Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO,BAT and COA algorithms

In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance.     

Modelling of piping collapses and gully headcut landforms:Evaluating topographic variables from different types of DEM

The geomorphic studies are extremely dependent on the quality and spatial resolution of digital elevation model(DEM)data.The unique terrain characteristics of a particular landscape are derived from DEM,which are responsible for initiation and development of ephemeral gullies.As the topographic features of an area significantly influences on the erosive power of the water flow,it is an important task the extraction of terrain features from DEM to properly research gully erosion.Alongside,topography is highly correlated with other geo-environmental factors i.e.geology,climate,soil types,vegetation density and floristic composition,runoff generation,which ultimately influences on gully occurrences.Therefore,terrain morphometric attributes derived from DEM data are used in spatial prediction of gully erosion susceptibility(GES)mapping.In this study,remote sensing-Geographic information system(GIS)tech-niques coupled with machine learning(ML)methods has been used for GES mapping in the parts of Semnan province,Iran.Current research focuses on the comparison of predicted GES result by using three types of DEM i.e.Advanced Land Observation satellite(ALOS),ALOS World 3D-30 m(AW3D30)and Advanced Space borne Thermal Emission and Reflection Radiometer(ASTER)in different resolutions.For further progress of our research work,here we have used thirteen suitable geo-environmental gully erosion conditioning factors(GECFs)based on the multi-collinearity analysis.ML methods of conditional inference forests(Cforest),Cubist model and Elastic net model have been chosen for modelling GES accordingly.Variable's importance of GECFs was measured through sensitivity analysis and result show that elevation is the most important factor for occurrences of gullies in the three aforementioned ML methods(Cforest=21.4,Cubist=19.65 and Elastic net=17.08),followed by lithology and slope.Validation of the model's result was performed through area under curve(AUC)and other statistical indices.The validation result of AUC has shown that Cforest is the most appropriate model for predicting the GES assessment in three different DEMs(AUC value of Cforest in ALOS DEM is 0.994,AW3D30 DEM is 0.989 and ASTER DEM is 0.982)used in this study,followed by elastic net and cubist model.The output result of GES maps will be used by decision-makers for sustainable development of degraded land in this study area.     

Petrogenesis of Middle-Eocene granitoids and their Mafic microgranular enclaves in central Urmia-Dokhtar Magmatic Arc (Iran): Evidence for interaction between felsic and mafic magmas

Whole rock major and trace element geochemistry together with zircon U-Pb ages and Sr-Nd isotope compositions for the Middle Eocene intrusive rocks in the Haji Abad region are presented. The granitoid hosts, including granodiorite and diorite, yielded zircon U-Pb ages with a weighted mean value of 40.0 ± 0.7 Ma for the granodiorite phase. Mafic microgranular enclaves(MMEs) are common in these plutons, and have relatively low SiO_2 contents(53.04-57.08 wt.%) and high Mg#(42.6-60.1), probably reflecting a mantle-derived origin. The host rocks are metaluminous(A/CNK = 0.69-1.03), arc-related calc-alkaline, and I-type in composition, possessing higher SiO_2 contents(59.7-66.77 wt.%) and lower Mg#(38.6-52.2); they are considered a product of partial melting of the mafic lower crust. Chondritenormalized REE patterns of the MMEs and granitoid hosts are characterized by LREE enrichment and show slight negative Eu anomalies(Eu/Eu* = 0.60-0.93). The host granodiorite samples yield(⁸⁷Sr/⁸⁶Sr);ratios ranging from 0.70498 to 0.70591,positive eNd(t) values varying from +0.21 to +2.3, and TDM2 ranging from 760 to 909 Ma, which is consistent with that of associated mafic microgranular enclaves(⁸⁷Sr/⁸⁶Sr)i = 0.705111-0.705113, ε_Nd(t)= +2.14 to +2.16, T_DM2 = 697-785 Ma). Petrographic and geochemical characterization together with bulk rock Nd-Sr isotopic data suggest that host rocks and associated enclaves originated by interaction between basaltic lower crust-derived felsic and mantlederived mafic magmas in an active continental margin arc environment.     

Phenolic endocrine disrupting chemicals (EDCs) in Anzali Wetland, Iran: elevated concentrations of 4-nonylphenol, octhylphenol and bisphenol A

We have studied the distribution and value of phenolic endocrine disrupting chemicals (EDCs) in surface sediment samples taken from Anzali Wetland, Iran. These samples were collected from 22 stations during the time span of June-May 2010. In each of the sampling stations, we detected 4-nonylphenol (4-NP), octylphenol (OP), and bisphenol A (BPA) with maximal concentrations of 29, 4.3, and 7 μg g(-1) dry weight (dw), respectively. High levels of alkylphenols (APs) and BPA were also found near urban areas. Furthermore there were no significant differences between those stations in terms of the detected levels. One of the important factors in controlling the fate of these compounds in the aquatic environment appeared to be Total Organic Carbon (TOC). Hierarchical cluster analysis showed differences in the biomarker characteristics of EDCs and TOC between the stations. Our findings indicate that EDCs are ubiquitous in sediments from northeast Wetlands of Iran, contaminating the aquatic habitats in this area.     

Model updating and seismic loss assessment for a portfolio of bridges

The majority of bridge infrastructures in Italy were built in the 1960s and ‘70s without any specific seismic provision being made. As a consequence, it is expected that these bridges would be highly vulnerable if subjected to a significant seismic event. Given this background, it is natural that the rapid and accurate assessment of economic losses incurred to the bridge infrastructure as a result of such an event could play a crucial role in emergency management in the immediate aftermath of an earthquake. Focusing on the infrastructure system of highway bridges in the Campania region in Italy, this paper demonstrates how both state-of-the-art methodologies in portfolio loss assessment and the available data can be used to assess the probability distribution of the repair costs incurred due to the 1980 Irpinia earthquake. Formulating a probabilistic loss assessment for a portfolio of bridges as a standard Monte Carlo simulation problem helps to resolve the spatial risk integral efficiently. One of the specific features of this case study is the use of statistical methods for updating models of: (a) ground motion predictions, (b) vulnerability/fragility and (c) exposure/costs, based on the available data. It has been observed that alternative hypotheses concerning the ground motion correlation structure can significantly affect the distribution of direct economic losses. Furthermore, updating the ground motion prediction based on available recordings may significantly reduce the dispersion in the estimate of the direct economic losses.     

Vulnerability evaluation of a coastal aquifer via GALDIT model and comparison with DRASTIC index using quality parameters

In recent years, environmental assessments of groundwater resources have resulted in the development of models that help identify the vulnerable zones. An aquifer is investigated using both GALDIT and DRASTIC indices. The GALDIT model is developed to determine the vulnerability of coastal aquifers in terms of saltwater intrusion whereas the DRASTIC model is generally applicable to all aquifers. Having compared the results of both the GALDIT and DRASTIC models with quality parameters, the salinity model proved to be more appropriate in identifying the vulnerability of coastal aquifers. The results show a Pearson correlation coefficient between TDS and the GALDIT vulnerability map of 0.58 while the corresponding value for the DRASTIC index is 0.48.

EDITOR D. Koutsoyiannis

ASSOCIATE EDITOR A. Fiori     

Analytical fragility assessment using unscaled ground motion records

It is desirable that nonlinear dynamic analyses for structural fragility assessment are performed using unscaled ground motions. The widespread use of a simple dynamic analysis procedure known as Cloud Analysis, which uses unscaled records and linear regression, has been impeded by its alleged inaccuracies. This paper investigates fragility assessment based on Cloud Analysis by adopting, as the performance variable, a scalar demand to capacity ratio that is equal to unity at the onset of limit state. It is shown that the Cloud Analysis, performed based on a careful choice of records, leads to reasonable and efficient fragility estimates. There are 2 main rules to keep in mind for record selection: to make sure that a good portion of the records leads to a demand to capacity ratio greater than unity and that the dispersion in records' seismic intensity is considerable. An inevitable consequence of implementing these rules is that one often needs to deal with the so‐called collapse cases. To formally consider the collapse cases, a 5‐parameter fragility model is proposed that mixes the simple regression in the logarithmic scale with logistic regression. The joint distribution of fragility parameters can be obtained by adopting a Markov Chain Monte Carlo simulation scheme leading directly to the fragility and its confidence intervals. The resulting fragility curves compare reasonably with those obtained from the Incremental Dynamic Analysis and Multiple Stripe Analysis with (variable) conditional spectrum–compatible suites of records at different intensity levels for 3 older reinforced concrete frames with shear‐, shear‐flexure‐, and flexure‐dominant behavior.     

Earthquake hazard assessment in the Zagros Orogenic Belt of Iran using a fuzzy rule-based model

Producing accurate seismic hazard map and predicting hazardous areas is necessary for risk mitigation strategies. In this paper, a fuzzy logic inference system is utilized to estimate the earthquake potential and seismic zoning of Zagros Orogenic Belt. In addition to the interpretability, fuzzy predictors can capture both nonlinearity and chaotic behavior of data, where the number of data is limited. In this paper, earthquake pattern in the Zagros has been assessed for the intervals of 10 and 50 years using fuzzy rule-based model. The Molchan statistical procedure has been used to show that our forecasting model is reliable. The earthquake hazard maps for this area reveal some remarkable features that cannot be observed on the conventional maps. Regarding our achievements, some areas in the southern (Bandar Abbas), southwestern (Bandar Kangan) and western (Kermanshah) parts of Iran display high earthquake severity even though they are geographically far apart.