In this study, ensemble models using the Bates–Granger approach and least square method are developed to combine forecasts of multi-wavelet artificial neural network (ANN) models. Originally, this study is aimed to investigate the proposed models for forecasting of chlorophyll a concentration. However, the modeling procedure was repeated for water salinity forecasting to evaluate the generality of the approach. The ensemble models are employed for forecasting purposes in Hilo Bay, Hawaii. Moreover, the efficacy of the forecasting models for up to three days in advance is investigated. To predict chlorophyll a and salinity with different lead, the previous daily time series up to three lags are decomposed via different wavelet functions to be applied as input parameters of the models. Further, outputs of the different wavelet-ANN models are combined using the least square boosting ensemble and Bates–Granger techniques to achieve more accurate and more reliable forecasts. To examine the efficiency and reliability of the proposed models for different lead times, uncertainty analysis is conducted for the best single wavelet-ANN and ensemble models as well. The results indicate that accurate forecasts of water temperature and salinity up to three days ahead can be achieved using the ensemble models. Increasing the time horizon, the reliability and accuracy of the models decrease. Ensemble models are found to be superior to the best single models for both forecasting variables and for all the three lead times. The results of this study are promising with respect to multi-step forecasting of water quality parameters such as chlorophyll a and salinity, important indicators of ecosystem status in coastal and ocean regions.

The labyrinth spillway continues to be a popular type of the control structures. The focus of the present study is that on the optimization of the shape of the labyrinth spillway through the minimization of the construction costs because the use of it is a suitable solution in the rehabilitation process of existing reservoirs. An Adaptive Neural Fuzzy Inference System (ANFIS) model was developed to determine the discharge coefficient of the labyrinth spillway as a function of the angle between alignment of the crest and direction of flow, the relative depth of flow over spillway and its crest height. Differential Evolution (DE) algorithm and Genetic Algorithm (GA) were adopted to minimize the spillway cost as the objective function by considering certain hydraulic conditions as the constraints of the optimization procedure. The results indicated that DE and GA can respectively reduce 19.3% and 16.6% the construction cost of a real benchmark design.

Stepped spillways have a wide range of applicability as a hydraulic structure in large dams to dissipate energy of high-velocity flows at a downstream area of dams as well as release overflows into the downstream. In this study, the numerical simulation of the flow over the stepped spillway was investigated by using Flow3D software as an analytic flow field. The RNG k-ε model was applied as the turbulence model, and Volume of Fluid (VOF) model was used to determine the free surface flow profiles. At the first stage, the model was verified by reliable experimental data. Then, in order to investigate the various features of skimming flow regime, 112 numerical spillway models was designed, which 96 models were stepped spillway models and 16 models were smooth spillway models (i.e., WES profile). In these numerical experiment, two step sizes, six configuration, four passing discharge and four profile slopes (15, 30, 45 and 60 degrees) with various relative discharges were considered to investigate the energy dissipation and discharge coefficient rates. The results indicated that discharge coefficient rate and energy dissipation rate have inverse relationship. Also it was observed that when relative discharges increased, energy dissipation rate decreased and discharge coefficient rate increased.

Due to the importance of channel flow characteristics in the water conveyance, the study of it is a noteworthy problem for hydraulics experts and much attempts has been accomplished for the modeling of the flow characteristics. One significant problem in this respect is the secondary flow cells and their effect on flow specifications. Widespread experimental and analytical investigations have been accomplished on this phenomenon. However, researchers are trying to replace the expensive and time-consuming experimental approaches and ad hoc analytical models with numerical simulation procedures using computational fluid dynamics (CFD). Selection of the proper turbulence model is one of the most important problems for this type of the numerical modeling. In the present study, after evaluating several turbulence models including k–ε, shear stress transport (SST) and three versions of the Reynolds stress model (RSM) (i.e. LRR-IP, LRR-QI, and SSG models), for the numerical simulation of the secondary flow cells and their effects on trapezoidal channels flow, the more efficient model was selected. Available experimental data and theoretical model was used to validate the selected turbulence model. The results were validated in terms of the free water surface, depth-averaged velocity, and boundary shear stress. The results confirmed the performance and efficiency of SSG version of the Reynolds stress model for the numerical modeling of the secondary flow cells.

This study investigates the efficiency of Bayesian network (BN) and also artificial neural network models for predicting water quality parameters in Honolulu, Pacific Ocean. Monthly forecasting of three important characteristics of water body including water temperature, salinity and dissolved oxygen have been taken under consideration. Two separate strategies were applied in which the first strategy was related to prediction of the water quality parameters based on previous time series of the same variable. In the second strategy, an attempt was made to forecast DO using different affecting parameters such as temperature, salinity, previous time series of DO, and amount of chlorophyll. The efficiency of the models were assessed by using error measures. Results revealed that the BN models are superior over the ANN models in case of temperature and DO forecasting. Also, it was found that the first strategy is more efficient than the second strategy for predicting DO concentration. The best BN models for temperature, salinity and DO were achieved when time series of the same parameter up to 3, 2, and 3 previous months applied as input variables respectively. Overall, it can be concluded that BN and ANN models can be successfully applied for water quality modelling and forecasting in coastal waters. Moreover, the current study demonstrated that the BN models have a great ability dealing with time series including incomplete or missing data.