Evaluating the support vector machine for suspended sediment load forecasting based on gamma test

Due to the various influencing factors on river suspended sediment transportation, determining an appropriate input combination for developing the suspended sediment load forecasting model is very important for water resources management. The influence of pre-processing of input variables by Gamma Test (GT) was investigated on performance of Support Vector Machine (SVM) with two kernels; Radial Basis Function (RBF) and polynomial in order to forecast daily suspended sediment amount in the period between 1983 and 2014 at Korkorsar basin, northern Iran. The best input combination was identified using GT and correlation coefficient analysis. Then, the SVM model was developed and the suspended sediment amount was forecasted with RBF and polynomial kernels. The obtained results in testing phase showed that GT-SVM (RBF kernel) model can estimate suspended sediment more accurately with the lowest RMSE (14.045 ton/day), highest correlation coefficient (0.88) and highest NSEC coefficient (0.88) than SVM (RBF kernel) model (RMSE?=?18.36ton/day, \( {R}^2=0.79, \) \( NSEC=0.73 \)) and had a better performance than the other models. The results indicated that in forecasting the first nine maximum values of suspended sediment load, GT-SVM (RBF) had a higher capability than the other models and could provide a more accurate estimation from the maximum rate of suspended sediment. The results of this study showed the capability of identifying the priority of the input parameters can change GT to a useful and technical test for input variables pre-processing to forecast the amount of suspended sediments.     

Storage dam’s locality placing by MCDM techniques (case study: three dams in Iran)

MCDM (multi-criteria decision making) techniques are used to choose the best alternative among the relevant ones and rank the others. In this research, MCDM techniques were used to choose and rank the best places for constructing storage dams in Iran. To achieve this goal, the relevant information and data about dam construction situations were collected. Then, the recommended places for constructing storage dams were ranked by using MCDM techniques and according to the most suitable criteria which have been chosen based on experts’ opinions. To rank dam constructing project, three MCDM techniques, i.e., TOPSIS, AHP, and DEMATEL, were used. The results showed that the application of MCDM models by putting emphasis on economic, social, political, and technical criteria enables government and watershed managers to choose the best alternative(s) for constructing a storage dam.     

Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province,Iran

Flood is one of the most devastating natural disasters with socio-economic and environmental consequences. Thus, comprehensive flood management is essential to reduce the flood effects on human lives and livelihoods. The main goal of this study was to investigate the application of the frequency ratio (FR) and weights-of-evidence (WofE) models for flood susceptibility mapping in the Golestan Province, Iran. At first, a flood inventory map was prepared using Iranian Water Resources Department and extensive field surveys. In total, 144 flood locations were identified in the study area. Of these, 101 (70%) floods were randomly selected as training data and the remaining 43 (30%) cases were used for the validation purposes. In the next step, flood conditioning factors such as lithology, land-use, distance from rivers, soil texture, slope angle, slope aspect, plan curvature, topographic wetness index (TWI) and altitude were prepared from the spatial database. Subsequently, the receiver operating characteristic (ROC) curves were drawn for produced flood susceptibility maps and the area under the curves (AUCs) was computed. The final results indicated that the FR (AUC = 76.47%) and WofE (AUC = 74.74%) models have almost similar and reasonable results. Therefore, these flood susceptibility maps can be useful for researchers and planner in flood mitigation strategies.     

Probabilistic analyses of soil consolidation by prefabricated vertical drains for single‐drain and multi‐drain systems

Natural soils are one of the most inherently variables in the ground. Although the significance of inherent soil variability in relation to reliable predictions of consolidation rates of soil deposits has long been realized, there have been few studies that addressed the issue of soil variability for the problem of ground improvement by prefabricated vertical drains. Despite showing valuable insights into the impact of soil spatial variability on soil consolidation by prefabricated vertical drains, available stochastic works on this subject are based on a single‐drain (or unit cell) analyses. However, how the idealized unit cell solution can be a supplement to the complex multi‐drain systems for spatially variable soils has never been addressed in the literature. In this study, a rigorous stochastic finite elements modeling approach that allows the true nature of soil spatial variability to be considered in a reliable and quantifiable manner, both for the single‐drain and multi‐drain systems, is presented. The feasibility of performing an analysis based on the unit cell concept as compared with the multi‐drain analysis is assessed in a probabilistic context. It is shown that with proper input statistics representative of a particular domain of interest, both the single‐drain and multi‐drain analyses yield almost identical results. Copyright © 2016 John Wiley & Sons, Ltd.     

Luminescence dating of buried cobble surfaces from sandy beach ridges: a case study from Denmark

Here we investigate the use of optically stimulated luminescence (OSL) for dating cobbles from the body of successive beach ridges and compare cobble surface‐derived ages to standard quartz OSL ages from sand. Between four and eight cobbles and sand samples (age control) were dated with the luminescence method, taken from the modern beach and from beach ridges on the south and north extremes of a prograding spit on the westernmost coast of Lolland, Denmark. Luminescence‐depth profiles perpendicular to the surfaces of the cobbles show that the feldspar infrared signals stimulated at 50 °C were fully reset to various depths into the cobbles prior to final deposition; as a result, the equivalent doses determined from close to the surface of such cobbles can be used to calculate burial ages. Beach‐ridge burial ages given by the average of ages of individual cobbles taken from the same site are consistent, within errors, with the ages derived from the sand samples. Cobble‐ and sand‐derived ages show that the southernmost beach ridge at Albuen was formed around 2 ka ago, indicating that this sandy spit is younger than other coastal systems in Denmark. The agreement between ages derived from clasts and from standard quartz OSL in this study confirms that, even in the absence of sandy sediments, we can reliably date sites using OSL by targeting larger clasts. In addition, the record of prior light exposure contained in the shape of the cobbles’ luminescence‐depth profile removes one of the major uncertainties (i.e. the degree of signal reset prior to burial) in the luminescence dating of high latitude sites.     

Simulating precipitation in the Northeast United States using a climate-informed K-nearest neighbour algorithm

Decadal prediction using climate models faces long-standing challenges. While global climate models may reproduce long-term shifts in climate due to external forcing, in the near term, they often fail to accurately simulate interannual climate variability, as well as seasonal variability, wet and dry spells, and persistence, which are essential for water resources management. We developed a new climate-informed K-nearest neighbour (K-NN)-based stochastic modelling approach to capture the long-term trend and variability while replicating intra-annual statistics. The climate-informed K-NN stochastic model utilizes historical data along with climate state information to provide improved simulations of weather for near-term regional projections. Daily precipitation and temperature simulations are based on analogue weather days that belong to years similar to the current year's climate state. The climate-informed K-NN stochastic model is tested using 53 weather stations in the Northeast United States with an evident monotonic trend in annual precipitation. The model is also compared to the original K-NN weather generator and ISIMIP-2b GFDL general circulation model bias-corrected output in a cross-validation mode. Results indicate that the climate-informed K-NN model provides improved simulations for dry and wet regimes, and better uncertainty bounds for annual average precipitation. The model also replicates the within-year rainfall statistics. For the 1961–1970 dry regime, the model captures annual average precipitation and the intra-annual coefficient of variation. For the 2005–2014 wet regime, the model replicates the monotonic trend and daily persistence in precipitation. These improved modelled precipitation time series can be used for accurately simulating near-term streamflow, which in turn can be used for short-term water resources planning and management.     

Socioeconomic impacts of environmental risks in the western Makran zone (Chabahar,Iran)

Natural Hazards - The western Makran subduction zone is capable of producing considerable tsunami run-up heights that penetrate up to 5 km inland. In this study, we show how climate change...     

Assessing factors affecting drought,earthquake, and flood risk perception: empirical evidence from Bangladesh

Natural Hazards - Understanding household disaster risk perception is crucial to formulate and apply disaster risk reduction strategies. Using survey data from 300 households from three highly...