Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network

Developing water level forecasting models is essential in water resources management and flood prediction. Accurate water level forecasting helps achieve efficient and optimum use of water resources and minimize flooding damages. The artificial neural network (ANN) is a computing model that has been successfully tested in many forecasting studies, including river flow. Improving the ANN computational approach could help produce accurate forecasting results. Most studies conducted to date have used a sigmoid function in a multi-layer perceptron neural network as the basis of the ANN; however, they have not considered the effect of sigmoid steepness on the forecasting results. In this study, the effectiveness of the steepness coefficient (SC) in the sigmoid function of an ANN model designed to test the accuracy of 1-day water level forecasts was investigated. The performance of data training and data validation were evaluated using the statistical index efficiency coefficient and root mean square error. The weight initialization was fixed at 0.5 in the ANN so that even comparisons could be made between models. Three hundred rounds of data training were conducted using five ANN architectures, six datasets and 10 steepness coefficients. The results showed that the optimal SC improved the forecasting accuracy of the ANN data training and data validation when compared with the standard SC. Importantly, the performance of ANN data training improved significantly with utilization of the optimal SC.     

Hybrid ANN–GA model for predicting turbidity and chlorophyll-a concentrations

The transport and fate of admixtures at coastal zones are driven, or at least modulated, by currents. In particular, in tide-dominated areas due to higher near-bottom shear stress at strong currents, sediment concentration and turbidity are expected to be at maximum during spring tide, while algal growth rate likely is peaking up at slack currents during neap tide. Varying weather and atmospheric conditions might modulate the said dependencies, but the water quality pattern still is expected to follow the dominant tidal cycle. As tidal cycling could be predicted well ahead, there is a possibility to use water quality and hydrodynamic high-resolution data to learn past dependencies, and then use tidal hydrodynamic model for nowcasting and forecasting of selected water quality parameters.This paper develops data driven models for nowcasting and forecasting turbidity and chlorophyll-a using Artificial Neural Network (ANN) combined with Genetic Algorithm (GA). The use of GA aims to automate and enhance ANN designing process. The training of the ANN model is done by constructing input–output mapping, where hydrodynamic parameters act as an input for the network, while turbidity and chlorophyll-a are the corresponding outputs (desired target). Afterward, the prediction is carried out only by employing computed water surface elevation as an input for the trained ANN model. The proposed data driven model has successfully revealed complex relationships and utilized its experiential knowledge acquired from the training process for facilitating the subsequent use of the data driven model to yield an accurate prediction.     

Measurement and mathematical modelling of nutrient level and water quality parameters

Physico-chemical water quality parameters and nutrient levels such as water temperature, turbidity, saturated oxygen, dissolved oxygen, pH, chlorophyll-a, salinity, conductivity, total nitrogen and total phosphorus, were measured from April to September 2011 in the Karaj dam area, Iran. Total nitrogen in water was modelled using an artificial neural network system. In the proposed system, water temperature, depth, saturated oxygen, dissolved oxygen, pH, chlorophyll-a, salinity, turbidity and conductivity were considered as input data, and the total nitrogen in water was considered as output. The weights and biases for various systems were obtained by the quick propagation, batch back propagation, incremental back propagation, genetic and Levenberg-Marquardt algorithms. The proposed system uses 144 experimental data points; 70% of the experimental data are randomly selected for training the network and 30% of the data are used for testing. The best network topology was obtained as (9-5-1) using the quick propagation method with tangent transform function. The average absolute deviation percentages (AAD%) are 2.329 and 2.301 for training and testing processes, respectively. It is emphasized that the results of the artificial neural network (ANN) model are compatible with the experimental data.     

Intermittent Streamflow Forecasting and Extreme Event Modelling using Wavelet based Artificial Neural Networks

Forecasting of intermittent stream flow is necessary for water resource planning and management at catchment scale. Forecasting of extreme events and events outside the range of training data used for artificial neural network (ANN) model development has been a major bottleneck in their generalization capabilities till date. Despite of several studies using wavelet analysis in water resource modelling, no study has yet been conducted to explore capabilities of hybrid ANN modelling techniques for extreme events outside the training range. In this study a wavelet based ANN model (WANN) is proposed for intermittent streamflow forecasting and extreme event modelling. This study is carried out in a watershed in semi arid middle region of Gujarat, India. 6 years of hydro-climatic data are used in this study. 4 years of data are used for model training, 1 year for cross-validation and remaining 1 year data are used to evaluate the effectiveness of the WANN model. Two different approaches of data arrangement are considered in this study, in one approach testing data are within the range of training dataset, whereas in another approach testing data are outside the training dataset range. Performance of four different training algorithms and different types of wavelet functions are also evaluated for WANN model development. In this study it is found that WANN model performed significantly better than standard ANN models. It is observed in this study that different wavelet functions have different role in modelling complexities of normal and extreme events. WANN model simulated peak values very well and it shows that WANN model has the potential to be applied successfully for intermittent streamflow forecasting even for the data outside the training range and for extreme events.     

输水线路旁侧出流预测的数值研究

调水、引水工程沿线非计划用水的评估计算及控制是受水区能否得到足够水量的关键问题。选取南水北调工程苏北江都至淮安调水线路进行数值试验,采用神经网络技术预测非计划旁侧出流,探讨该技术的精度和可靠性。根据数值实验的结果,和传统水力学方法的计算结果相比较,神经网络模型的预测、预报精度较高,但用于实际预测还需实测数据作进一步验证。     

Prediction of scour below submerged pipeline crossing a river using ANN

The process involved in the local scour below pipelines is so complex that it makes it difficult to establish a general empirical model to provide accurate estimation for scour. This paper describes the use of artificial neural networks (ANN) to estimate the pipeline scour depth. The data sets of laboratory measurements were collected from published works and used to train the network or evolve the program. The developed networks were validated by using the observations that were not involved in training. The performance of ANN was found to be more effective when compared with the results of regression equations in predicting the scour depth around pipelines.     

Applications of Artificial Neural Networks in integrated water management: fiction or future?

An Artificial Neural Network (ANN) is nowadays recognized as a very promising tool for relating input data to output data. It is said that the possibilities of artificial neural networks are unlimited. Here we focus on the potential role of neural networks in integrated water management. An Artificial Neural Network (ANN) is a mathematical methodology which describes relations between cause (input data) and effects (output data) irrespective of the process laying behind and without the need for making assumptions considering the nature of the relations. The applications are widespread and vary from optimization of measuring networks, operational water management, prediction of drinking water consumption, on-line steering of wastewater treatment plants and sewage systems, up to more specific applications such as establishing a relationship between the observed erosion of groyne field sediments and the characteristics of passing vessels on the river Rhine. Especially where processes are complex, neural networks can open new possibilities for understanding and modelling these kinds of complex processes. Besides explaining the method of ANN this paper shows different applications. Three examples have been worked out in more detail. An intelligent monitoring system is shown for the on-line prediction of water consumption, ANN are successfully used for sludge cost monitoring and optimizing wastewater treatment and the usage of ANN is shown in optimizing and monitoring water quality measuring networks. An ANN appears to be a multiuse and powerful tool for modelling complex processes.     

Applying Genetic Algorithm and Neural Network to the Conjunctive Use of Surface and Subsurface Water

The conjunctive use of surface and subsurface water is one of the most effective ways to increase water supply reliability with minimal cost and environmental impact. This study presents a novel stepwise optimization model for optimizing the conjunctive use of surface and subsurface water resource management. At each time step, the proposed model decomposes the nonlinear conjunctive use problem into a linear surface water allocation sub-problem and a nonlinear groundwater simulation sub-problem. Instead of using a nonlinear algorithm to solve the entire problem, this decomposition approach integrates a linear algorithm with greater computational efficiency. Specifically, this study proposes a hybrid approach consisting of Genetic Algorithm (GA), Artificial Neural Network (ANN), and Linear Programming (LP) to solve the decomposed two-level problem. The top level uses GA to determine the optimal pumping rates and link the lower level sub-problem, while LP determines the optimal surface water allocation, and ANN performs the groundwater simulation. Because the optimization computation requires many groundwater simulations, the ANN instead of traditional numerical simulation greatly reduces the computational burden. The high computing performance of both LP and ANN significantly increase the computational efficiency of entire model. This study examines four case studies to determine the supply efficiencies under different operation models. Unlike the high interaction between climate conditions and surface water resource, groundwater resources are more stable than the surface water resources for water supply. First, results indicate that adding an groundwater system whose supply productivity is just 8.67 % of the entire water requirement with a surface water supply first (SWSF) policy can significantly decrease the shortage index (SI) from 2.93 to 1.54. Second, the proposed model provides a more efficient conjunctive use policy than the SWSF policy, achieving further decrease from 1.54 to 1.13 or 0.79, depending on the groundwater rule curves. Finally, because of the usage of the hybrid framework, GA, LP, and ANN, the computational efficiency of proposed model is higher than other models with a purebred architecture or traditional groundwater numerical simulations. Therefore, the proposed model can be used to solve complicated large field problems. The proposed model is a valuable tool for conjunctive use operation planning.     

River Flow Forecasting using Recurrent Neural Networks

Forecasting a hydrologic time series has been one of the most complicated tasks owing to the wide range of data, the uncertainties in the parameters influencing the time series and also due to the non availability of adequate data. Recently, Artificial Neural Networks (ANNs) have become quite popular in time series forecasting in various fields. This paper demonstrates the use of ANNs to forecast monthly river flows. Two different networks, namely the feed forward network and the recurrent neural network, have been chosen. The feed forward network is trained using the conventional back propagation algorithm with many improvements and the recurrent neural network is trained using the method of ordered partial derivatives. The selection of architecture and the training procedure for both the networks are presented. The selected ANN models were used to train and forecast the monthly flows of a river in India, with a catchment area of 5189 km² up to the gauging site. The trained networks are used for both single step ahead and multiple step ahead forecasting. A comparative study of both networks indicates that the recurrent neural networks performed better than the feed forward networks. In addition, the size of the architecture and the training time required were less for the recurrent neural networks. The recurrent neural network gave better results for both single step ahead and multiple step ahead forecasting. Hence recurrent neural networks are recommended as a tool for river flow forecasting.     

Artificial Neural Network (ANN) Based Modeling for Karstic Groundwater Level Simulation

A relatively new method of addressing different hydrological problems is the use of artificial neural networks (ANN). In groundwater management ANNs are usually used to predict the hydraulic head at a well location. ANNs can prove to be very useful because, unlike numerical groundwater models, they are very easy to implement in karstic regions without the need of explicit knowledge of the exact flow conduit geometry and they avoid the creation of extremely complex models in the rare cases when all the necessary information is available. With hydrological parameters like rainfall and temperature, as well as with hydrogeological parameters like pumping rates from nearby wells as input, the ANN applies a black box approach and yields the simulated hydraulic head. During the calibration process the network is trained using a set of available field data and its performance is evaluated with a different set. Available measured data from Edward??s aquifer in Texas, USA are used in this work to train and evaluate the proposed ANN. The Edwards Aquifer is a unique groundwater system and one of the most prolific artesian aquifers in the world. The present work focuses on simulation of hydraulic head change at an observation well in the area. The adopted ANN is a classic fully connected multilayer perceptron, with two hidden layers. All input parameters are directly or indirectly connected to the aquatic equilibrium and the ANN is treated as a sophisticated analogue to empirical models of the past. A correlation analysis of the measured data is used to determine the time lag between the current day and the day used for input of the measured rainfall levels. After the calibration process the testing data were used in order to check the ability of the ANN to interpolate or extrapolate in other regions, not used in the training procedure. The results show that there is a need for exact knowledge of pumping from each well in karstic aquifers as it is difficult to simulate the sudden drops and rises, which in this case can be more than 6 ft (approx. 2 m). That aside, the ANN is still a useful way to simulate karstic aquifers that are difficult to be simulated by numerical groundwater models.     

Deriving Hedging Rules of Multi-Reservoir System by Online Evolving Neural Networks

This paper presents an online optimization scheme for combined use of Artificial Neural Networks (ANN), hedging policies and harmony search algorithm (HS) in developing optimum operating policies for Tehran water resources system. Past efforts in this area are concentrated on using an offline approach. In that approach, an optimization method is first used to derive a long-term set of optimum reservoir releases. These releases are then used as the target vector for training the ANN model. The online method simultaneously uses the optimization and ANN methods and can adopt objective functions other than minimizing the error indices. Therefore, it requires methods other than the backpropagation for training the ANN model. Hence, under the proposed online approach the application of a heuristic method, such as HS, is inevitable for training the network. This is accomplished by using an optimization-simulation procedure where different objective functions and system constraints could be easily handled. The proposed approach is a novel and efficient method for finding the parameters of hedging policies where earlier methods suffered from high computational costs and the curse of dimensionality. The results show the superiority of the proposed online scheme. Moreover, a surrogate model for the hedging policy is presented, which by adhering to the principle of parsimony is more efficient in large scale systems involving many decision variables.     

Review and assessment of water resources in Gulf cooperation council countries

The water resources of the Gulf Cooperating Council (GCC) countries are considered to be of equal importance to their oil resources. This paper takes a brief look at the current situation concerning the water‐related problems encountered by the GCC countries, the availability and use of water in these countries and then presents estimates of future requirements. In conclusion, a number of suggestions are proposed for the GCC countries which will affect water management actions that attempt to balance water availability and demand. These actions range from improving institutional arrangements, training and data management to the development of a cooperative long‐term water management plan.     

A Wavelet-ANFIS Hybrid Model for Groundwater Level Forecasting for Different Prediction Periods

Artificial neural network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) have an extensive range of applications in water resources management. Wavelet transformation as a preprocessing approach can improve the ability of a forecasting model by capturing useful information on various resolution levels. The objective of this research is to compare several data-driven models for forecasting groundwater level for different prediction periods. In this study, a number of model structures for Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Wavelet-ANN and Wavelet-ANFIS models have been compared to evaluate their performances to forecast groundwater level with 1, 2, 3 and 4 months ahead under two case studies in two sub-basins. It was demonstrated that wavelet transform can improve accuracy of groundwater level forecasting. It has been also shown that the forecasts made by Wavelet-ANFIS models are more accurate than those by ANN, ANFIS and Wavelet-ANN models. This study confirms that the optimum number of neurons in the hidden layer cannot be always determined by using a specific formula but trial-and-error method. The decomposition level in wavelet transform should be determined according to the periodicity and seasonality of data series. The prediction of these models is more accurate for 1 and 2 months ahead (for example RMSE?=?0.12, E?=?0.93 and R ²?=?0.99 for wavelet-ANFIS model for 1 month ahead) than for 3 and 4 months ahead (for example RMSE?=?2.07, E?=?0.63 and R ²?=?0.91 for wavelet-ANFIS model for 4 months ahead).     

Socio-Economic Impact of Evaporation Losses from Reservoirs Under Past, Current and Future Water Availability Scenarios in the Semi-Arid Segura Basin

This study assesses evaporation losses from water reservoirs in the semi-arid Segura basin (south-east Spain), one of the most water stressed European catchments. These losses are evaluated from both the hydrologic and economic perspectives under different water availability scenarios that are based on water policy trends and climate change predictions. We take a multidisciplinary approach to the analysis, combining energy balance models to assess the effect of climate change on evaporation from water bodies, Class-A pan data and pan coefficients to determine evaporation loss on a regional scale, and non-linear mathematical programming modelling to simulate the economic impact of water use and allocation in the basin. Our results indicate that water availability could be reduced by up to 40 % in the worst-case scenario, with an economic impact in the 32–36 % range, depending on the indicator in question. The total annual evaporation loss from reservoirs ranges from 6.5 % to 11.7 % of the water resources available for irrigation in the basin, where evaporation from small reservoirs is more than twice that from large dams. The economic impact of such losses increases with water scarcity, ranging from 4.3 % to 12.3 % of the value of agricultural production, 4.0 % to 12.0 % of net margin, 5.8 % to 10.7 % of the irrigated area, and 5.4 % to 13.5 % of agricultural employment. Results illustrate the importance of evaporation losses from reservoirs in this region and the marked upward trend for future scenarios. Besides, they highlight the extent of the impact of climate change on future water resources availability and use in southern Europe.     

Wavelet Regression Model as an Alternative to Neural Networks for River Stage Forecasting

River stage forecasting is an important issue in water resources management and real-time prediction of extreme floods. The present study investigates the performance of the wavelet regression (WR) technique in daily river stage forecasting. The WR model was improved combining two methods, discrete wavelet transform and a linear regression model. Two different WR models were developed using the stage sub-time series, and these were compared with each other. The data from two stations on the Schuylkill River in Philadelphia were used. The root mean square errors (RMSE), mean absolute errors (MAE) and correlation coefficient (R) statistics were used for evaluating the accuracy of the WR models. The accuracy of the WR models was then compared with those of the artificial neural networks (ANN) models. Based on a comparison of these results, the WR models were found to perform better than the ANN models. For the upstream and downstream stations, it was found that the WR models with upstream readings of with RMSE = 0.070, MAE = 0.027, R = 0.937 and with downstream readings of RMSE = 0.048, MAE = 0.024, R = 0.969 in the validation stage performed better in forecasting daily river stages than the best accurate ANN models with upstream readings of RMSE = 0.168, MAE = 0.052, R = 0.802 and with downstream readings of RMSE = 0.115, MAE = 0.051, R = 0.807, respectively.     

Optimizing Operation Rules of Sluices in River Networks Based on Knowledge-driven and Data-driven Mechanism

Many river networks are controlled by sluices, especially in plain area. To prevent potential floods, maintain water level, and improve water environment in the inner river, the water transfer of river networks is needed and executed often in terms of optimized operation rules of sluices planned in advancing. To guarantee maintaining the optimized operation status, the provision of appropriate operating framework of sluices in river networks is necessary and presented in this study based on the knowledge-driven and data-driven mechanism. The general framework is formed by River Networks Mathematical Model (RNMM), Artificial Neural Networks (ANN) and Genetic Algorithms (GA), in which, ANN is used to build a rapid simulation of the flow variables in river networks, RNMM is used to train the ANN model, and GA method, whose fitness function is constructed by the ANN model, is used to optimize the operation rules of sluices. As a demonstration, the framework was applied to water transfer project of the tidal river networks locating in Pudong New Area of Shanghai in mainland China. Firstly, RNMM of Pudong was built and validated according to observed data during water transfer tests. Then, the Backward Propagation Neural Networks (BPNN) model was established as the fast simulation tool of flow variables of river networks through the numerical experiments with RNMM. The Generalized Genetic Algorithms (GGA) was recommended as optimization algorithm of sluices operation rules. Through comparing the optimization results with the RNMM simulation outputs under eight cases, it is verified that the framework can offer sub-optimal operation rules of sluices in river networks and present excellent speediness, robustness and flexibility. It is encouraged to be applied to more complicated, practical problems.     

Artificial Neural Network Modeling for Groundwater Level Forecasting in a River Island of Eastern India

Forecasting of groundwater levels is very useful for planning integrated management of groundwater and surface water resources in a basin. In the present study, artificial neural network models have been developed for groundwater level forecasting in a river island of tropical humid region, eastern India. ANN modeling was carried out to predict groundwater levels 1 week ahead at 18 sites over the study area. The inputs to the ANN models consisted of weekly rainfall, pan evaporation, river stage, water level in the drain, pumping rate and groundwater level in the previous week, which led to 40 input nodes and 18 output nodes. Three different ANN training algorithms, viz., gradient descent with momentum and adaptive learning rate backpropagation (GDX) algorithm, Levenberg–Marquardt (LM) algorithm and Bayesian regularization (BR) algorithm were employed and their performance was evaluated. As the neural network became very large with 40 input nodes and 18 output nodes, the LM and BR algorithms took too much time to complete a single iteration. Consequently, the study area was divided into three clusters and the performance evaluation of the three ANN training algorithms was done separately for all the clusters. The performance of all the three ANN training algorithms in predicting groundwater levels over the study area was found to be almost equally good. However, the performance of the BR algorithm was found slightly superior to that of the GDX and LM algorithms. The ANN model trained with BR algorithm was further used for predicting groundwater levels 2, 3 and 4 weeks ahead in the tubewells of one cluster using the same inputs. It was found that though the accuracy of predicted groundwater levels generally decreases with an increase in the lead time, the predicted groundwater levels are reasonable for the larger lead times as well.     

Predicting Mean and Bankfull Discharge from Channel Cross-Sectional Area by Expert and Regression Methods

This study employed four methods—non-linear regression, fuzzy logic (FL), artificial neural networks (ANNs), and genetic algorithm (GA)-based nonlinear equation—for predicting mean discharge and bank-full discharge from cross-sectional area. The data compiled from the literature were separated into two groups—training (calibration) and testing (verification). Using training data sets, the methods were calibrated to obtain optimal values of the coefficients of the non-linear regression method; optimal number of fuzzy subsets, their base widths and fuzzy rules for the fuzzy method; and the optimal number of neurons in the hidden layer, the learning rate and momentum factor values for the ANN model. The GA-based method employed 100 chromosomes in the initial gene pool, 80% cross over rate and 4% mutation rate in determining the optimal values of the coefficients of the constructed nonlinear equation. The calibrated methods were then applied to the test data sets. The test results showed that the non-linear regression, ANN and GA-based methods were comparable in predicting the mean discharge while the fuzzy method produced high errors and low accuracy. The GA-based method had the highest accuracy of 75%. In terms of predicting bankfull discharge, all methods produced satisfactory results, although the fuzzy method had the lowest accuracy of 33%. The results of sensitivity analysis, which is limited to the GA-based and nonlinear regression methods, showed that the GA-based method calibrated with low bankfull discharge values can be successfully applied to predict high bankfull discharge values. This has important implications for predicting bankfull rates at ungauged sites. On the other hand, the sensitivity analysis results also showed that both the non-linear regression and GA-based methods have poor extrapolation capability for predicting mean discharge data.     

Development of Nonlinear Model Based on Wavelet-ANFIS for Rainfall Forecasting at Klang Gates Dam

Rainfall is one of the most complicated effective hydrologic processes in runoff prediction and water management. Artificial neural networks (ANN) have been found efficient, particularly in problems where characteristics of the processes are stochastic and difficult to describe using explicit mathematical models. However, time series prediction based on ANN algorithms is fundamentally difficult and faces some other problems. For this purpose, one method that has been identified as a possible alternative for ANN in hydrology and water resources problems is the adaptive neuro-fuzzy inference system (ANFIS). Nevertheless, the data arising from the monitoring stations and experiment might be corrupted by noise signals owing to systematic and non-systematic errors. This noisy data often made the prediction task relatively difficult. Thus, in order to compensate for this augmented noise, the primary objective of this paper is to develop a technique that could enhance the accuracy of rainfall prediction. Therefore, the wavelet decomposition method is proposed to link to ANFIS and ANN models. In this paper, two scenarios are employed; in the first scenario, monthly rainfall value is imposed solely as an input in different time delays from the time (t) to the time (t-4) into ANN and ANFIS, second scenario uses the wavelet transform to eliminate the error and prepares sub-series as inputs in different time delays to the ANN and ANFIS. The four criteria as Root Mean Square Error (RMSE), Correlation Coefficient (R ²), Gamma coefficient (G), and Spearman Correlation Coefficient (ρ) are used to evaluate the proposed models. The results showed that the model based on wavelet decomposition conjoined with ANFIS could perform better than the ANN and ANFIS models individually.     

Evidence of Land-use Controlled Water Storage Depletion in Hai River Basin,North China

Although critical for human sustenance, irrational land use could cause land resources depletion, environmental degradation, food insecurity and social instability. This study uses Landsat images (06/09/1979 and 12/08/2009) with historical precipitation data (1955–2012) to analyze land use change in relation to surface water storage change in Hai River Basin, North China. Based on analysis in ENVI (Environment for Visualizing Images) and ArcMap, land area under water in 1979 is 1.8 % and that in 2009 is 0.6 % of the 23 826 km² study area. Although the rate of precipitation decline in 1955–2012 is 4.41 mm/year, it is almost the same for 1979 (582 mm) and 2009 (564 mm). This suggests that drought or flooding has no significant effect on the water storage change. For 1979–2009, land area under forest and grass decreases respectively by 54.2 % and 70.7 %. Then that under settlement, farmland and others increases respectively by 64.8 %, 56.0 % and 63.6 %. The loss of land area under water is 64.6 %, which is more the effect of land use change and the related water use in the region. Irrespectively, more water-efficient land use measures could ensure the sustainability and availability of water resources for future use in the predominantly agrarian semiarid region.