approach would be effective for flood risk management in the study area along the expressway and could be easily replicated in other areas. [ABSTRACT FROM AUTHOR]

The main purpose of this paper is to explore some potential applications of sophisticated machine learning techniques such as the kernel logistic regression, Naïve-Bayes tree and alternating decision tree models for landslide susceptibility analysis at Taibai county (China). Initially, a landslide inventory map containing the information of 212 historical landslide locations was prepared. Seventy percentage (148) of landslides were randomly selected for training models and the remaining were used for validation. Additionally, 12 landslide conditioning factors were considered and the thematic layers were prepared in GIS. Subsequently, these three models were applied to build landslide susceptibility maps. The performances of the models were compared using the receive operating characteristic curves, kappa index, and statistical evaluation measures. The results show that the KLR model has the highest AUC values of 0.910 and 0.936 for training and validation datasets, respectively. The KLR model also has the highest degree of goodness-of-fits (84.5%) for the training dataset. The NBTree model has the highest goodness-of-fits (91.4%) for the validation dataset. However, the KLR model has the preferable balance performance for both the training and validation process. The results of this study demonstrate the benefit of selecting the optimal machine learning techniques in landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

Cross River, which originates from Cameroon, flows through several communities in Nigeria. The population upsurge and settlements near the river channel, however, portends the possibility of natural hazards such as floods. Floods within the upper Cross River basin (UCRB) have resulted in the loss of lives and property. The importance of flood studies, therefore, cannot be overemphasized. This study evaluated the influence of sub-basins on the flooding of the main channel in the UCRB using morphometric analysis. The UCRB was delineated into sub-basins using Shuttle Radar Topographic Mission Digital Elevation Model. The drainage network and morphometric parameters were extracted using QSWAT installed as a plugin in QGIS. Based on the compound factors computed from morphometric parameters that directly impact runoff, the UCRB was categorized into three flood vulnerability zones namely: high vulnerability (10.93–13.10), moderate vulnerability (8.75–10.92), and low vulnerability (6.57–8.74). The analysis revealed that sub-basins 18, 10, 8, 17, 1, 6, 15, and 13 have greater potentials to attain peak discharge in a short period, therefore, the instantaneous high runoff contribution of their tributaries to Cross River. The results of this study provide useful information for the effective mitigation and management of the flood vulnerabilities of the UCRB. [ABSTRACT FROM AUTHOR]

Along with the development of computer science and communication techniques, tunnel monitoring has been digital and intellectualized gradually. In recent years, traditional tunnel monitoring systems have been becoming powerless to deal with huge amounts of data as the number of tunnels and monitoring sensors surge. In this study, an innovative and comprehensive intelligent tunnel monitoring system was designed based on micro-service architecture. Various function modules were distributed to multiple service instances to get the computing pressure decentralized. The system offered powerful massive data processing support, flexibility, and extensibility. For a certain tunnel, the system could acquire the monitoring data in real-time using wireless sensors deployed on its surface. When data reached the early warning threshold, the system would immediately transmit the warning message to users. Besides, an app was developed to offer support for wireless communication between the monitoring apparatus and watchers. The application of the Anping case, one of the monitoring targets, proved the high efficiency of data transmitting and effective emergency response of the developed system. The results indicated that the microservice architecture could facilitate algorithm development, decentralize calculation pressure, and promote the service capacity by decoupling components and distributing loads. [ABSTRACT FROM AUTHOR]

Considering the critical importance of the quality of input data for landslide susceptibility, we investigate the performance improvements that can be achieved by different globally available digital elevation models (DEMs) using different state-of-the-art statistical and machine-learning models. For this purpose we compare the predictive performances achieved using terrain attributes derived from TanDEM-X DEM (12 m resolution and resampled to 30 m), ASTER DEM (30 m), SRTM DEM (30 m), and a DEM (25 m) interpolated from contour lines (1:25.000 map scale), exploiting the capabilities of logistic regression, generalized additive models, random forests and support vector machines. The study was conducted in the Buzău Sector of the Curvature Subcarpathians of Romania, a region highly susceptible to landslides. While the performances varied little among modelling techniques, the use of different DEMs strongly influenced the cross-validation accuracy of landslide susceptibility models. TanDEM-X (12 m) based susceptibility models outperformed models based on the other DEMs (median Area Under the Receiver Operating Characteristics Curve (AUROC) values 0.708–0.730). Models using ASTER-derived terrain attributes showed the poorest predictive capabilities (median AUROC 0.568–0.595). We conclude that the quality of DEMs is of critical importance in landslide susceptibility modelling, and greater efforts should be made to obtain suitable DEM products. [ABSTRACT FROM AUTHOR]

Underground mining is known to cause the deformation and failure of the surrounding rocks and frequently associated with water-inrush through the mine floor. In this study, in-situ strain tests along with borehole imaging measurements were utilized to investigate the deformation and failure characteristics of the rock mass of the mine floor caused by mining. We directly measured the strain and borehole images of the rocks in the mine floor at different depths in five coal mines in the Yanzhou mining area, China. We observed from plotting the increments of strain that mining caused and then led to the deformation and failure of the rock mass of the mine floor. The zone in the floor that was affected by stress from mining was over 170 m in length and decreases with depth. We also found that the depth of failure in floor of the five different coal mines varied between 8.4 to 20 m. [ABSTRACT FROM AUTHOR]

Besides the dangers of an actively burning wildfire, a plethora of other hazardous consequences can occur afterwards. Debris flows are among the most hazardous of these, being known to cause fatalities and extensive damage to infrastructure. Although debris flows are not exclusive to fire affected areas, a wildfire can increase a location's susceptibility by stripping its protective covers like vegetation and introducing destabilizing factors such as ash filling soil pores to increase runoff potential. Due to the associated dangers, researchers are developing statistical models to isolate susceptible locations. Existing models predominantly employ the logistic regression algorithm; however, previous studies have shown that the relationship between the predictors and response is likely better predicted using nonlinear modeling. We therefore propose the use of nonlinear C5.0 decision tree algorithm, a simple yet robust algorithm that uses inductive inference for categorical data modelling. It employs a tree-like decision making system that makes conditional statements to split data into homogeneous classes. Our results showed the C5.0 approach to produce stable and higher validation metrics in comparison to the logistic regression. A sensitivity of 81% and specificity of 78% depicts improved predictive capability and gives credence to the hypothesis that data relationships are likely nonlinear. [ABSTRACT FROM AUTHOR]