Comparison of three methods of hydrogeological parameter estimation in leaky aquifers using transient flow pumping tests

Accurate knowledge of hydrogeological parameters is essential for groundwater modeling, protection and remediation. Three methods (type curve fitting method, inflection point method and global curve‐fitting method (GCFM)) which are frequently applied in the estimation of leaky aquifer parameters were compared using synthetic pumping tests. The results revealed GCFM could provide best parameter estimation among the three methods with fewer uncertainties associated with the processes of parameter estimation. GCFM was also found to be both time saving and of low cost and is thus more preferable for hydrogeological parameter estimation than the other two methods. Copyright © 2013 John Wiley & Sons, Ltd.     

Optimal pumping locations of skimming wells

Abstract

A real-life problem involving pumping of groundwater from a series of existing wells along a river flood plain underlain with geologically saline water is examined within a conceptual framework. Unplanned pumping results in upconing of saline water. Therefore, it is necessary to determine optimal locations of fixed capacity pumping wells in space and time from a set of pre-selected candidate wells that minimize total salinity concentration in space and time. The nonlinear, non-convex, combinatorial problem involving zero—one decision variables is solved in a simulation—optimization (S/O) framework. Optimization is accomplished by using simulated annealing (SA)—a search algorithm. The computational burden is primarily managed by replacing the numerical model with a surrogate simulator—artificial neural network (ANN). The computational burden is further reduced through intuitive algorithmic guidance. The model results suggest that the skimming wells must be operated from optimal locations such that they are staggered in space and time to obtain least saline water.     

淄博市王旺庄水源地地下水开采预测的数值模拟

王旺庄水源地是淄博市晴纶工程的后备水源地,设计供水能力20000m^2／d。利用Ritz有限元数值分析方法。结合单纯性线性规划,在完成了对山东省淄博市临淄区王旺庄一朱台地段的淄博市腈纶工程水源地的水文地质模型建造的基础上,成功地对水源地进行地下水开采模拟,同时对该水源地的未来10年开采作了两种大气降水条件下的地下水动态预测。为腈纶工程水源地地下水开采提供了充分的设计依据。     

Application of analytical solution for stream depletion due to groundwater pumping in Gapcheon watershed,South Korea

A number of groundwater wells for agricultural activity, including rice farming and greenhouses, have been developed near streams over the past 20 years in South Korea. The result of a stream depletion calculation using an analytical solution of complimentary error function shows that groundwater pumping at 1949 wells drilled in the Gapcheon watershed can produce stream depletion. This amount is estimated at about 7% of annual baseflow and reaches as high as 18% of monthly baseflow during the maximum agricultural water consumption period in May. Agricultural wells have a larger effect on stream depletion than domestic wells because of their higher pumping rate. Stream depletion from agricultural wells located within 200 m from a stream represents 65% of the total depletion rate. Agricultural water policy for water use at nearby streams should be changed to reduce stream depletion and thereby maintain sustainable water development in South Korea. Copyright © 2010 John Wiley & Sons, Ltd.     

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.     

Interactions and connectivity between runoff generation processes of different spatial scales

Monitoring runoff generation processes in the field is a prerequisite for developing conceptual hydrological models and theories. At the same time, our perception of hydrological processes strongly depends on the spatial and temporal scale of observation. Therefore, the aim of this study is to investigate interactions between runoff generation processes of different spatial scales (plot scale, hillslope scale, and headwater scale). Different runoff generation processes of three hillslopes with similar topography, geology and soil properties, but differences in vegetation cover (grassland, coniferous forest, and mixed forest) within a small v‐shaped headwater were measured: water table dynamics in wells with high spatial and temporal resolution, subsurface flow (SSF) of three 10 m wide trenches at the bottom of the hillslopes subdivided into two trench sections each, overland flow at the plot scale, and catchment runoff. Bachmair et al. ( 2012 ) found a high spatial variability of water table dynamics at the plot scale. In this study, we investigate the representativity of SSF observations at the plot scale versus the hillslope scale and vice versa, and the linkage between hillslope dynamics (SSF and overland flow) and streamflow. Distinct differences in total SSF within each 10 m wide trench confirm the high spatial variability of the water table dynamics. The representativity of plot scale observations for hillslope scale SSF strongly depends on whether or not wells capture spatially variable flowpaths. At the grassland hillslope, subsurface flowpaths are not captured by our relatively densely spaced wells (3 m), despite a similar trench flow response to the coniferous forest hillslope. Regarding the linkage between hillslope dynamics and catchment runoff, we found an intermediate to high correlation between streamflow and hillslope hydrological dynamics (trench flow and overland flow), which highlights the importance of hillslope processes in this small watershed. Although the total contribution of SSF to total event catchment runoff is rather small, the contribution during peak flow is moderate to substantial. Additionally, there is process synchronicity between spatially discontiguous measurement points across scales, potentially indicating subsurface flowpath connectivity. Our findings stress the need for (i) a combination of observations at different spatial scales, and (ii) a consideration of the high spatial variability of SSF at the plot and hillslope scale when designing monitoring networks and assessing hydrological connectivity. Copyright © 2013 John Wiley & Sons, Ltd.     

Optimizing layout of pumping well in irrigation district for groundwater sustainable use in northwest China

Optimizing layout of pumping well plays a vital role in curbing the groundwater level decline. A novel optimization model is presented in this study. First, the optimal well number is obtained by taking into account factors of local economy and environment based on nonlinear programming model. Then, the well spatial layout assessment model is attained based on information entropy weight and technique for order preference by similarity to ideal solution (TOPSIS). After that, the relative closeness to positive ideal solution of alternative (c_i) on the rationality of well spatial layout in cultivated land is calculated, and a set of alternatives are ranked according to the descending order of c_i. Finally, the well optimization layout is obtained by combining the optimal well number with well spatial layout assessment result based on the GIS data of pumping wells. As a case study, this method was applied in Yongchang Irrigation District of Shiyang River Basin, the arid region of northwest China. Results show that under the conditions of sustainable use of water resources, the irrigation district needed 724 wells for irrigation, with a decrease of 31.0% when compared with the existing number of wells. The wells with low flow rate and operating efficiency distributed in high density where groundwater is over‐exploitation were recommended to be closed. This well optimization layout method is expected to play a significant role in helping make plans for exploiting groundwater at more sustainable level, curbing the groundwater level decline trend, and improving the local ecological environment. Copyright © 2015 John Wiley & Sons, Ltd.     

Probabilistic and ensemble simulation approaches for input uncertainty quantification of artificial neural network hydrological models

Artificial neural network (ANN) has been demonstrated to be a promising modelling tool for the improved prediction/forecasting of hydrological variables. However, the quantification of uncertainty in ANN is a major issue, as high uncertainty would hinder the reliable application of these models. While several sources have been ascribed, the quantification of input uncertainty in ANN has received little attention. The reason is that each measured input quantity is likely to vary uniquely, which prevents quantification of a reliable prediction uncertainty. In this paper, an optimization method, which integrates probabilistic and ensemble simulation approaches, is proposed for the quantification of input uncertainty of ANN models. The proposed approach is demonstrated through rainfall-runoff modelling for the Leaf River watershed, USA. The results suggest that ignoring explicit quantification of input uncertainty leads to under/over estimation of model prediction uncertainty. It also facilitates identification of appropriate model parameters for better characterizing the hydrological processes.     

Assessment of sediment transport approaches for sand-bed rivers by means of machine learning

Abstract

The quantification of the sediment carrying capacity of a river is a difficult task that has received much attention. For sand-bed rivers especially, several sediment transport functions have appeared in the literature based on various concepts and approaches; however, since they present a significant discrepancy in their results, none of them has become universally accepted. This paper employs three machine learning techniques, namely artificial neural networks, symbolic regression based on genetic programming and an adaptive-network-based fuzzy inference system, for the derivation of sediment transport formulae for sand-bed rivers from field and laboratory flume data. For the determination of the input parameters, some of the most prominent fundamental approaches that govern the phenomenon, such as shear stress, stream power and unit stream power, are utilized and a comparison of their efficacy is provided. The results obtained from the machine learning techniques are superior to those of the commonly-used sediment transport formulae and it is shown that each of the input combinations tested has its own merit, as they produce similarly good results with respect to the data-driven technique employed.

Editor Z.W. Kundzewicz     

Impacts on groundwater recharge areas of megacity pumping: analysis of potential contamination of Kolkata,India, water supply

Abstract

Water supply to the world’s megacities is a problem of quantity and quality that will be a priority in the coming decades. Heavy pumping of groundwater beneath these urban centres, particularly in regions with low natural topographic gradients, such as deltas and floodplains, can fundamentally alter the hydrological system. These changes affect recharge area locations, which may shift closer to the city centre than before development, thereby increasing the potential for contamination. Hydrogeological simulation analysis allows evaluation of the impact on past, present and future pumping for the region of Kolkata, India, on recharge area locations in an aquifer that supplies water to over 13 million people. Relocated recharge areas are compared with known surface contamination sources, with a focus on sustainable management of this urban groundwater resource. The study highlights the impacts of pumping on water sources for long-term development of stressed city aquifers and for future water supply in deltaic and floodplain regions of the world.

Editor D. Koutsoyiannis

Citation Sahu, P., Michael, H.A., Voss, C.I., and Sikdar, P.K., 2013. Impacts on groundwater recharge areas of megacity pumping: analysis of potential contamination of Kolkata, India, water supply. Hydrological Sciences Journal, 58 (6), 1340–1360.     

地震诱发的侧向水平位移神经网络预测模型

在对地震液化诱发的侧向水平位移预测模型评述的基础上，分析了地震、地形、土质等实测数据与侧向水平水移之间的相互关系，并提出了侧向位平位移神经网络预测模型。模型较好地反映了参数之间复杂的非线性关系，网络预测结果与实测数据较为吻合，两者之间相关系数为0．9左右。模型数据分析结果表明侧向位移随着距自由临空面距离（L）的增加而呈双曲线关系下降，随液化层厚度的增加而增加。不同L条件一临空面高度与侧向位移之间有一灵敏变化区，即当H约等于4－7m之间时，侧向位移急剧变化。     

Comparison of bootstrap confidence intervals for an ANN model of a karstic aquifer response

Following many applications artificial neural networks (ANNs) have found in hydrology, a question has been rising for quantification of the output uncertainty. A pre‐optimized ANN simulated the hydraulic head change at two observation wells, having as input hydrological and meteorological parameters. In order to calculate confidence intervals (CI) for the ANN output two bootstrap methods were examined namely bootstrap percentile and BCa (Bias‐Corrected and accelerated). The actual coverage of the CI was compared to the theoretical coverage for different certainty levels as a means of examining the method's reliability. The results of this work support the idea that the bootstrap methods provide a simple tool for confidence interval computation of ANNs. Comparing the two methods, the percentile requires fewer calculations and yields narrower intervals with similar actual coverage to that of BCa. Overall, the actual coverage was proved lower than desired when not modeled points were present in the data subset. Copyright © 2011 John Wiley & Sons, Ltd.     

Genetic programming model for forecast of short and noisy data

Though forecasting of river flow has received a great deal of attention from engineers and researchers throughout the world, this still continues to be a challenging task owing to the complexity of the process. In the last decade or so, artificial neural networks (ANNs) have been widely applied, and their ability to model complex phenomena has been clearly demonstrated. However, the success of ANNs depends very crucially on having representative records of sufficient length. Further, the forecast accuracy decreases rapidly with an increase in the forecast horizon. In this study, the use of the Darwinian theory‐based recent evolutionary technique of genetic programming (GP) is suggested to forecast fortnightly flow up to 4‐lead. It is demonstrated that short lead predictions can be significantly improved from a short and noisy time series if the stochastic (noise) component is appropriately filtered out. The deterministic component can then be easily modelled. Further, only the immediate antecedent exogenous and/or non‐exogenous inputs can be assumed to control the process. With an increase in the forecast horizon, the stochastic components also play an important role in the forecast, besides the inherent difficulty in ascertaining the appropriate input variables which can be assumed to govern the underlying process. GP is found to be an efficient tool to identify the most appropriate input variables to achieve reasonable prediction accuracy for higher lead‐period forecasts. A comparison with ANNs suggests that though there is no significant difference in the prediction accuracy, GP does offer some unique advantages. Copyright © 2006 John Wiley & Sons, Ltd.     

基于人工神经网络的钢筋混凝土异型节点滞回模型

讨论了应用神经网络技术模拟钢筋混凝土材料滞回行为的若干问题，建立了钢筋混凝土异型节点滞回特性的BP神经网络预测模型，并获得了满意的结果。分析表明，神经网络计算是钢筋混凝土构件抗震性能研究中的一种很有潜力的新方法。     

Optimal selection of artificial neural network parameters for the prediction of a karstic aquifer's response

The simulation of karstic aquifers is difficult using traditional groundwater numerical simulators, as the exact knowledge of the hydraulic characteristics of the physical system in small scale is rarely available and the numerical simulators produce results of limited reliability. In the present work, artificial neural networks (ANNs) are utilized to predict the response of a karstic aquifer, using the hydraulic head change per time step rather than the hydraulic head itself as output parameter of the network. As it will be demonstrated, in the first case a better approximation of the physical system's response is achieved as the change of the hydraulic head is more naturally connected to the input parameters of the network, which model the aquatic equilibrium of the system. The correlation of rainfall and hydraulic head change per time step was initially used to determine the time lag of the rainfall input data, which represents the time needed by the rainfall to percolate and reach the water table. In a second step, a differential evolution (DE) algorithm is utilized for the optimal selection of rainfall time lag as well as ANN's architecture and training parameters. Although a time consuming procedure, the improvement obtained suggests that the empirical determination of the ANN parameters and structure is not always sufficient and an optimization procedure, which minimizes the training and evaluation errors of the ANN, may provide substantially better simulation results. The optimized networks were finally used for midterm predictions (30 to 90 days ahead) of the hydraulic head, showing the ability of the ANN with hydraulic head change as output parameter to provide predictions with high accuracy at the end of the considered time period. Copyright © 2009 John Wiley & Sons, Ltd.     

Comparison of data-driven modelling techniques for river flow forecasting

Abstract

Accurate forecasting of streamflow is essential for the efficient operation of water resources systems. The streamflow process is complex and highly nonlinear. Therefore, researchers try to devise alterative techniques to forecast streamflow with relative ease and reasonable accuracy, although traditional deterministic and conceptual models are available. The present work uses three data-driven techniques, namely artificial neural networks (ANN), genetic programming (GP) and model trees (MT) to forecast river flow one day in advance at two stations in the Narmada catchment of India, and the results are compared. All the models performed reasonably well as far as accuracy of prediction is concerned. It was found that the ANN and MT techniques performed almost equally well, but GP performed better than both these techniques, although only marginally in terms of prediction accuracy in normal and extreme events.

Citation Londhe, S. & Charhate, S. (2010) Comparison of data-driven modelling techniques for river flow forecasting. Hydrol. Sci. J. 55(7), 1163–1174.     

On the importance of training methods and ensemble aggregation for runoff prediction by means of artificial neural networks

ABSTRACT

Artificial neural networks (ANNs) become widely used for runoff forecasting in numerous studies. Usually classical gradient-based methods are applied in ANN training and a single ANN model is used. To improve the modelling performance, in some papers ensemble aggregation approaches are used whilst in others, novel training methods are proposed. In this study, the usefulness of both concepts is analysed. First, the applicability of a large number of population-based metaheuristics to ANN training for runoff forecasting is tested on data collected from four catchments, namely upper Annapolis (Nova Scotia, Canada), Biala Tarnowska (Poland), upper Allier (France) and Axe Creek (Victoria, Australia). Then, the importance of the search for novel training methods is compared with the importance of the use of a very simple ANN ensemble aggregation approach. It is shown that although some metaheuristics may slightly outperform the classical gradient-based Levenberg-Marquardt algorithm for a specific catchment, none performs better for the majority of the tested ones. One may also point out a few metaheuristics that do not suit ANN training at all. On the other hand, application of even the simplest ensemble aggregation approach clearly improves the results when the ensemble members are trained by any suitable algorithms.

EDITOR D. Koutsoyiannis; ASSOCIATE EDITOR E. Toth     

Dynamic loading test and simulation analysis of full‐scale semi‐active hydraulic damper for structural control

A semi‐active hydraulic damper (SHD) for a semi‐active damper system, which is useful for practical structural control especially for large earthquakes, has been developed. Its maximum damping force is set to 1 or 2 MN, and it is controlled by only 70 W of electric power. An SHD with a maximum damping force of 1 MN was applied to an actual building in 1998. This paper first presents the results of a dynamic loading test to confirm the control performance of the SHD. Next, an analytical model of SHDs (SHD model) is constructed with the same concept for two kinds of SHDs based on the test results. Through simulation analyses of the test results using the proposed SHD model, the dynamic characteristics of the SHD can be well represented within practical conditions. Simulation analyses are also carried out using a simple structure model with the SHD model. It is shown that this SHD model can be used to precisely evaluate the control effect of the semi‐active damper system and is useful in practical SHD design under the applied conditions. Copyright © 2000 John Wiley & Sons, Ltd.