Prediction of Density Flow Plunging Depth in Dam Reservoirs: An Artificial Neural Network Approach

Experimental findings and observations indicate that plunging flow is related to the formation of bed load deposition in dam reservoirs. The sediment delta begins to form in the plunging region where the inflow river water meets the ambient reservoir water. Correct estimation of dam reservoir flow, plunging point, and plunging depth is crucial for dam reservoir sedimentation and water quality issues. In this study, artificial neural network (ANN), multi‐linear regression (MLR), and two‐dimensional hydrodynamic model approaches are used for modeling the plunging point and depth. A multi layer perceptron (MLP) is used as the ANN structure. A two‐dimensional model is adapted to simulate density plunging flow through a reservoir with a sloping bottom. In the model, nonlinear and unsteady continuity, momentum, energy, and k–ε turbulence equations are formulated in the Cartesian coordinates. Density flow parameters such as velocity, plunging points, and plunging depths are determined from the simulation and model results, and these are compared with previous experimental and model works. The results show that the ANN model forecasts are much closer to the experimental data than the MLR and mathematical model forecasts.     

Water-table fluctuation in semipervious stream-unconfined aquifer systems

Available expressions which describe the water-table fluctuation in a stream-aquifer system are based primarily on the assumption that the bed of the stream is as permeable as the aquifer it completely cuts through. Analytical expressions are developed, in terms of the head averaged over the depth of saturation, which take into account the semiperviousness of the streambed. The situations considered are finite and semi-infinite aquifer systems in which the water level in the semipervious stream is suddenly lowered below its initial elevation, and suddenly raised above its initial elevation, and maintained constant thereafter. As a by-product, solutions are also obtained for finite and semi-infinite aquifer systems in which the bed of the stream is as permeable as the aquifer.     

Aquifer response to stream-stage and recharge variations. II. Convolution method and applications

In this second of two papers, analytical step-response functions, developed in the companion paper for several cases of transient hydraulic interaction between a fully penetrating stream and a confined, leaky, or water-table aquifer, are used in the convolution integral to calculate aquifer heads, streambank seepage rates, and bank storage that occur in response to stream-stage fluctuations and basinwide recharge or evapotranspiration. Two computer programs developed on the basis of these step-response functions and the convolution integral are applied to the analysis of hydraulic interaction of two alluvial stream–aquifer systems in the northeastern and central United States. These applications demonstrate the utility of the analytical functions and computer programs for estimating aquifer and streambank hydraulic properties, recharge rates, streambank seepage rates, and bank storage. Analysis of the water-table aquifer adjacent to the Blackstone River in Massachusetts suggests that the very shallow depth of water table and associated thin unsaturated zone at the site cause the aquifer to behave like a confined aquifer (negligible specific yield). This finding is consistent with previous studies that have shown that the effective specific yield of an unconfined aquifer approaches zero when the capillary fringe, where sediment pores are saturated by tension, extends to land surface. Under this condition, the aquifer's response is determined by elastic storage only. Estimates of horizontal and vertical hydraulic conductivity, specific yield, specific storage, and recharge for a water-table aquifer adjacent to the Cedar River in eastern Iowa, determined by the use of analytical methods, are in close agreement with those estimated by use of a more complex, multilayer numerical model of the aquifer. Streambank leakance of the semipervious streambank materials also was estimated for the site. The streambank-leakance parameter may be considered to be a general (or lumped) parameter that accounts not only for the resistance of flow at the river–aquifer boundary, but also for the effects of partial penetration of the river and other near-stream flow phenomena not included in the theoretical development of the step-response functions.     

Long-range forecasting of suspended sediment

This study examines the employment of two methods, multiple linear regression (MLR) and an artificial neural network (ANN), for multistep ahead forecasting of suspended sediment. The autoregressive integrated moving average (ARIMA) model is considered for one-step ahead forecasting of sediment series in order to provide a comparison with the MLR and ANN methods. For one- and two-step ahead forecasting, the ANN model performance is superior to that of the MLR model. For longer ranges, MLR models provide better accuracy, but there is an important assumption violation. The Durbin-Watson statistics of the MLR models show a noticeable decrease from 1.3 to 0.5, indicating that the residuals are not dependent over time. The scatterplots of the three methods (MLR, ARIMA and ANN) for one-step ahead forecasting for the validation period illustrate close fits with the regression line, with the ANN configuration having a slightly higher R² value.     

Spatial prediction of river channel topography by kriging

Topographic information is fundamental to geomorphic inquiry, and spatial prediction of bed elevation from irregular survey data is an important component of many reach‐scale studies. Kriging is a geostatistical technique for obtaining these predictions along with measures of their reliability, and this paper outlines a specialized framework intended for application to river channels. Our modular approach includes an algorithm for transforming the coordinates of data and prediction locations to a channel‐centered coordinate system, several different methods of representing the trend component of topographic variation and search strategies that incorporate geomorphic information to determine which survey data are used to make a prediction at a specific location. For example, a relationship between curvature and the lateral position of maximum depth can be used to include cross‐sectional asymmetry in a two‐dimensional trend surface model, and topographic breaklines can be used to restrict which data are retained in a local neighborhood around each prediction location. Using survey data from a restored gravel‐bed river, we demonstrate how transformation to the channel‐centered coordinate system facilitates interpretation of the variogram, a statistical model of reach‐scale spatial structure used in kriging, and how the choice of a trend model affects the variogram of the residuals from that trend. Similarly, we show how decomposing kriging predictions into their trend and residual components can yield useful information on channel morphology. Cross‐validation analyses involving different data configurations and kriging variants indicate that kriging is quite robust and that survey density is the primary control on the accuracy of bed elevation predictions. The root mean‐square error of these predictions is directly proportional to the spacing between surveyed cross‐sections, even in a reconfigured channel with a relatively simple morphology; sophisticated methods of spatial prediction are no substitute for field data. Copyright © 2007 John Wiley & Sons, Ltd.     

Method for estimating available groundwater volume of small coral islands

We present a simple modelling method to estimate the volume of available groundwater in the freshwater lens of atoll islands under steady-state conditions. Model inputs include annual rainfall depth, island width for cross-sections along the length of the island, aquifer hydraulic conductivity, and depth to the contact between the upper sand aquifer and the lower limestone aquifer. The methodology is tested for nine islands of varying size in the Maldives and Micronesia. Sensitivity analysis indicates that lens volume on large islands typically is governed by the depth to the discontinuity, whereas lens volume for smaller islands is governed by rainfall rate and hydraulic conductivity. Volume curves, which relate lens volume to lens thickness, are developed for each of the nine islands and for three generic island shapes to allow rapid estimation of lens volume given field-estimated lens thickness. The methods presented in this study can be used for any small atoll island.     

Aquifer response to stream-stage and recharge variations. I. Analytical step-response functions

Laplace transform step-response functions are presented for various homogeneous confined and leaky aquifer types and for anisotropic, homogeneous unconfined aquifers interacting with perennial streams. Flow is one-dimensional, perpendicular to the stream in the confined and leaky aquifers, and two-dimensional in a plane perpendicular to the stream in the water-table aquifers. The stream is assumed to penetrate the full thickness of the aquifer. The aquifers may be semi-infinite or finite in width and may or may not be bounded at the stream by a semipervious streambank. The solutions are presented in a unified manner so that mathematical relations among the various aquifer configurations are clearly demonstrated. The Laplace transform solutions are inverted numerically to obtain the real-time step-response functions for use in the convolution (or superposition) integral. To maintain linearity in the case of unconfined aquifers, fluctuations in the elevation of the water table are assumed to be small relative to the saturated thickness, and vertical flow into or out of the zone above the water table is assumed to occur instantaneously. Effects of hysteresis in the moisture distribution above the water table are therefore neglected. Graphical comparisons of the new solutions are made with known closed-form solutions.     

Interpolations of groundwater table elevation in dissected uplands

The variable elevation of the groundwater table in the St. Louis area was estimated using multiple linear regression (MLR), ordinary kriging, and cokriging as part of a regional program seeking to assess liquefaction potential. Surface water features were used to determine the minimum water table for MLR and supplement the principal variables for ordinary kriging and cokriging. By evaluating the known depth to the water and the minimum water table elevation, the MLR analysis approximates the groundwater elevation for a contiguous hydrologic system. Ordinary kriging and cokriging estimate values in unsampled areas by calculating the spatial relationships between the unsampled and sampled locations. In this study, ordinary kriging did not incorporate topographic variations as an independent variable, while cokriging included topography as a supporting covariable. Cross validation suggests that cokriging provides a more reliable estimate at known data points with less uncertainty than the other methods. Profiles extending through the dissected uplands terrain suggest that: (1) the groundwater table generated by MLR mimics the ground surface and elicits a exaggerated interpolation of groundwater elevation; (2) the groundwater table estimated by ordinary kriging tends to ignore local topography and exhibits oversmoothing of the actual undulations in the water table; and (3) cokriging appears to give the realistic water surface, which rises and falls in proportion to the overlying topography. The authors concluded that cokriging provided the most realistic estimate of the groundwater surface, which is the key variable in assessing soil liquefaction potential in unconsolidated sediments.     

Suspended sediment yield estimation using genetic algorithm-based artificial intelligence models: case study of Mahanadi River,India

The estimation of sediment yield is important in design, planning and management of river systems. Unfortunately, its accurate estimation using traditional methods is difficult as it involves various complex processes and variables. This investigation deals with a hybrid approach which comprises genetic algorithm-based artificial intelligence (GA-AI) models for the prediction of sediment yield in the Mahanadi River basin, India. Artificial neural network (ANN) and support vector machine (SVM) models are developed for sediment yield prediction, where all parameters associated with the models are optimized using genetic algorithms simultaneously. Water discharge, rainfall and temperature are used as input to develop the GA-AI models. The performance of the GA-AI models is compared to that of traditional AI models (ANN and SVM), multiple linear regression (MLR) and sediment rating curve (SRC) method for evaluating the predictive capability of the models. The results suggest that GA-AI models exhibit better performance than other models.     

A Comparative Study of Specific Yield Determinations for a Shallow Sand Aquifer

Using the type-curve methods of Boulton (1963) and Neuman (1972), and comparisons, at various times, of the cumulative volume of water pumped to the volume of the water-table drawdown cone (volume-balance method), values of specific yield were obtained from pumping test data from numerous piezometers in an unconfined sand aquifer. The long-term value of specific yield for the aquifer was determined from measurements of the laboratory drainage curve of the aquifer material. The volume-balance method gave specific yield values of 0.02, 0.05, 0.12, 0.20, 0.23, and 0.25 at times of 0.25, 0.66, 10, 26, 45, and 65 hours, respectively, indicating a gradual increase in specific yield and an asymptotic approach to the long-term value of 0.30 determined from the laboratory method. The type-curve methods provided values of 0.07 and 0.08, which correspond to the volume-balance values at early times, but which are less than one-third of the value obtained from the laboratory method and from the volume-balance method applied at the end of the pumping test (2.7 days). The type-curve procedures therefore provide unrealistically low values of specific yield for application to problems concerning the long-term yield characteristics of the aquifer. The observed trend towards increasing values of specific yield with increasing duration of pumping, and the vertical hydraulic head profiles that were measured during the pumping test indicate that both delayed drainage from above the water table and downward hydraulic gradients in the saturated zone can be important hydraulic effects contributing to the delayed-drawdown segment that is characteristic of time-drawdown graphs for unconfined aquifers.     

Comparing the stream re-aeration coefficient estimated from ANN and empirical models / Comparaison d'estimations par un RNA et par des modèles empiriques du coefficient de réaération en cours d'eau

Abstract

Dissolved oxygen (DO) is one of the most useful indices of river's health and the stream re-aeration coefficient is an important input to computations related to DO. Normally, this coefficient is expressed as a function of several variables, such as mean stream velocity, shear stress velocity, bed slope, flow depth, and Froude number. However, in free surface flows, some of these variables are interrelated, and it is possible to obtain simplified stream re-aeration equations. In recent years, different functional forms have been advanced to represent the re-aeration coefficient for different data sets. In the present study, the artificial neural network (ANN) technique has been applied to estimate the re-aeration coefficient (K ₂) using data sets measured at different reaches of the Kali River in India and values obtained from the literature. Observed stream/channel velocity, bed slope, flow depth, cross-sectional area and re-aeration coefficient data were used for the analysis. Different combinations of variables were tested to obtain the re-aeration coefficient using an ANN. The performance of the ANN was compared with other estimation methods. It was found that the re-aeration coefficient estimated by using an ANN was much closer to the observed values as compared with the other techniques.     

Using stable water isotopes to identify spatio-temporal controls on groundwater recharge in two contrasting East African aquifer systems

Understanding the spatio-temporal variability in groundwater recharge is a prerequisite to sustainable management of aquifers. Spatial analysis of groundwater stable isotopes uncovered predominant controls on groundwater recharge in the Nairobi aquifer system (NAS) and the South Coast aquifer (SC), two exemplar East African aquifers relied upon by 7 million people. We analysed 368 samples for stable isotopes and basic physico-chemical parameters. The NAS groundwater isotopes are controlled by precipitation orographic effects and enriched recharge from impounded lakes/wetlands; the SC isotopes are correlated with water-table depth influencing evapotranspiration. Global Network of Isotopes in Precipitation (GNIP) data revealed groundwater recharge during months of heavy rains in the NAS, whilst the SC experiences spatio-temporally diffuse recharge. Inferred “isoscapes” show: in the NAS, (1) direct, rapid recharge favoured by faults, well-drained soils and ample rainfall in uplands, (2) delayed recharge from impounded lakes and wetlands in mid-lands, and (3) focused, event-based recharge in floodplains; and in the SC, diffuse recharge complicated by significant water-table evapotranspiration processes.     

Spatial interpolation schemes of daily precipitation for hydrologic modeling

Distributed hydrologic models typically require spatial estimates of precipitation interpolated from sparsely located observational points to the specific grid points. We compare and contrast the performance of regression-based statistical methods for the spatial estimation of precipitation in two hydrologically different basins and confirmed that widely used regression-based estimation schemes fail to describe the realistic spatial variability of daily precipitation field. The methods assessed are: (1) inverse distance weighted average; (2) multiple linear regression (MLR); (3) climatological MLR; and (4) locally weighted polynomial regression (LWP). In order to improve the performance of the interpolations, the authors propose a two-step regression technique for effective daily precipitation estimation. In this simple two-step estimation process, precipitation occurrence is first generated via a logistic regression model before estimate the amount of precipitation separately on wet days. This process generated the precipitation occurrence, amount, and spatial correlation effectively. A distributed hydrologic model (PRMS) was used for the impact analysis in daily time step simulation. Multiple simulations suggested noticeable differences between the input alternatives generated by three different interpolation schemes. Differences are shown in overall simulation error against the observations, degree of explained variability, and seasonal volumes. Simulated streamflows also showed different characteristics in mean, maximum, minimum, and peak flows. Given the same parameter optimization technique, LWP input showed least streamflow error in Alapaha basin and CMLR input showed least error (still very close to LWP) in Animas basin. All of the two-step interpolation inputs resulted in lower streamflow error compared to the directly interpolated inputs.     

Simulating soil loss rate in Ekbatan Dam watershed using experimental and statistical approaches

Reservoir sedimentation resulting fromwater erosion is an important environmental issue inmany countries where storage of water is crucial for economic and agricultural development.Therefore,this paper reports results from analysis of the soil hydrological response,i.e.soil water erosion,to simulated rainfall resulting in sediment accumulation at the reservoir of Ekbatan Dam(Hamedan province,Iran).Also,another objective of this study was to simulate the future trends in reservoir sedimentation(soil loss rate;SLR)from indoor rainfall simulator data by multiple linear regression(MLR)and Artificial Neural Networks(ANNs).For this research,three sampling points with different types of soils were chosen including clayey sand soil(SC-SM),silty soil(ML),and clayey soil(CL).The input parameters were slope gradient(sin θ),soil type(St),water content(w),dry density(γd),shear strength(τ),unconfined compressive strength(qu),permeability(k),and California bearing ratio(CBR).Using MLR and ANN methods,7 models were developed with 2 constant predictors(i.e.sin θ and St)and 6 free predictors which were added in each step one by one.Among MLR models,model 5 with St,sin θ,γd,τ,w,and qu as input parameters was statistically significant.Among ANN models,model 4 with St,sin θ,?d,τ,and w as input parameters,9 nodes,and 1 hidden layer was statistically significant.The root mean square error(RMSE),mean error(ME),and correlation coefficient(R)values were 1.433 kg/m^2 h,0.0195 kg/m^2 h,and 0.698 for the MLRmodel and 0.38 kg/m^2 h,0.151 kg/m^2 h,and 0.98 for the ANN model,respectively.These results show that the ANN model could better predict the SLR in comparison to the MLR model.The results also demonstrate that shear strength,among the strength parameters,had a greater impact on the SLR than compressive strengths(qu and CBR).Last but not the least,the reservoir sedimentationwas estimated for all methods and compared with the observed data.The results indicate that the ANN model is more appropriate for forecasting/simulating the sediment yield for a small watershed.     

Mapping water table depth using geophysical and environmental variables

Despite its importance, accurate representation of the spatial distribution of water table depth remains one of the greatest deficiencies in many hydrological investigations. Historically, both inverse distance weighting (IDW) and ordinary kriging (OK) have been used to interpolate depths. These methods, however, have major limitations: namely they require large numbers of measurements to represent the spatial variability of water table depth and they do not represent the variation between measurement points. We address this issue by assessing the benefits of using stepwise multiple linear regression (MLR) with three different ancillary data sets to predict the water table depth at 100-m intervals. The ancillary data sets used are Electromagnetic (EM34 and EM38), gamma radiometric: potassium (K), uranium (eU), thorium (eTh), total count (TC), and morphometric data. Results show that MLR offers significant precision and accuracy benefits over OK and IDW. Inclusion of the morphometric data set yielded the greatest (16%) improvement in prediction accuracy compared with IDW, followed by the electromagnetic data set (5%). Use of the gamma radiometric data set showed no improvement. The greatest improvement, however, resulted when all data sets were combined (37% increase in prediction accuracy over IDW). Significantly, however, the use of MLR also allows for prediction in variations in water table depth between measurement points, which is crucial for land management.     

The influence of delayed drainage on data from pumping tests in unconfined aquifers

Equations are derived for the flow to a pumped well in an aquifer having uniform anisotropy and overlain by a low-permeability aquitard. The water-table is assumed to be located in the aquitard. Drainage from the capillary zone above the water-table is taken into account.The differential equation for the flow in the aquifer is identical with that derived in a previous paper. The formation constants may therefore be evaluated by using type curves as described in that paper.A well-known pumping test is reanalysed, using the equations in the present paper. It is shown that the time-drawdown curves can be explained only by the existence of a low-permeability stratum in the vicinity of the water-table. In this example the slow draining of the unsaturated zone above the water-table seems to be a significant factor in determining the shape of the time-drawdown curves.     

An ANN‐based model for spatiotemporal groundwater level forecasting

This paper evaluates the feasibility of using an artificial neural network (ANN) methodology for estimating the groundwater levels in some piezometers placed in an aquifer in north‐western Iran. This aquifer is multilayer and has a high groundwater level in urban areas. Spatiotemporal groundwater level simulation in a multilayer aquifer is regarded as difficult in hydrogeology due to the complexity of the different aquifer materials. In the present research the performance of different neural networks for groundwater level forecasting is examined in order to identify an optimal ANN architecture that can simulate the piezometers water levels. Six different types of network architectures and training algorithms are investigated and compared in terms of model prediction efficiency and accuracy. The results of different experiments show that accurate predictions can be achieved with a standard feedforward neural network trained usung the Levenberg–Marquardt algorithm. The structure and spatial regressions of the ANN parameters (weights and biases) are then used for spatiotemporal model presentation. The efficiency of the spatio‐temporal ANN (STANN) model is compared with two hybrid neural‐geostatistics (NG) and multivariate time series‐geostatistics (TSG) models. It is found in this study that the ANNs provide the most accurate predictions in comparison with the other models. Based on the nonlinear intrinsic ANN approach, the developed STANN model gives acceptable results for the Tabriz multilayer aquifer. Copyright © 2008 John Wiley & Sons, Ltd.     

Sensitivity of regionalized transfer-function noise models to the input and parameter transfer method / Sensibilité de modèles de type fonction de transfert bruit régionalisée (FTBR) aux données d'entrée et aux méthodes de transfert de paramètres

Abstract

Monthly shallow water-table depths can be predicted from climate forcings on a large scale by the combination of a transfer-function noise (TFN) model with a parameter regionalization scheme. To investigate the sensitivity of regionalized transfer-function noise (RTFN) models, simulations with different input series and parameter regionalization methods, combined with topographic external drifts, are presented. The input series include the precipitation, precipitation surplus or infiltration calculated by the variable infiltration capacity (VIC) land surface model, and the regionalization methods include those based on a combination of the principal component analysis (PCA) classification or Gaussian mixture model (GMM) clustering, with the external drifts, such as the elevation or terrain slope, generated from digital elevation models (DEM). Verification and cross-validation show that the infiltration series reduces the errors for regionalization by 12.5–18.8%, but cannot improve the calibration. The PCA method outperforms its alternative GMM method for the input series and the external drifts. The combination of the infiltration series and the regionalization method based on PCA classification and elevation produces the best results with respect to the mean absolute error and root mean squared error. The spatial and temporal variations of water-table depths at a macro-scale in continental China are predicted by the combination.     

Using geophysical methods to define the attitude and extension of water-bearing strata in the Miocene sediments of the Pannonian Basin

In the area near the village of Jazak (southern part of Fruška Gora mountain, Serbia), hydrogeological investigations were carried out for the purpose of finding a water supply source to provide an adequate volume of water for a mineral water bottling plant. The first exploratory borehole (IBJf-1) penetrated a water-bearing layer of Miocene organogenic limestones. This aquifer has a thickness of about 30 m and a yield of only 2.2 l/s, which falls short of the required water volume (5 l/s).The objective of further exploration was to define the attitude and extension of the aquifer and thus select a more favourable site for a new exploratory borehole that would secure the required volume of water. For this purpose, geophysical exploration was carried out in 2003 through vertical electrical sounding (VES) and high-resolution 3D reflection seismic methods. The VES measurements enabled determination of aquifer depth and indicated that the water-bearing strata extend over the entire area studied. However, because of the equivalence problem, it was not possible to determine the thickness of the water-bearing stratum based solely on the VES data. Thus, the 3D seismic method was used in the second stage of investigation. A low-cost 3D seismic survey was carried out with fixed receiver lines, using a vibrator as the source of the seismic waves.From the 3D seismic data it was possible to determine the aquifer thickness. The depth of the aquifer determined by interpretation of the 3D seismic data was in accordance with the depth determined by the VES method. Based on the assumption that the hydraulic conductivity of this formation is identical or similar over the entire area, as well as the fact that the first well showed the presence of a subartesian aquifer, we proposed drilling another borehole (IBJf-2) in the zone where the data indicated that the water-bearing stratum was much thicker. The data obtained by drilling and coring were in agreement with the predicted aquifer thickness. Pumping tests showed that the water discharge in borehole IBJf-2 was 6 l/s.The results show that the objective of delineating the groundwater body by combined application of two geophysical methods (VES and 3D seismic) was successfully performed.     

The value of subsidence data in ground water model calibration

The accurate estimation of aquifer parameters such as transmissivity and specific storage is often an important objective during a ground water modeling investigation or aquifer resource evaluation. Parameter estimation is often accomplished with changes in hydraulic head data as the key and most abundant type of observation. The availability and accessibility of global positioning system and interferometric synthetic aperture radar data in heavily pumped alluvial basins can provide important subsidence observations that can greatly aid parameter estimation. The aim of this investigation is to evaluate the value of spatial and temporal subsidence data for automatically estimating parameters with and without observation error using UCODE-2005 and MODFLOW-2000. A synthetic conceptual model (24 separate cases) containing seven transmissivity zones and three zones each for elastic and inelastic skeletal specific storage was used to simulate subsidence and drawdown in an aquifer with variably thick interbeds with delayed drainage. Five pumping wells of variable rates were used to stress the system for up to 15 years. Calibration results indicate that (1) the inverse of the square of the observation values is a reasonable way to weight the observations, (2) spatially abundant subsidence data typically produce superior parameter estimates under constant pumping even with observation error, (3) only a small number of subsidence observations are required to achieve accurate parameter estimates, and (4) for seasonal pumping, accurate parameter estimates for elastic skeletal specific storage values are largely dependent on the quantity of temporal observational data and less on the quantity of available spatial data.