Flash flood susceptibility mapping using a novel deep learning model based on deep belief network,back propagation and genetic algorithm

Flash floods are responsible for loss of life and considerable property damage in many countries.Flood susceptibility maps contribute to flood risk reduction in areas that are prone to this hazard if appropriately used by landuse planners and emergency managers.The main objective of this study is to prepare an accurate flood susceptibility map for the Haraz watershed in Iran using a novel modeling approach(DBPGA) based on Deep Belief Network(DBN) with Back Propagation(BP) algorithm optimized by the Genetic Algorithm(GA).For this task, a database comprising ten conditioning factors and 194 flood locations was created using the One-R Attribute Evaluation(ORAE) technique.Various well-known machine learning and optimization algorithms were used as benchmarks to compare the prediction accuracy of the proposed model.Statistical metrics include sensitivity,specificity accuracy, root mean square error(RMSE), and area under the receiver operatic characteristic curve(AUC) were used to assess the validity of the proposed model.The result shows that the proposed model has the highest goodness-of-fit(AUC = 0.989) and prediction accuracy(AUC = 0.985), and based on the validation dataset it outperforms benchmark models including LR(0.885), LMT(0.934), BLR(0.936), ADT(0.976), NBT(0.974), REPTree(0.811), ANFIS-BAT(0.944), ANFIS-CA(0.921), ANFIS-IWO(0.939), ANFIS-ICA(0.947), and ANFIS-FA(0.917).We conclude that the DBPGA model is an excellent alternative tool for predicting flash flood susceptibility for other regions prone to flash floods.     

Geochemical background of potentially toxic trace elements in reclaimed soils of the abandoned pyrite–uranium mine (south-central Poland)

Spatial distribution patterns of As, Ba, Cd, Cr, Cu, Mn, Ni, Pb, U and Zn were determined in topsoil samples collected after 40 years of chemical remediation conducted in the inoperative “Staszic” pyrite–uranium mine in the Holy Cross Mountains, south-central Poland. Soil samples were taken from 58 sites using a systematic random sampling design. Selected samples were subjected to an X-ray diffractometry analysis on bulk soils and separated clay fractions. Hematite, goethite and gypsum are common mineral phases in soil samples. Technogenic soils developed on reclaimed mine spoils show uniform spatial element distribution patterns and additionally a distinct enrichment in As, Pb, Mn, U and Zn. Mineral and chemical composition of soils vs. rocks points to the lithogenic source of the determined elements. The results of chemical analysis have been used for evaluation of geochemical background of trace elements in the study area with the iterative 2σ-technique. This investigation shows that using mean crustal element concentrations (Clarke values) as proxies of threshold values in soils are not useful for determination of strongly positive geochemical anomalies. A modified enrichment factor, i.e. a local enrichment factor, is proposed for identification of sites where soils are contaminated.     

Applicability of CPT-based methods in predicting toe bearing capacities of driven piles in sand

This paper presents a study on applicability of predicting toe bearing capacities from cone penetration test (CPT) for PHC (pretensioned spun high-strength concrete) driven piles into deep sandy deposits in the Nakdong River deltaic area west of Busan City in South Korea. Using toe bearing capacities obtained from pile driving analyzer (PDA) tests as reference values, which were reliably calibrated by on-site O-cell tests, the applicability of the CPT-based methods was evaluated using a statistical rank index (RI). A total of 82 piezocone penetration test soundings and 190 PDA test piles were used for reliability analysis in this study. Three correction steps were applied to obtain reliable PDA and CPT data sets before ranking is carried out. The RI index is combined from four criteria: (1) the best-fit line, (2) the arithmetic mean and standard deviation, (3) the cumulative probabilities, and (4) the log-normal and histogram distributions. Based on these criteria the performance of some SPT-based methods in the literature is evaluated.     

A new methodology for computing ionic profiles and disjoining pressure in swelling porous media

A new two-scale computational model is proposed to construct the constitutive law of the swelling pressure which appears in the modified form of the macroscopic effective stress principle for expansive clays saturated by an aqueous electrolyte solution containing multivalent ionic species. The microscopic non-local nanoscale model is constructed based on a coupled Poisson-Fredholm integral equation arising from the thermodynamics of inhomogeneous fluids in nanopores (Density Functional Theory), which governs the local electric double layer potential profile coupled with the ion-particle correlation function in an electrolytic solution of finite size ions. The local problem is discretized by invoking the eigenvalue expansion of the convolution kernel in conjunction with the Galerkin method for the Gauss-Poisson equation. The discretization of the Fredholm equation is accomplished by a collocation scheme employing eigenfunction basis. Numerical simulations of the local ionic profiles in rectangular cell geometries are obtained showing considerable discrepancies with those computed with Poisson-Boltzmann based models for point charges, particularly for divalent ions in calcium montmorillonite. The constitutive law for the disjoining pressure is reconstructed numerically by invoking the contact theorem within a post-processing approach. The resultant computational model is capable of capturing ranges of particle attraction characterized by negative values of the disjoining pressure overlooked by the classical electric double layer theory. Such results provide further insight in the role the swelling pressure plays in the modified macroscopic effective stress principle for expansive porous media.     

Rainfall-induced landslide susceptibility assessment at the Chongren area (China) using frequency ratio,certainty factor,and index of entropy

The main objective of the study was to evaluate and compare the overall performance of three methods, frequency ratio (FR), certainty factor (CF) and index of entropy (IOE), for rainfall-induced landslide susceptibility mapping at the Chongren area (China) using geographic information system and remote sensing. First, a landslide inventory map for the study area was constructed from field surveys and interpretations of aerial photographs. Second, 15 landslide-related factors such as elevation, slope, aspect, plan curvature, profile curvature, stream power index, sediment transport index, topographic wetness index, distance to faults, distance to rivers, distance to roads, landuse, NDVI, lithology and rainfall were prepared for the landslide susceptibility modelling. Using these data, three landslide susceptibility models were constructed using FR, CF and IOE. Finally, these models were validated and compared using known landslide locations and the receiver operating characteristics curve. The result shows that all the models perform well on both the training and validation data. The area under the curve showed that the goodness-of-fit with the training data is 79.12, 80.34 and 80.42% for FR, CF and IOE whereas the prediction power is 80.14, 81.58 and 81.73%, for FR, CF and IOE, respectively. The result of this study may be useful for local government management and land use planning.     

Basin progress: active deformation analysis by tectonostratigraphic elements and geophysical methods on North Anatolian Fault System (Eastern Marmara Region,Turkey)

Natural Hazards - The Northern Branch of the North Anatolian Fault System controls and deforms the Izmit Basin and the Sapanca Lake Basin in the study area. Unlike the Sapanca Lake Basin, the...