Comparative study of multilayer perceptron-stochastic gradient descent and gradient boosted trees for predicting daily suspended sediment load: The case study of the Mississippi River,U.S.

Monitoring sediment transport is essential for managing and maintaining rivers.Estimation of the sediment load in rivers is fundamental for the study of sediment movement,erosion,and flood control.In the current study,three machine learning models-multi-layer perceptron(MLP),multi-layer perceptron-stochastic gradient descent(MLP-SGD),and gradient boosted tree(GBT)-were utilized to estimate the suspended sediment load(SSL)at the St.Louis(SL)and Chester(CH)stations on the Mississippi River,U.S.Four evaluation criteria including the Correlation Coefficient(CC),Nash Sutcliffe Efficiency(NSE),Scatter Index(SI),and Willmott’s Index(WI)were utilized to evaluate the performance of the used models.A sensitivity analysis of the models to the input variables revealed that the current day discharge variable had the most effect on the SSL at both stations,but in the absence of current-day discharge data(Qt),a combination of input parameters including SSL_t-3,SSL_t-2,SSL_t-1,Q_t-3,Q_t-2,Q_t-1 can be used to estimate the SSL.The comparative outcomes indicated the high accuracy of MLP-SGD-5 model with a CC of 0.983,SI of 0.254,WI of 0.991,and NSE of 0.967 at station CH and the MLP-SGD-6 model with a CC of 0.933,SI of 0.576,WI of 0.961,and NSE of 0.867,respectively,at station SL.The results of MLP models were improved by SGD optimization.Therefore,the MLP-SGD method is recommended as the most accurate model for SSL estimation.     

Sedimentological and geoenvironmental evaluation of the coastal area between Al-Khowkhah and Al-Mokha,southeastern Red Sea,Republic of Yemen

The increasing anthropogenic activities (e.g., constructing touristic resorts) have led to notable changes in the Yemeni Red Sea coastal regions. In this context, recent sediments have been investigated to infer possible natural and man-induced processes on these coastal areas. The target area lies between longitudes 43°13′–43°30′E and latitudes 13°15′–13°55′N. It extends about 90 km along the coastline as a part of the Tihama plain. Geomorphologically, it forms a long-curved stretch with pronounced headlands, embayments and bays. Generally, it is covered by recent sediments (wadi, lagoon, beach and spit deposits along with sabkha, coastal dunes and mangrove). Textural studies reveal that most of the studied sediments are mainly poorly to moderately sorted and are composed mainly of sandy fractions with few gravel and mud, mostly bimodal with minor unimodal patterns. The igneous (granites) as well as basic (basalt, andesite and andesitic pyroclastics) and acidic (dacite and rhyolite) volcanic rocks of Tertiary age, which are exposed to the east of the study area, are believed to be the source of pyroxenes, amphiboles, epidotes, biotite, sphene, zircon, tourmaline and rutile, in a decreasing order of abundance. Moreover, smectite, kaolinite, chlorite, illite and palygorskite are the predominant clay minerals, mainly of detrital origin. The total carbonate content fluctuates from 37.41% (lagoon sediments) to 53.74% (sabkha sediments). The high amount of sea grasses, which covers the tidal flat zone and relates to the fine-grained sediments, accounts for the high organic matter content. The mineralogy of the source rocks has controlled the general distribution of major elements (Fe, Mg, Na, K and Mn) in the beach sediments. In such sediments, the concentrations of the heavy metals (Cu, Zn, Cd, Ni, Pb and Co) may reflect the sediment pollution using different approaches. The enrichment factors (EFs) of the trace metals for most samples reveal values that are greater than 1, referring to three groupings, which are: moderate to moderately severe (Zn, Cu and Mn), minor to moderate (Pb and Co) and zero to minor (Cd and Ni) enrichment. The EFs for Pb, Cd, Ni and Co metals (<5) may be attributed to the crustal materials and/or natural weathering processes. But, those for Zn, Cu and Mn (>5), especially in Al-Khowkhah–Abu-Zahr, Moushij–Zahari–Ruays, Yokhtol and Mokha localities, are possible of anthropogenic contributions.     

Spectroscopic-based assessment of the content and geochemical behaviour of arsenic in a highly heterogeneous sulphide-rich mine waste dump

Soil pollution by arsenic is a serious environmental problem in many mining areas. Quick identification of the amount and extent of the pollution is an important basis for developing appropriate remediation strategies. In a case study, 55 soil samples were collected from a highly heterogeneous waste dump around the Sarcheshmeh copper mine, south east Iran. Samples’ visible and near-infrared (VNIR) reflectance spectra were measured, transformed to absorbance and then pre-processed using Savitzky–Golay first-derivative (FD) and Savitzky–Golay second-derivative (SD) transformation methods. The obtained spectra were then subjected to three regression models including principal component regression (PCR), partial least squares regression (PLSR) and support vector regression (SVR) for predicting arsenic concentration. The best prediction accuracies were obtained by SVR and PLSR methods applied on first-derivative pre-processed spectra with R ² values of 0.81 and 0.69, respectively. It was found that VNIR spectroscopy is a successful method for predicting As concentration in contaminated soils of the dumpsites. Study of the prediction mechanism showed that the intercorrelation between arsenic and spectral features of soil including iron oxy/hydroxides and clay minerals was the major mechanism enabling the prediction of arsenic concentration. However, higher values of correlation coefficients at ~460, ~560 and ~590 nm suggested the internal association between arsenic and iron minerals as the more important mechanism for prediction. This conclusion supported previous speciation studies conducted in the same waste dump using improved correlation analysis and chemical sequential extraction method.     

Development of a Land Subsidence Forecasting Model Using Small Baseline Subset—Differential Synthetic Aperture Radar Interferometry and Particle Swarm Optimization—Random Forest (Case Study: Tehran-Karaj-Shahriyar Aquifer,Iran)

Doklady Earth Sciences - Land subsidence, as a dangerous environmental issue, causes serious damages to farms and urban infrastructure. In this regards, this research was conducted with aimed to...     

Bayesian spatio-temporal analysis of stomach cancer incidence in Iran, 2003–2010

Stomach cancer is the second most common cancer in Iranian men and the fourth most common cancer in Iranian women. The incidence rate of this cancer in Iranian men is almost 2.5 times that in women. The objective of this study was to investigate the trend of stomach cancer incidence rate in Iran in an 8-year time period (2003–2010) and also update the incidence estimates of stomach cancer. Data from a total number of 41,830 patients diagnosed with stomach cancer according to the International Classification of Diseases (C16) in 2003–2010 were analyzed. We used Bayesian spatial and Bayesian spatio-temporal models to study the relative risk and trend of stomach cancer incidence rate in Iran. Out of 41,830 stomach cancer registered patients, 72% were male. The average smoothed SIRs were 0.79, 0.82 and 0.78 for the general, female and male population, respectively. This shows a nearly stable incidence rate. The northwest of Iran had the highest incidence rate of stomach cancer. The trend of this rate was declining to the lowest rate in the southeast of the country. The estimated values of coefficient of the trend term for general, female and male population in this model were 0.0085, ? 0.018 and 0.0041, which indicate almost a stable fixed trend. The map of temporal trends also showed that although the incidence rate of this cancer is to some extent stable, in general, in the central and in the east of the country the incidence relative risk has increased over time. The prevalence of Helicobacter pylori infection, Lower socioeconomic status and Iodine deficiency were speculated to be relevant factors for the high incidence rates of stomach cancer in the northwest of Iran. Preventive measures in the north and northwest of Iran could have an effect on controlling this cancer in these areas.     

Efficiency of employing fiber-based finite-length plastic hinges in simulating the cyclic and seismic behavior of steel hollow columns compared with other common modelling approaches

The accuracy and efficiency of the modelling techniques utilized to model the nonlinear behavior of structural components is a significant issue in earthquake engineering. In this study, the sufficiency of three different modelling techniques that can be employed to simulate the structural behavior of columns is investigated. A fiber-based finite length plastic hinge (FB-FLPH) model is calibrated in this study. In order to calibrate the FB-FLPH model, a novel database of the cyclic behavior of hollow steel columns under simultaneous axial and lateral loading cycles with varying amplitudes is used. By employing the FB-FLPH model calibrated in this study, the interaction of the axial force and the bending moment in columns is directly taken into account, and the deterioration in the cyclic behavior of these members is implicitly considered. The superiority of the calibrated FB-FLPH modelling approach is examined compared with the cases in which conventional fiber-based distributed plasticity and concentrated plasticity models are utilized. The efficiency of the enumerated modelling techniques is probed when they are implemented to model the columns of a typical special moment frame in order to prove the advantage of the FB-FLPH modelling approach.

     

Simulating compound flooding events in a hurricane

Ocean Dynamics - Compound flooding is usually induced by the concurrence of coastal storm surge and heavy precipitation induced river flooding, with the former involving oceanic processes and the...     

Climate change impact on precipitation and cardinal temperatures in different climatic zones in Iran: analyzing the probable effects on cereal water-use efficiency

Global greenhouse gases increase could be a threat to sustainable agriculture since it might affect both green water and air temperature. Using the outputs of 15 general circulation models (GCMs) under three SRES scenarios of A1B, A2 and B1, the projected annual and seasonal precipitation (P) and cardinal temperatures (T) were analyzed for five climatic zones in Iran. In addition, the probable effects of climate change on cereal production were studied using AquaCrop model. Data obtained from the GCMs were downscaled using LARS-WG for 52 synoptic stations up to 2100. An uncertainty analysis was done for the projected P and T associated to GCMs and SRES scenarios. Based on station observations, LARS-WG was capable enough for simulating both P and T for all the climatic zones. The majority of GCMs as well as the median of the ensemble for each scenario project positive P and T changes. In all the climatic zones, wet seasons have a higher P increase than dry seasons, with the highest increase (27.9–83.3%) corresponding to hyper-arid and arid regions. A few GCMs project a P reduction mainly in Mediterranean and hyper-humid climatic regions. The highest increase (11.2–44.5%) in minimum T occurred in Mediterranean climatic regions followed by semi-arid regions in which a concurrent increase in maximum T (2.9–14.6%) occurred. The largest uncertainty in P and cardinal T projection occurred in rainy seasons as well as in hyper-humid regions. The AquaCrop simulation results revealed that the increased cardinal T under global warming will cause 0–28.5% increase in cereal water requirement as well as 0–15% reduction in crop yield leading to 0–30% reduction in water use efficiency in 95% of the country.     

Reconstructing Regional Ionospheric Electron Density: A Combined Spherical Slepian Function and Empirical Orthogonal Function Approach

The computerized ionospheric tomography is a method for imaging the Earth’s ionosphere using a sounding technique and computing the slant total electron content (STEC) values from data of the global positioning system (GPS). The most common approach for ionospheric tomography is the voxel-based model, in which (1) the ionosphere is divided into voxels, (2) the STEC is then measured along (many) satellite signal paths, and finally (3) an inversion procedure is applied to reconstruct the electron density distribution of the ionosphere. In this study, a computationally efficient approach is introduced, which improves the inversion procedure of step 3. Our proposed method combines the empirical orthogonal function and the spherical Slepian base functions to describe the vertical and horizontal distribution of electron density, respectively. Thus, it can be applied on regional and global case studies. Numerical application is demonstrated using the ground-based GPS data over South America. Our results are validated against ionospheric tomography obtained from the constellation observing system for meteorology, ionosphere, and climate (COSMIC) observations and the global ionosphere map estimated by international centers, as well as by comparison with STEC derived from independent GPS stations. Using the proposed approach, we find that while using 30 GPS measurements in South America, one can achieve comparable accuracy with those from COSMIC data within the reported accuracy (1 × 10¹¹ el/cm³) of the product. Comparisons with real observations of two GPS stations indicate an absolute difference is less than 2 TECU (where 1 total electron content unit, TECU, is 10¹⁶ electrons/m²).     

A Unified Computational Method for Simulating Dynamic Behavior of Planing Vessels

High speed planing hulls have complex hydrodynamic behaviors. The trim angle and drafts are very sensitive to speed and location of the center of gravity. Therefore, motion simulation for such vessels needs a strong coupling between rigid body motions and hydrodynamic analysis. In addition, free surface should be predicted with good accuracy for each time step. In this paper, velocity and pressure fields are coupled by use of the fractional step method. On the basis of integration of the two-phase viscous flow induced stresses over the hull, acting loads (forces and moments) are calculated. With the strategy of boundary-fitted body-attached mesh and calculation of 6-DoF motions in each time step, time history of ship motions including displacements, speeds and accelerations are evaluated. For the demonstration of the software capabilities, circular cylinder slamming is simulated as a simple type of water slamming. Then, a high-speed planing catamaran is investigated in the case of steady forward motion. All of the results are in good concordance with experimental data. The present method can be widely implemented in design as well as in performance prediction of high-speed vessels.