Fuzzy Genetic Approach for Estimating Reference Evapotranspiration of Turkey: Mediterranean Region

The applicability of fuzzy genetic (FG) approach in modeling reference evapotranspiration (ET₀) is investigated in this study. Daily solar radiation, air temperature, relative humidity and wind speed data of two stations, Isparta and Antalya, in Mediterranean region of Turkey, are used as inputs to the FG models to estimate ET₀ obtained using the FAO-56 Penman–Monteith equation. The FG estimates are compared with those of the artificial neural networks (ANN). Root mean-squared error, mean absolute error and determination coefficient statistics were used as comparison criteria for the evaluation of the models’ accuracies. It was found that the FG models generally performed better than the ANN models in modeling ET₀ of Mediterranean region of Turkey.     

Integrated Sustainable Irrigation Planning with Multiobjective Fuzzy Optimization Approach

Multiobjective fuzzy methodology is applied to a case study of Khadakwasla complex irrigation project located near Pune city of Maharashtra State, India. Three objectives, namely, maximization of net benefits, crop production and labour employment are considered. Effect of reuse of wastewater on the planning scenario is also studied. Three membership functions, namely, nonlinear, hyperbolic and exponential are analyzed for multiobjective fuzzy optimization. In the present study, objective functions are considered as fuzzy in nature whereas inflows are considered as dependable. It is concluded that exponential and hyperbolic membership functions provided similar cropping pattern for most of the situations whereas nonlinear membership functions provided different cropping pattern. However, in all the three cases, irrigation intensities are more than the existing irrigation intensity.     

基于微粒群优化算法的水轮机调节系统最优参数整定

（PSO）算法是一种随机全局优化技术，该算法简单、容易实现，且功能强大。文中研究了水轮机PID调节器参数的优化问题，利用PSO算法对系统所处的不同状态和工况进行了PID参数寻优。仿真结果表明，此种PID控制器比常规PID有更好的动态调节性能和鲁棒性，不失为一种具有较好实用价值的PID参数优化方法。     

Fuzzy Systems Tuned By Swarm Based Optimization Algorithms for Predicting Stream flow

River flow prediction is an important phenomenon in water resources for which different methods and perspective have been used. Using fuzzy system with black box perspective is one of them. Fuzzy systems have some parameters and properties that have to be determined. This is an optimization problem that can be solved by swarm optimization techniques among several techniques. Swarm optimization are developed by inspiring from the behavior of the animals living as swarm. The study presents two achievements fuzzy system that tuned by swarm optimization algorithms can be used for prediction of monthly mean streamflow and which swarm optimization algorithm is better than the others for tuning fuzzy systems. Three swarm optimization algorithms, hunter search, firefly, artificial bee colony are used in this study. These algorithms are compared with mean performance values and convergence speed. Monthly streamflow data of three stream gauging stations in Susurluk Basin are used for the case study. The results show, swarm optimization algorithms can be used for prediction of monthly mean streamflow and ABC algorithm has better performance values than other optimization algorithms.     

New Approach for Sediment Yield Forecasting with a Two-Phase Feedforward Neuron Network-Particle Swarm Optimization Model Integrated with the Gravitational Search Algorithm

Water Resources Management - Predicting sediment yield is an important task for decision-makers in environmental monitoring and water management since the benefits of applying non-linear,...     

A Novel Hybrid Decompose-Ensemble Strategy with a VMD-BPNN Approach for Daily Streamflow Estimating

Streamflow estimation is highly significant for water resource management. In this work, we improve the accuracy and stability of streamflow estimation through a novel hybrid decompose-ensemble model that employs variational mode decomposition (VMD) and back-propagation neural networks (BPNN). First, the latest decomposition algorithm, namely, VMD, was used to extract multiscale features that were subsequently learned and ensembled by the BPNN model to obtain the final estimate streamflow results. The historical daily streamflow series of Laoyukou and Wushan hydrological stations in China were analysed by VMD-BPNN, by a single GBRT and BPNN model, ensemble empirical mode decomposition (EEMD) models. The results confirmed that the VMD outperformed a single-estimation model without any decomposition and EEMD-based models; moreover, ensemble estimations using the BPNN model development technique were consistently better than a general summation method. The VMD-BPNN model’s estimation performance was superior to that of five other models at the Wushan station (GBRT, BPNN, EEMD-BPNN-SUM, VMD-BPNN-SUM, and EEMD-BPNN) using evaluation criteria of the root-mean-square error (RMSE?=?2.62 m³/s), the Nash–Sutcliffe efficiency coefficient (NSE?=?0. 9792) and the mean absolute error (MAE?=?1.38 m³/s). The proposed model also had a better performance in estimating higher-magnitude flows with a low criterion for MAE. Therefore, the hybrid VMD-BPNN model could be applied as a promising approach for short-term streamflow estimating.

     

Symbolic Regression Equations for Calculating Daily Reference Evapotranspiration with the Same Input to Hargreaves-Samani in Arid China

To present an alternative simple equation for reference evapotranspiration (ET _o) estimation, the symbolic regression (SR) method was applied to establish equations with the same inputs to simple Hargreaves-Samani (HS) equation in arid China. For most of the equations derived by SR method for each station, their performance increased with an increase in the equation complex index (CI). The most precise equation performed well although it was always complex and greatly varied in form. On the other hand, the simplest one was uniform in equation structure and performed slightly better than the HS equation for all the five stations, and sometimes better than the local calibrated HS equation. A trade-off equation was selected with almost the same equation form for all the five stations and low CI index. The site-specific trade-off equation performed better than the simplest one and the locally calibrated HS equation. Then parameters in the trade-off equation were unified for all the five stations, it did not perform as good as the site-specific one, but performed better than the HS equation and unified local calibrated HS equation. Thus, the SR method is suitable to determine both the site-specific and the unified equation among stations for daily ET _o calculation in arid regions.     

Establishing Reference Conditions for Lake Water Quality: A Novel Extrapolation Approach

The serious lake eutrophication has drawn increasingly attention, requiring further and deeper knowledge to understand its restriction factors of pre-disturbance conditions or historical reference conditions. In the meanwhile, Lake Nutrient Reference Conditions (LNRCs) are important indicators of eutrophication but hardly determined in the presence of eutrophication. In this research, a novel extrapolation approach was raised to determine LNRCs and its impacts on eutrophication, with the integral model of Optimal Map Recognition (OMR) and Pattern Recognition Inverse Mapping (PRIM). Validated with public data and experimental simulation, the approach was suggested as a reliable extrapolation for LNRCs determination. Further case study on Dianshan Lake and Chenghai Lake applied the novel extrapolation model in real eutrophication estimation and prediction, the results of which were in good agreement with those deduced by other techniques.     

A Novel Adaptive Multi-Objective Particle Swarm Optimization Based on Decomposition and Dominance for Long-term Generation Scheduling of Cascade Hydropower System

Water Resources Management - Multi-objective long-term generation scheduling (MLGS) considering ecological flow demands is important for comprehensive utilization of water resources in cascade...     

A Particle Swarm Optimization Assessment for the Determination of Non-Darcian Flow Parameters in a Confined Aquifer

Being one of the preliminary in-situ testing methods, aquifer pumping tests would provide significant insights which form a basis for the aquifer characterization. The use of Darcian based flow models to describe the groundwater flow would be ineffective for the aquifer pumping tests under certain circumstances. Non-Darcian flow models could therefore construct more accurate portrayal of physical reality for the assessment of aquifer testing. The interpretation of flow parameters obtained from non-Darcian flows via classical curve matching methods seems extremely difficult to acquire a unique match since the well-defined type curves have not been developed. In this study, an evolutionary optimization based algorithm, called as Particle Swarm Optimization (PSO), was established to determine the flow parameters namely power index, storativity and the turbulent factor which serves as an apparent hydraulic conductivity. The proposed PSO based parameter estimation scheme was implemented for a number of numerical test cases and the estimation performance was evaluated by comparing with available population based algorithms. The results reveal that the PSO based estimation approach is successfully able to identify the flow parameters in an accurate and fast manner. A number of sensitivity analyses were also conducted to draw the limitations of the introduced PSO based technique. The positive findings from this study pointed the potential capability of using PSO as a viable algorithm to process the complex relations in the flow.

     

New Approach: Integrated Risk-Stochastic Dynamic Model for Dam and Reservoir Optimization

Multiple studies have developed management models to identify optimal operating policies for reservoirs in the last four decades. In an uncertain environment, in which climatic factors such as stream flow are stochastic, the economic returns from reservoir releases that are based on policy are uncertain. Furthermore, the consequences of reservoir release are not fully realized until it occurs. Rather than explicitly recognizing the full spectrum of consequences that are possible within an uncertain environment, the existing optimization models have focused on addressing these uncertainties by identifying the release policies that optimize the summative metric of the risks that are associated with release decisions. This technique has limitations for representing risks that are associated with release policy decisions. In fact, the approach of these techniques may conflict with the actual attitudes of the decision-makers regarding the risk aspects of release policies. The risk aspects of these decisions affect the design and operation of multi-purpose reservoirs. A method is needed to completely represent and evaluate potential consequences that are associated with release decisions. In this study, these techniques were reviewed from the stochastic model and risk analysis perspectives. Therefore, previously developed optimization models for operating dams and reservoirs were reviewed based on their advantages and disadvantages. Specifically, optimal release decisions that use the stochastic variable impacts and the levels of risk that are associated with decisions were evaluated regarding model performance. In addition, a new approach was introduced to develop an optimization model that is capable of replicating the manner in which reservoir release decision risks are perceived and interpreted. This model is based on the Neural Network (NN) theory and enables a more complete representation of the risk function that occurs from particular reservoir release decisions.     

Performance Assessment of a Coupled Particle Swarm Optimization and Network Flow Programming Model for Optimum Water Allocation

Water resources allocation problems are mainly categorized in two classes of simulation and optimization. In most cases, optimization problems due to the number of variables, constraints and nonlinear feasible search space are known as a challenging subject in the literature. In this research, by coupling particle swarm optimization (PSO) algorithm and a network flow programming (NFP) based river basin simulation model, a PSO-NFP hybrid structure is constructed for optimum water allocation planning. In the PSO-NFP model, the NFP core roles as the fast inner simulation engine for finding optimum values for a large number of water discharges in the network links (rivers and canals) and nodes (reservoirs and demands) while the heuristic PSO algorithm forms the outer optimization cover to search for the optimum values of reservoirs capacities and their storage priorities. In order to assess the performance of the PSO-NFP model, three hypothetical test problems are defined, and their equivalent nonlinear mathematical programs are developed in LINGO and the results are compared. Finally, the PSO-NFP model is applied in solving a real river basin water allocation problem. Results indicate that the applied method of coupling PSO and NFP has an efficient ability for handling river basin-scale water resources optimization problems.     

Daily Reference Evapotranspiration for Hyper-Arid to Moist Sub-Humid Climates in Inner Mongolia,China: I. Assessing Temperature Methods and Spatial Variability

When weather data sets available for computing the reference evapotranspiration are incomplete or of questionable quality, there is the need to replace the FAO Penman-Monteith (PM-ET_o) method by approaches requiring reduced sets only, particularly maximum and minimum temperature. The Hargreaves-Samani (HS) equation and the PM-ET_o using only temperature data (PMT) are considered in this study and their results are compared with those of the PM-ET_o using full datasets. Daily data sets refer to the period 1981–2012 and to a network of 50 meteorological stations covering the wide range of climates of Inner Mongolia. For both the PMT and HS methods, the solar radiation coefficients k_Rs were calibrated and have shown to be similar for both methods and to vary with climate aridity. For the PMT, the estimation of the dew point temperature (T_dew) was performed using the minimum temperature corrected for site aridity or, for humid climates, from a value near the average temperature. This improved estimation of T_dew was essential for a good performance of the PMT method in arid conditions and when temperatures are extremely low. RMSE <1 mm day^?1 was obtained for both HS and PMT methods, and the modeling efficiency generally exceeded 0.85. The worse results correspond to windy and arid locations. The principal components analysis (PCA) in R-Mode have shown that the spatial variability of ET_o computed with PM-ET_o or with the HS and PMT methods were coherent. PCA supported the interpretation of ET_o results. Overall, PMT performed better than HS for most locations.     

Rainfall Extremes: a Novel Modeling Approach for Regionalization

The rainfall events of extreme magnitude over the past few decades have caused destructive damages to lives and properties, especially in the subcontinent (e.g. Pakistan, India, Bangladesh etc). Rainfall hazard maps for these areas can be of great practical and theoretical interests. In our work, we used extreme value analysis and spatial interpolation techniques to provide such maps through a combination of the Tropical Rainfall Measuring Mission Precipitation (TRMM) 3B42 product and raingauge data. This mixed approach takes advantage of both the long time series available at a limited number of stations, and the large spatial coverage of the satellite data which, instead, has a poor temporal extent. The methodology is implemented by (1) creating a unique growth curve for the homogeneous region by utilizing in-situ rainfall data and (2) mapping the parameters of intensity-duration functions for the entire length of the study area by using TRMM 3B42 product. The regional results obtained by using mixed approach and TRMM 3B42 are compared with the estimates obtained by using in-situ data. The comparison showed that the overall output of mixed approach is more consistent with what transpired by in-situ data for a pre-defined return period.     

Particle Swarm Optimization for Automatic Calibration of Large Scale Water Quality Model (CE-QUAL-W2): Application to Karkheh Reservoir,Iran

An automatic calibration of water quality model is developed in this research. Automatic calibration as the process to determine the parameters appearing in the equations of a 2-dimensional, hydrodynamic, and water quality models (CE-QUAL-W2) is carried out with Particle Swarm technique as an optimization tool. In the calibration of the CE-QUAl-W2 model, evaporation as a significant parameter influences the thermal profile and water surface elevation in reservoir, simultaneously. Therefore to consider the simultaneous effects of the water temperature variations on water surface elevation in the reservoir, a multi objective technique is used to minimize the weighted sum of total deviations of temperature from field data at check points on monitoring days and those of water surface elevation on daily monitoring period. The proposed approach overcomes the high computational efforts required if a conventional calibration search technique was used, while retaining the quality of the final calibration results. The automatic calibration approach is applied in temperature and water budget calibration of Karkheh reservoir in Iran. Applying the proposed automatic calibration approach, shows the produced results by the CE-QUAL-W2 model with the calibrated coefficients agree closely with a set of field data.     

Pressure Zoning Approach for Leak Detection in Water Distribution Systems Based on a Multi Objective Ant Colony Optimization

Leakages result in considerable loss of water in water pipe networks. Therefore it is an important issue to detect leakage amount and its approximate location. Leakages in water distribution system are directly related to the operating pressure. In the current study, a new model is proposed for leakage amount and location detection and it is applied into two benchmark water distribution networks. In the proposed method, the water distribution networks are divided into three pressure zones in order to consider the leakage differences in different operating pressures. Then, nodal pressures and demands are calibrated using a new multi objective ant colony based optimization model. In this method, leaks are simulated as extra nodal demands. For determining the nodes where leakage happens, a probability based scheme is used. The leakage occurrence probability varies depending on the pressure zone that each node is located. The results illustrate the applicability of the proposed model for detecting the leakages in water distribution systems.     

A Novel Approach for Prediction of Monthly Ground Water Level Using a Hybrid Wavelet and Non-Tuned Self-Adaptive Machine Learning Model

Water Resources Management - In recent decades, due to groundwater withdrawal in the Kabodarahang region, Iran, Hamadan, hazardous events such as sinkholes, droughts, water scarcity, etc., have...     

Application of a Simple Raster-Based Hydrological Model for Streamflow Prediction in a Humid Catchment with Polder Systems

The hydrological processes are controlled by many factors such as topography, soil, climate and land management practices. These factors have been included in most hydrological models. This study develops a raster-based distributed hydrological model for catchment runoff simulation integrating flood polders regulation. The overland flow and channel flow are calculated by kinematic wave equations. A simple bucket method is used for outflow estimation of polders. The model was applied to Xitiaoxi catchment of Taihu Lake Basin. The accuracy of the model was satisfactory with Nash–Sutcliffe efficiencies of 0.82 during calibration period and 0.85 for validation at Hengtangcun station. The results at Fanjiacun station are slightly worse due to the tidal influence of Taihu Lake with high values of root mean square errors. A model sensitivity analysis has shown that the ratio of potential evapotranspiration to pan evaporation (K), the outflow coefficients of the freewater storage to groundwater (KG) and interflow (KSS) and the areal mean tension water capacity (WM) were the most sensitive parameters. The simulation results indicate that the polder systems could reduce the flood peaks. Additionally, it was confirmed that the proposed polders operation method improved the accuracy of discharge simulation slightly.     

Daily Reference Evapotranspiration for Hyper-Arid to Moist Sub-Humid Climates in Inner Mongolia,China: II. Trends of ET<Subscript>o</Subscript> and Weather Variables and Related Spatial Patterns

This study focuses on assessing trends of reference evapotranspiration (ET_o) considering aridity. Weather data sets of 54–62 years of Inner Mongolia, a Chinese Province where climate varies from hyper-arid in the West to wet sub-humid in the East, were used. Trends were analyzed for ET_o computed with the FAO Penman-Monteith method (PM-ET_o) using full data sets of maximum and minimum temperature (T_max and T_min), sunshine duration (SD) used to compute net radiation, relative humidity (RH) and wind speed (WS). Trends were also assessed for ET_o computed with the Hargreaves-Samani temperature eq. (ET_{o HS}) and the Penman-Monteith equation with temperature estimates of solar radiation and actual vapour pressure (ET_{o PMT}). In addition, trends relative to T_max, T_min, SD, RH and WS were assessed. Trends for PM-ET_o show to vary with aridity, with decreasing trends in the areas marked by aridity in the West and increased trends in less arid and sub-humid areas in the East. The detected trends are well explained by the trends in weather variables which consist of large increasing trends of T_max and T_min and of decreasing trends for SD, RH and WS. Therefore, negative trends of ET_o occur where impacts of increases in temperature and decreases in RH are smaller than impacts of declining SD and WS; otherwise, when warming influences are larger it results a positive trend for ET_o. Trends were coherent when considering seasonality influences. Contrarily, results for the temperature methods, ET_{o PMT} and ET_{o HS,} always identified increased trends for ET_o due to warming effects. These results show that it is inappropriate to assess ET_o trends when using simplified temperature methods.     

A Novel Approach Using Hybrid Fuzzy Vertex Method-MATLAB Framework Based on GMS Model for Quantifying Predictive Uncertainty Associated with Groundwater Flow and Transport Models

Identification of the uncertain parameters, which affecting on the qualitative behavior of the aquifer, and determining their effect on the uncertainty of the simulated nitrate concentration (NC) is one of the major challenges in the qualitative monitoring of aquifers. In this study, in order to determine the quantitative amount of uncertainty related to the simulated nitrate, an approach based on a hybrid of Groundwater Modeling System (GMS) model and Fuzzy Vertex Method (FVM) method was developed using the developed code for the relationship between aquifer simulation model and MATLAB environment. In this model, hydraulic conductivity, NC in aquifer recharge sources, longitudinal dispersivity coefficient, and specific storage parameters were considered as uncertain parameters in the distributed simulation model of the Ardabil aquifer. In the proposed approach, first the quantitative and qualitative (QQ) model of the aquifer was prepared using the GMS model and calibrated. Then, using the FVM method and developed MATALB code, the uncertain values appropriate for each of the aquifer active cells were determined. The results obtained from the monthly NC uncertainty show that with increasing the level of uncertainty, the uncertainty of the simulated NC increases significantly. For example, can be mentioned a 14-fold increase in the number of cells with variation of NC less than 10% in the September month. Also, the lowest and highest variation in the deterministic amount of NC is related to the months of Nov. and Sep. with concentration variations equal to [??8.5, 8.35] and [??23.43, 19.8] mg/L, respectively. The findings of this study show that the application of at least 10% uncertainty in the deterministic values of the simulated NC is necessary to provide a suitable view for quality monitoring of aquifer. A quantitative amount of monthly uncertainty in areas with nitrate concentrations greater than 50 mg/L indicates that the amount of uncertainty in these areas is higher than areas with nitrate concentrations less than 50 mg/L. This leads to errors in the monitoring of contaminated areas to eliminate contamination and quality restoration. Also, centralization of uncertainty is mainly concentrated in the northeastern, western and southwestern parts of Ardabil plain and the severity of uncertainty in the mentioned areas increases with the intensification of uncertainty and continues to the central areas. Finally, it must be said that hydraulic conductivity and NC in aquifer recharge sources, respectively, play the most important role in creating uncertainty and is necessary to be considered in the NC simulation models.