Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization

Abstract

Artificial neural networks (ANNs) have recently been used to predict the hydraulic head in well locations. In the present work, the particle swarm optimization (PSO) algorithm was used to train a feed-forward multi-layer ANN for the simulation of hydraulic head change at an observation well in the region of Agia, Chania, Greece. Three variants of the PSO algorithm were considered, the classic one with inertia weight improvement, PSO with time varying acceleration coefficients (PSO-TVAC) and global best PSO (GLBest-PSO). The best performance was achieved by GLBest-PSO when implemented using field data from the region of interest, providing improved training results compared to the back-propagation training algorithm. The trained ANN was subsequently used for mid-term prediction of the hydraulic head, as well as for the study of three climate change scenarios. Data time series were created using a stochastic weather generator, and the scenarios were examined for the period 2010–2020.

Editor Z.W. Kundzewicz; Associate editor L. See

Citation Tapoglou, E., Trichakis, I.C., Dokou, Z., Nikolos, I.K., and Karatzas, G.P., 2014. Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization. Hydrological Sciences Journal, 59(6), 1225–1239. http://dx.doi.org/10.1080/02626667.2013.838005     

Evaluation of global optimization algorithms for parameter calibration of a computationally intensive hydrologic model

With the popularity of complex hydrologic models, the time taken to run these models is increasing substantially. Comparing and evaluating the efficacy of different optimization algorithms for calibrating computationally intensive hydrologic models is becoming a nontrivial issue. In this study, five global optimization algorithms (genetic algorithms, shuffled complex evolution, particle swarm optimization, differential evolution, and artificial immune system) were tested for automatic parameter calibration of a complex hydrologic model, Soil and Water Assessment Tool (SWAT), in four watersheds. The results show that genetic algorithms (GA) outperform the other four algorithms given model evaluation numbers larger than 2000, while particle swarm optimization (PSO) can obtain better parameter solutions than other algorithms given fewer number of model runs (less than 2000). Given limited computational time, the PSO algorithm is preferred, while GA should be chosen given plenty of computational resources. When applying GA and PSO for parameter optimization of SWAT, small population size should be chosen. Copyright © 2008 John Wiley & Sons, Ltd.     

Development of operating rules for a complex multi-reservoir system by coupling genetic algorithms and network optimization

Abstract

An alternative procedure for assessment of reservoir Operation Rules (ORs) under drought situations is proposed. The definition of ORs for multi-reservoir water resources systems (WRSs) is a topic that has been widely studied by means of optimization and simulation techniques. A traditional approach is to link optimization methods with simulation models. Thus the objective here is to obtain drought ORs for a real and complex WRS: the Júcar River basin in Spain, in which one of the main issues is the resource allocation among agricultural demands in periods of drought. To deal with this problem, a method based on the combined use of genetic algorithms (GA) and network flow optimization (NFO) is presented. The GA used was PIKAIA, which has previously been used in other water resources related fields. This algorithm was linked to the SIMGES simulation model, a part of the AQUATOOL decision support system (DSS). Several tests were developed for defining the parameters of the GA. The optimization of various ORs was analysed with the objective of minimizing short-term and long-term water deficits. The results show that simple ORs produce similar results to more sophisticated ones. The usefulness of this approach in the assessment of ORs for complex multi-reservoir systems is demonstrated.

Citation Lerma, N., Paredes-Arquiola, J., Andreu, J., and Solera, A., 2013. Development of operating rules for a complex multi-reservoir system by coupling genetic algorithms and network optimization. Hydrological Sciences Journal, 58 (4), 797–812.     

222Rn as Natural Tracer for LNAPL Recovery in a Crude Oil‐Contaminated Aquifer

The objective of this study was to investigate whether ²²²Rn in groundwater can be used as a tracer for light non‐aqueous phase liquid (LNAPL) quantification at a field site treated by dual‐phase LNAPL removal. After the break of a pipeline, 5 ha of soil in the nature reserve Coussouls de Crau in southern France was contaminated by 5100 m³ of crude oil. Part of this oil seeped into the underlying gravel aquifer and formed a floating oil body of about 3.9 ha. The remediation consists of plume management by hydraulic groundwater barriers and LNAPL extraction in the source zone. ²²²Rn measurements were performed in 21 wells in and outside the source zone during 15 months. In uncontaminated groundwater, the radon activity was relatively constant and remained always >11 Bq/L. The variability of radon activity measurements in wells affected by the pump‐and‐skim system was consistent with the measurements in wells that were not impacted by the system. The mean activities in wells in the source zone were, in general, significantly lower than in wells upgradient of the source zone, owing to partitioning of ²²²Rn into the oil phase. The lowest activities were found in zones with high non‐aqueous phase liquid (NAPL) recovery. LNAPL saturations around each recovery well were furthermore calculated during a period of high groundwater level, using a laboratory‐determined crude oil–water partitioning coefficient of 38.5 ± 2.9. This yielded an estimated volume of residual crude oil of 309 ± 93 m³ below the capillary fringe. We find that ²²²Rn is a useful and cheap groundwater tracer for finding zones of good LNAPL recovery in an aquifer treated by dual‐phase LNAPL removal, but that quantification of NAPL saturation using Rn is highly uncertain.     

Advantages of the analytic element method for the solution of groundwater management problems

In the simulation‐optimization approach, a coupled optimization and groundwater flow/transport model is used to solve groundwater management problems. The efficiency of the numerical method, which is used to simulate the groundwater flow, is one the major reason to obtain the best solution for a management problem. This study was carried out to examine the advantages of the analytic element method (AEM) in the simulation‐optimization approach, for the solution of groundwater management problems. For this study, the AEM and finite difference method (FDM) based flow models were developed and coupled with the particle swarm optimization (PSO)‐based optimization model. Furthermore, the AEM‐PSO and FDM‐PSO models developed were applied in hypothetical as well as real field conditions to address groundwater management problems and the results were compared. For the real field situation, the models developed were applied to the Dore River basin in France to minimize the installation and operational cost of new pumping wells taking the location and discharge of the pumping wells as decision variables. The constraints of the problem were identified with the help of stakeholders and water authority officials. The AEM flow model was developed to facilitate the management model particularly when at each iteration, the optimization model calls for a simulation model to calculate the values of groundwater heads. The results show that, at some points, the AEM‐PSO model is efficient in identifying the optimal location of wells and consequently results in optimal costs, sometimes difficult when using the FDM. Copyright © 2011 John Wiley & Sons, Ltd.     

Optimizing separate phase light hydrocarbon recovery from contaminated unconfined aquifers

A modeling approach is presented that optimizes separate phase recovery of light non-aqueous phase liquids (LNAPL) for a single dual-extraction well in a homogeneous, isotropic unconfined aquifer. A simulation/regression/optimization (S/R/O) model is developed to predict, analyze, and optimize the oil recovery process. The approach combines detailed simulation, nonlinear regression, and optimization. The S/R/O model utilizes nonlinear regression equations describing system response to time-varying water pumping and oil skimming. Regression equations are developed for residual oil volume and free oil volume. The S/R/O model determines optimized time-varying (stepwise) pumping rates which minimize residual oil volume and maximize free oil recovery while causing free oil volume to decrease a specified amount. This S/R/O modeling approach implicitly immobilizes the free product plume by reversing the water table gradient while achieving containment. Application to a simple representative problem illustrates the S/R/O model utility for problem analysis and remediation design. When compared with the best steady pumping strategies, the optimal stepwise pumping strategy improves free oil recovery by 11.5% and reduces the amount of residual oil left in the system due to pumping by 15%. The S/R/O model approach offers promise for enhancing the design of free phase LNAPL recovery systems and to help in making cost-effective operation and management decisions for hydrogeologists, engineers, and regulators.     

基于混沌微粒群和二维Otsu法的图像快速分割

为了解决二维Otsu法在求取最佳阈值时存在计算量大,及微粒群算法容易陷入局部最优且速度较慢等问题,提出一种将混沌微粒群优化算法和二维Otsu法相结合的图像分割方法。利用混沌微粒群优化算法,实现二维阈值向量的快速全局搜索。实验证明,该算法对复杂图像具有良好的分割效果和较强的实时处理能力。     

Hybrid meta-heuristic machine learning methods applied to landslide susceptibility mapping in the Sahel-Algiers

Landslides are considered as one among many phenomena jeopardizing human beings as well as their constructions. To prevent this disastrous problem, researchers have used several approaches for landslide susceptibility modeling, for the purpose of preparing accurate maps marking landslide prone areas. Among the most frequently used approaches for landslide susceptibility mapping is the Artificial Neural Network (ANN) method. However, the effectiveness of ANN methods could be enhanced by using hybrid metaheuristic algorithms, which are scarcely applied in landslide mapping. In the current study, nine hybrid metaheuristic algorithms, genetic algorithm (GA)-ANN, evolutionary strategy (ES)-ANN, ant colony optimization (ACO)-ANN, particle swarm optimization (PSO)-ANN, biogeography based optimization (BBO)-ANN, gravitational search algorithm (GHA)-ANN, particle swarm optimization and gravitational search algorithm (PSOGSA)-ANN, grey wolves optimization (GWO)-ANN, and probability based incremental learning (PBIL)-ANN have been used to spatially predict landslide susceptibility in Algiers’ Sahel, Algeria. The modeling phase was done using a database of 78 landslides collected utilizing Google Earth images, field surveys, and six conditioning factors (lithology, elevation, slope, land cover, distance to stream, and distance to road). Initially, a gamma test was used to decrease the input variable numbers. Furthermore, the optimal inputs have been modeled by the mean of hybrid metaheuristic ANN techniques and their performance was assessed through seven statistical indicators. The comparative study proves the effectiveness of the co-evolutionary PSOGSA-ANN model, which yielded higher performance in predicting landslide susceptibility compared to the other models. Sensitivity analysis using the step-by-step technique was done afterward, which revealed that the distance to the stream is the most influential factor on landslide susceptibility, followed by the slope factor which ranked second. Lithology and the distance to road have demonstrated a moderate effect on landslide susceptibility. Based on these findings, an accurate map has been designed to help land-use managers and decision-makers to mitigate landslide hazards.     

A stochastic optimization framework for the restoration of an over-exploited aquifer

ABSTRACT

This study investigates the impact of hydraulic conductivity uncertainty on the sustainable management of the aquifer of Lake Karla, Greece, using the stochastic optimization approach. The lack of surface water resources in combination with the sharp increase in irrigation needs in the basin over the last 30 years have led to an unprecedented degradation of the aquifer. In addition, the lack of data regarding hydraulic conductivity in a heterogeneous aquifer leads to hydrogeologic uncertainty. This uncertainty has to be taken into consideration when developing the optimization procedure in order to achieve the aquifer’s sustainable management. Multiple Monte Carlo realizations of this spatially-distributed parameter are generated and groundwater flow is simulated for each one of them. The main goal of the sustainable management of the ‘depleted’ aquifer of Lake Karla is two-fold: to determine the optimum volume of renewable groundwater that can be extracted, while, at the same time, restoring its water table to a historic high level. A stochastic optimization problem is therefore formulated, based on the application of the optimization method for each of the aquifer’s multiple stochastic realizations in a future period. In order to carry out this stochastic optimization procedure, a modelling system consisting of a series of interlinked models was developed. The results show that the proposed stochastic optimization framework can be a very useful tool for estimating the impact of hydraulic conductivity uncertainty on the management strategies of a depleted aquifer restoration. They also prove that the optimization process is affected more by hydraulic conductivity uncertainty than the simulation process.

Editor Z.W. Kundzewicz; Guest editor S. Weijs     

利用改进的粒子群算法反演视震源时间函数

视震源时间函数的提取是研究震源参数的重要途径. 本文提出了利用改进的粒子群(PSO)算法反演视震源时间函数的方法, 以水平线方法得到的结果作为PSO算法的初值, 并对PSO算法的惯性因子和学习因子进行改进, 提高计算效率. 采用改进的PSO算法对模拟数据进行了反演计算, 并与映射Landweber反褶积(PLD)方法和遗传算法(GA)进行了对比分析. 结果表明, 相对于PLD方法, 改进的PSO算法反演结果与真实结果误差更小; 相对于遗传算法, 改进的PSO算法计算效率提高了5倍以上. 最后, 利用改进的算法对2005年10月8日巴基斯坦克什米尔M_W7.6地震的P波视震源时间函数进行了提取, 结果表明此次地震P波视震源时间函数在25 s之内, 震源沿西北向破裂. 该结果与张勇等的结果一致.      

Estimation of unconfined aquifer parameters by genetic algorithms

Abstract

Unconfined aquifer parameters, viz. transmissivity, storage coefficient, specific yield and delay index from a pumping test are estimated using the genetic algorithm optimization (GA) technique. The parameter estimation problem is formulated as a least-squares optimization, in which the parameters are optimized by minimizing the deviations between the field-observed and the model-predicted time–drawdown data. Boulton's convolution integral for the determination of drawdown is coupled with the GA optimization technique. The bias induced by three different objective functions: (a) the sum of squares of absolute deviations between the observed and computed drawdown; (b) the sum of squares of normalized deviations with respect to the observed drawdown; and (c) the sum of squares of normalized deviations with respect to the computed drawdown, is statistically analysed. It is observed that, when the time–drawdown data contain no errors, the objective functions do not induce any bias in the parameter estimates and the true parameters are uniquely identified. However, in the presence of noise, these objective functions induce bias in the parameter estimates. For the case considered, defining the objective function as the sum of the squares of absolute deviations between the observed and simulated drawdowns resulted in the best possible estimates. A comparison of the GA technique with the curve-matching procedure and a conventional optimization technique, such as the sequential unconstrained minimization technique (SUMT), is made in estimating the aquifer parameters from a reported field pumping test in an unconfined aquifer. For the case considered, the GA technique performed better than the other two techniques in parameter estimation, with the sum-of-squares errors obtained from the GA about one fourth of those obtained by the curve matching procedure, and about half of those obtained by SUMT.

Citation Rajesh, M., Kashyap, D. & Hari Prasad, K. S. (2010) Estimation of unconfined aquifer parameters by genetic algorithms. Hydrol. Sci. J. 55(3), 403–413.     

Calibration of a semi-distributed model for conjunctive simulation of surface and groundwater flows / Calage d’un modèle semi-distribué pour la simulation conjointe d’écoulements superficiels et souterrains

Abstract

Abstract A hydrological simulation model was developed for conjunctive representation of surface and groundwater processes. It comprises a conceptual soil moisture accounting module, based on an enhanced version of the Thornthwaite model for the soil moisture reservoir, a Darcian multi-cell groundwater flow module and a module for partitioning water abstractions among water resources. The resulting integrated scheme is highly flexible in the choice of time (i.e. monthly to daily) and space scales (catchment scale, aquifer scale). Model calibration involved successive phases of manual and automatic sessions. For the latter, an innovative optimization method called evolutionary annealing-simplex algorithm is devised. The objective function involves weighted goodness-of-fit criteria for multiple variables with different observation periods, as well as penalty terms for restricting unrealistic water storage trends and deviations from observed intermittency of spring flows. Checks of the unmeasured catchment responses through manually changing parameter bounds guided choosing final parameter sets. The model is applied to the particularly complex Boeoticos Kephisos basin, Greece, where it accurately reproduced the main basin response, i.e. the runoff at its outlet, and also other important components. Emphasis is put on the principle of parsimony which resulted in a computationally effective modelling. This is crucial since the model is to be integrated within a stochastic simulation framework.     

Coupling of finite element and optimization methods for the management of groundwater systems

The paper describes an optimization method for the solution of groundwater management problems. The method consists of a combination of the computation of horizontal plane groundwater flow with a free surface (finite element method) and a linear optimization procedure (simplex algorithm). Considering the special structure of data which result form computing the groundwater flow with the finite element method, and modifying the simplex algorithm, the solution of management problems with complex groundwater flow is realized without any difficulties. Compared to a flow computation alone the additional effort of the optimization (computer time and scope for data storage) is only small.     

Multiple criteria rainfall–runoff model calibration using a parallel genetic algorithm in a cluster of computers / Calage multi-critères en modélisation pluie–débit par un algorithme génétique parallèle mis en œuvre par une grappe d'ordinateurs

Abstract

Genetic algorithms are among of the global optimization schemes that have gained popularity as a means to calibrate rainfall–runoff models. However, a conceptual rainfall–runoff model usually includes 10 or more parameters and these are interdependent, which makes the optimization procedure very time-consuming. This may result in the premature termination of the optimization process which will prejudice the quality of the results. Therefore, the speed of optimization procedure is crucial in order to improve the calibration quality and efficiency. A hybrid method that combines a parallel genetic algorithm with a fuzzy optimal model in a cluster of computers is proposed. The method uses the fuzzy optimal model to evaluate multiple alternatives with multiple criteria where chromosomes are the alternatives, whilst the criteria are flood performance measures. In order to easily distinguish the performance of different alternatives and to address the problem of non-uniqueness of optimum, two fuzzy ratios are defined. The new approach has been tested and compared with results obtained by using a two-stage calibration procedure. The current single procedure produces similar results, but is simpler and automatic. Comparison of results between the serial and parallel genetic algorithms showed that the current methodology can significantly reduce the overall optimization time and simultaneously improve the solution quality.     

Identification of aquifer parameters by optimization methods under consideration of uncertainty

Abstract

An approach is presented to solve the inverse problem for simultaneous identification of different aquifer parameters under steady-state conditions. The proposed methodology is formulated as a maximum likelihood parameter estimation problem. Gauss-Newton and full Newton algorithms are used for optimization with an adjoint-state method for calculating the complete Hessian matrix. The methodology is applied to a realistic groundwater model and Monte-Carlo analysis is used to check the results.     

Estimation of water cloud model vegetation parameters using a genetic algorithm

Abstract

The water cloud model is used to account for the effect of vegetation water content on radar backscatter data. The model generally comprises two parameters that characterize the vegetated terrain, A and B, and two bare soil parameters, C and D. In the present study, parameters A and B were estimated using a genetic algorithm (GA) optimization technique and compared with estimates obtained by the sequential unconstrained minimization technique (SUMT) from measured backscatter data. The parameter estimation was formulated as a least squares optimization problem by minimizing the deviations between the backscatter coefficients retrieved from the ENVISAT ASAR image and those predicted by the water cloud model. The bias induced by three different objective functions was statistically analysed by generating synthetic backscatter data. It was observed that, when the backscatter coefficient data contain no errors, the objective functions do not induce any bias in the parameter estimation and the true parameters are uniquely identified. However, in the presence of noise, these objective functions induce bias in the parameter estimates. For the cases considered, the objective function based on the sum of squares of normalized deviations with respect to the computed backscatter coefficient resulted in the best possible estimates. A comparison of the GA technique with the SUMT was undertaken in estimating the water cloud model parameters. For the case considered, the GA technique performed better than the SUMT in parameter estimation, where the root mean squared error obtained from the GA was about half of that obtained by the SUMT.

Editor D. Koutsoyiannis; Associate editor L. See

Citation Kumar, K., Hari Prasad, K.S. and Arora, M.K., 2012. Estimation of water cloud model vegetation parameters using a genetic algorithm. Hydrological Sciences Journal, 57 (4), 776–789.     

A parallel evolutionary strategy based simulation–optimization approach for solving groundwater source identification problems

Groundwater characterization involves the resolution of unknown system characteristics from observation data, and is often classified as an inverse problem. Inverse problems are difficult to solve due to natural ill-posedness and computational intractability. Here we adopt the use of a simulation–optimization approach that couples a numerical pollutant-transport simulation model with evolutionary search algorithms for solution of the inverse problem. In this approach, the numerical transport model is solved iteratively during the evolutionary search. This process can be computationally intensive since several hundreds to thousands of forward model evaluations are typically required for solution. Given the potential computational intractability of such a simulation–optimization approach, parallel computation is employed to ease and enable the solution of such problems. In this paper, several variations of a groundwater source identification problem is examined in terms of solution quality and computational performance. The computational experiments were performed on the TeraGrid cluster available at the National Center for Supercomputing Applications. The results demonstrate the performance of the parallel simulation–optimization approach in terms of solution quality and computational performance.     

Comparing state-of-the-art evolutionary multi-objective algorithms for long-term groundwater monitoring design

This study compares the performances of four state-of-the-art evolutionary multi-objective optimization (EMO) algorithms: the Non-Dominated Sorted Genetic Algorithm II (NSGAII), the Epsilon-Dominance Non-Dominated Sorted Genetic Algorithm II (ε-NSGAII), the Epsilon-Dominance Multi-Objective Evolutionary Algorithm (εMOEA), and the Strength Pareto Evolutionary Algorithm 2 (SPEA2), on a four-objective long-term groundwater monitoring (LTM) design test case. The LTM test case objectives include: (i) minimize sampling cost, (ii) minimize contaminant concentration estimation error, (iii) minimize contaminant concentration estimation uncertainty, and (iv) minimize contaminant mass estimation error. The 25-well LTM design problem was enumerated to provide the true Pareto-optimal solution set to facilitate rigorous testing of the EMO algorithms. The performances of the four algorithms are assessed and compared using three runtime performance metrics (convergence, diversity, and ε-performance), two unary metrics (the hypervolume indicator and unary ε-indicator) and the first-order empirical attainment function. Results of the analyses indicate that the ε-NSGAII greatly exceeds the performance of the NSGAII and the εMOEA. The ε-NSGAII also achieves superior performance relative to the SPEA2 in terms of search effectiveness and efficiency. In addition, the ε-NSGAII’s simplified parameterization and its ability to adaptively size its population and automatically terminate results in an algorithm which is efficient, reliable, and easy-to-use for water resources applications.     

Improving kriging of groundwater level data using nonlinear normalizing transformations—a field application

Abstract

The present research study investigates the application of nonlinear normalizing data transformations in conjunction with ordinary kriging (OK) for the accurate prediction of groundwater level spatial variability in a sparsely-gauged basin. We investigate three established normalizing methods, Gaussian anamorphosis, trans-Gaussian kriging and the Box-Cox method to improve the estimation accuracy. The first two are applied for the first time to groundwater level data. All three methods improve the mean absolute prediction error compared to the application of OK to the non-transformed data. In addition, a modified Box-Cox transformation is proposed and applied to normalize the hydraulic heads. The modified Box-Cox transformation in conjunction with OK is found to be the optimal spatial model based on leave-one-out cross-validation. The recently established Spartan semivariogram family provides the optimal model fit to the transformed data. Finally, we present maps of the groundwater level and the kriging variance based on the optimal spatial model.

Editor D. Koutsoyiannis; Associate editor A. Montanari

Citation Varouchakis, E.A., Hristopoulos, D.T., and Karatzas, G.P., 2012. Improving kriging of groundwater level data using nonlinear normalizing transformations—a field application. Hydrological Sciences Journal, 57 (7), 1404–1419.