Prediction of Density Flow Plunging Depth in Dam Reservoirs: An Artificial Neural Network Approach

Experimental findings and observations indicate that plunging flow is related to the formation of bed load deposition in dam reservoirs. The sediment delta begins to form in the plunging region where the inflow river water meets the ambient reservoir water. Correct estimation of dam reservoir flow, plunging point, and plunging depth is crucial for dam reservoir sedimentation and water quality issues. In this study, artificial neural network (ANN), multi‐linear regression (MLR), and two‐dimensional hydrodynamic model approaches are used for modeling the plunging point and depth. A multi layer perceptron (MLP) is used as the ANN structure. A two‐dimensional model is adapted to simulate density plunging flow through a reservoir with a sloping bottom. In the model, nonlinear and unsteady continuity, momentum, energy, and k–ε turbulence equations are formulated in the Cartesian coordinates. Density flow parameters such as velocity, plunging points, and plunging depths are determined from the simulation and model results, and these are compared with previous experimental and model works. The results show that the ANN model forecasts are much closer to the experimental data than the MLR and mathematical model forecasts.     

Wavelet and Neuro‐fuzzy Conjunction Approach for Suspended Sediment Prediction

Simulation approaches employed in suspended sediment processes are important in the areas of water resources and environmental engineering. In the current study, neuro‐fuzzy (NF), a combination of wavelet transform and neuro‐fuzzy (WNF), multi linear regression (MLR), and the conventional sediment rating curve (SRC) models were considered for suspended sediment load (S) modeling in a gauging station in the USA. In the proposed WNF model, the discrete wavelet analysis was linked to a NF approach. To achieve this aim, the observed time series of river flow discharge (Q) and S were decomposed to sub time series at different scales by discrete wavelet transform. Afterwards, the effective sub time series were added together to obtain a useful Q and S time series for prediction. Eventually, the obtained total time series were imposed as inputs to the NF method for daily S prediction. The results illustrated that the predicted values by the proposed WNF model were in good agreement with the observed S values and gave better results than other models. Furthermore, the WNF model satisfactorily estimated the cumulative suspended sediment load and produced relatively reasonable predictions for extreme values of S, while NF, MLR, and SRC models provided unacceptable predictions.     

Wavelet regression model as an alternative to neural networks for monthly streamflow forecasting

The accuracy of the wavelet regression (WR) model in monthly streamflow forecasting is investigated in the study. The WR model is improved combining the two methods—the discrete wavelet transform (DWT) model and the linear regression (LR) model—for 1‐month‐ahead streamflow forecasting. In the first part of the study, the results of the WR model are compared with those of the single LR model. Monthly flow data from two stations, Gerdelli Station on Canakdere River and Isakoy Station on Goksudere River, in Eastern Black Sea region of Turkey are used in the study. The comparison results reveal that the WR model could increase the forecast accuracy of the LR model. In the second part of the study, the accuracy of the WR model is compared with those of the artificial neural networks (ANN) and auto‐regressive (AR) models. On the basis of the results, the WR is found to be better than the ANN and AR models in monthly streamflow forecasting. Copyright © 2009 John Wiley & Sons, Ltd.     

Rainfall‐runoff modelling using artificial neural networks: comparison of network types

Growing interest in the use of artificial neural networks (ANNs) in rainfall‐runoff modelling has suggested certain issues that are still not addressed properly. One such concern is the use of network type, as theoretical studies on a multi‐layer perceptron (MLP) with a sigmoid transfer function enlightens certain limitations for its use. Alternatively, there is a strong belief in the general ANN user community that a radial basis function (RBF) network performs better than an MLP, as the former bases its nonlinearities on the training data set. This argument is not yet substantiated by applications in hydrology. This paper presents a comprehensive evaluation of the performance of MLP‐ and RBF‐type neural network models developed for rainfall‐runoff modelling of two Indian river basins. The performance of both the MLP and RBF network models were comprehensively evaluated in terms of their generalization properties, predicted hydrograph characteristics, and predictive uncertainty. The results of the study indicate that the choice of the network type certainly has an impact on the model prediction accuracy. The study suggests that both the networks have merits and limitations. For instance, the MLP requires a long trial‐and‐error procedure to fix the optimal number of hidden nodes, whereas for an RBF the structure of the network can be fixed using an appropriate training algorithm. However, a judgment on which is superior is not clearly possible from this study. Copyright © 2004 John Wiley & Sons, Ltd.     

Multiple linear regression,multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals

ABSTRACT

Nowadays, mathematical models are widely used to predict climate processes, but little has been done to compare the models. In this study, multiple linear regression (MLR), multi-layer perceptron (MLP) network and adaptive neuro-fuzzy inference system (ANFIS) models were compared for precipitation forecasting. The large-scale climate signals were considered as inputs to the applied models. After selecting the most effective climate indices, the effects of large-scale climate signals on the seasonal standardized precipitation index (SPI) of the Maharlu-Bakhtaran catchment, Iran, simultaneously and with a delay, was analysed using a cross-correlation function. Hence, the SPI time series was forecasted up to four time intervals using MLR, MLP and ANFIS. The results showed that most of the indices were significant with SPI of different lag times. Comparison of the SPI forecast results by MLR, MLP and ANFIS models showed better performance for the MLP network than the other two models (RMSE = 0.86, MAE = 0.74 for the first step ahead of SPI forecasting).

Editor D. Koutsoyiannis; Associate editor F. Pappenberger     

Comparison of artificial neural network models for hydrologic predictions at multiple gauging stations in an agricultural watershed

This paper reports on an evaluation of the use of artificial neural network (ANN) models to forecast daily flows at multiple gauging stations in Eucha Watershed, an agricultural watershed located in north‐west Arkansas and north‐east Oklahoma. Two different neural network models, the multilayer perceptron (MLP) and the radial basis neural network (RBFNN), were developed and their abilities to predict stream flow at four gauging stations were compared. Different scenarios using various combinations of data sets such as rainfall and stream flow at various lags were developed and compared for their ability to make flow predictions at four gauging stations. The input vector selection for both models involved quantification of the statistical properties such as cross‐, auto‐ and partial autocorrelation of the data series that best represented the hydrologic response of the watershed. Measured data with 739 patterns of input–output vector were divided into two sets: 492 patterns for training, and the remaining 247 patterns for testing. The best performance based on the RMSE, R² and CE was achieved by the MLP model with current and antecedent precipitation and antecedent flow as model inputs. The MLP model testing resulted in R² values of 0·86, 0·86, 0·81, and 0·79 at the four gauging stations. Similarly, the testing R² values for the RBFNN model were 0·60, 0·57, 0·58, and 0·56 for the four gauging stations. Both models performed satisfactorily for flow predictions at multiple gauging stations, however, the MLP model outperformed the RBFNN model. The training time was in the range 1–2 min for MLP, and 5–10 s for RBFNN on a Pentium IV processor running at 2·8 GHz with 1 MB of RAM. The difference in model training time occurred because of the clustering methods used in the RBFNN model. The RBFNN uses a fuzzy min‐max network to perform the clustering to construct the neural network which takes considerably less time than the MLP model. Results show that ANN models are useful tools for forecasting the hydrologic response at multiple points of interest in agricultural watersheds. Copyright © 2008 John Wiley & Sons, Ltd.     

Prediction of effective porosity from seismic attributes using locally linear model tree algorithm

In this study, a locally linear model tree algorithm was used to optimize a neuro‐fuzzy model for prediction of effective porosity from seismic attributes in one of Iranian oil fields located southwest of Iran. Valid identification of effective porosity distribution in fractured carbonate reservoirs is extremely essential for reservoir characterization. These high‐accuracy predictions facilitate efficient exploration and management of oil and gas resources. The multi‐attribute stepwise linear regression method was used to select five out of 26 seismic attributes one by one. These attributes introduced into the neuro‐fuzzy model to predict effective porosity. The neuro‐fuzzy model with seven locally linear models resulted in the lowest validation error. Moreover, a blind test was carried out at the location of two wells that were used neither in training nor validation. The results obtained from the validation and blind test of the model confirmed the ability of the proposed algorithm in predicting the effective porosity. In the end, the performance of this neuro‐fuzzy model was compared with two regular neural networks of a multi‐layer perceptron and a radial basis function, and the results show that a locally linear neuro‐fuzzy model trained by a locally linear model tree algorithm resulted in more accurate porosity prediction than standard neural networks, particularly in the case where irregularities increase in the data set. The production data have been also used to verify the reliability of the porosity model. The porosity sections through the two wells demonstrate that the porosity model conforms to the production rate of wells. Comparison of the locally linear neuro‐fuzzy model performance on different wells indicates that there is a distinct discrepancy in the performance of this model compared with the other techniques. This discrepancy in the performance is a function of the correlation between the model inputs and output. In the case where the strength of the relationship between seismic attributes and effective porosity decreases, the neuro‐fuzzy model results in more accurate prediction than regular neural networks, whereas the neuro‐fuzzy model has a close performance to neural networks if there is a strong relationship between seismic attributes and effective porosity. The effective porosity map, presented as the output of the method, shows a high‐porosity area in the centre of zone 2 of the Ilam reservoir. Furthermore, there is an extensive high‐porosity area in zone 4 of Sarvak that extends from the centre to the east of the reservoir.     

Identification of the best architecture of a multilayer perceptron in modeling daily total ozone concentration over Kolkata,India

Autoregressive neural network (AR-NN) models of various orders have been generated in this work for the daily total ozone (TO) time series over Kolkata (22.56°N, 88.5°E). Artificial neural network in the form of multilayer perceptron (MLP) is implemented in order to generate the AR-NN models of orders varying from 1 to 13. An extensive variable selection method through multiple linear regression (MLR) is implemented while developing the AR-NNs. The MLPs are characterized by sigmoid non-linearity. The optimum size of the hidden layer is identified in each model and prediction are produced by validating it over the test cases using the coefficient of determination (R ²) and Willmott’s index (WI). It is observed that AR-NN model of order 7 having 6 nodes in the hidden layer has maximum prediction capacity. It is further observed that any increase in the orders of AR-NN leads to less accurate prediction.     

Artificial Neural Network Prediction of Tropospheric Ozone Concentrations in Istanbul,Turkey

Tropospheric (ground‐level) ozone has adverse effects on human health and environment. In this study, next day's maximum 1‐h average ozone concentrations in Istanbul were predicted using multi‐layer perceptron (MLP) type artificial neural networks (ANNs). Nine meteorological parameters and nine air pollutant concentrations were utilized as inputs. The total 578 datasets were divided into three groups: training, cross‐validation, and testing. When all the 18 inputs were used, the best performance was obtained with a network containing one hidden layer with 24 neurons. The transfer function was hyperbolic tangent. The correlation coefficient (R), mean absolute error (MAE), root mean squared error (RMSE), and index of agreement or Willmott's Index (d₂) for the testing data were 0.90, 8.78 µg/m³, 11.15 µg/m³, and 0.95, respectively. Sensitivity analysis has indicated that the persistence information (current day's maximum and average ozone concentrations), NO concentration, average temperature, PM₁₀, maximum temperature, sunshine time, wind direction, and solar radiation were the most important input parameters. The values of R, MAE, RMSE, and d₂ did not change considerably for the MLP model using only these nine inputs. The performances of the MLP models were compared with those of regression models (i.e., multiple linear regression and multiple non‐linear regression). It has been found that there was no significant difference between the ANN and regression modeling techniques for the forecasting of ozone concentrations in Istanbul.     

Neural network and wavelet conjunction model for modelling monthly level fluctuations in Turkey

This paper proposes the application of a conjunction model (neuro‐wavelet) for forecasting monthly lake levels. The neuro‐wavelet (NW) conjunction model is improved combining two methods, discrete wavelet transform and artificial neural networks. The application of the methodology is presented for the Lake Van, which is the biggest lake in Turkey, and Lake Egirdir. The accuracy of the NW model is investigated for 1‐ and 6‐month‐ahead lake level forecasting. The root mean square errors, mean absolute relative errors and determination coefficient statistics are used for evaluating the accuracy of NW models. The results of the proposed models are compared with those of the neural networks. In the 1‐month‐ahead lake level forecasting, the NW conjunction model reduced the root mean square errors and mean absolute relative errors by 87–34% and 86–31% for the Van and Egirdir lakes, respectively. In the 6‐month‐ahead lake level forecasting, the NW conjunction model reduced the root mean square errors and mean absolute relative errors by 34–48% and 30‐46% for the Van and Egirdir lakes, respectively. The comparison results indicate that the suggested model could significantly increase the short‐ and long‐term forecast accuracy. Copyright © 2009 John Wiley & Sons, Ltd.     

Daily pan evaporation modelling using multi‐layer perceptrons and radial basis neural networks

This paper reports on investigations of the abilities of three different artificial neural network (ANN) techniques, multi‐layer perceptrons (MLP), radial basis neural networks (RBNN) and generalized regression neural networks (GRNN) to estimate daily pan evaporation. Different MLP models comprising various combinations of daily climatic variables, that is, air temperature, solar radiation, wind speed, pressure and humidity were developed to evaluate the effect of each of these variables on pan evaporation. The MLP estimates are compared with those of the RBNN and GRNN techniques. The Stephens‐Stewart (SS) method is also considered for the comparison. The performances of the models are evaluated using root mean square errors (RMSE), mean absolute error (MAE) and determination coefficient (R²) statistics. Based on the comparisons, it was found that the MLP and RBNN computing techniques could be employed successfully to model the evaporation process using the available climatic data. The GRNN was found to perform better than the SS method. Copyright © 2008 John Wiley & Sons, Ltd.     

Evaporation process modelling over northern Iran: application of an integrative data-intelligence model with the krill herd optimization algorithm

ABSTRACT

An integrated data-intelligence model based on multilayer perceptron (MLP) and krill herd optimization – the MLP-KH model – is presented for the estimation of daily pan evaporation. Daily climatological information collected from two meteorological stations in the northern region of Iran is used to compare the potential of the proposed model against classical MLP and support vector machine models. The integrated and the classical models were assessed based on different error and goodness-of-fit metrics. The quantitative results evidenced the capacity of the proposed MLP-KH model to estimate daily pan evaporation compared to the classical ones. For both weather stations, the lowest root mean square error (RMSE) of 0.725 and 0.855 mm/d, respectively, was obtained from the integrated model, while the RMSE for MLP was 1.088 and 1.197, and for SVM it was 1.096 and 1.290, respectively.     

River flow forecasting using wavelet and cross‐wavelet transform models

In this study, short‐term river flood forecasting models based on wavelet and cross‐wavelet constituent components were developed and evaluated for forecasting daily stream flows with lead times equal to 1, 3, and 7 days. These wavelet and cross‐wavelet models were compared with artificial neural network models and simple perseverance models. This was done using data from the Skrwa Prawa River watershed in Poland. Numerical analysis was performed on daily maximum stream flow data from the Parzen station and on meteorological data from the Plock weather station in Poland. Data from 1951 to 1979 was used to train the models while data from 1980 to 1983 was used to test the models. The study showed that forecasting models based on wavelet and cross‐wavelet constituent components can be used with great accuracy as a stand‐alone forecasting method for 1 and 3 days lead time river flood forecasting, assuming that there are no significant trends in the amplitude for the same Julian day year‐to‐year, and that there is a relatively stable phase shift between the flow and meteorological time series. It was also shown that forecasting models based on wavelet and cross‐wavelet constituent components for forecasting river floods are not accurate for longer lead time forecasting such as 7 days, with the artificial neural network models providing more accurate results. Copyright © 2008 John Wiley & Sons, Ltd.     

Developing a hybrid multi‐model for peak flood forecasting

The present study aims to develop a hybrid multi‐model using the soft computing approach. The model is a combination of a fuzzy logic, artificial neural network (ANN) and genetic algorithm (GA). While neural networks are low‐level computational structures that perform well dealing with raw data, fuzzy logic deal with reasoning on a higher level by using linguistic information acquired from domain experts. However, fuzzy systems lack the ability to learn and cannot adjust themselves to a new environment. Moreover, experts occasionally make mistakes and thus some rules used in a system may be false. A network type structure of the present hybrid model is a multi‐layer feed‐forward network, the main part is a fuzzy system based on the first‐order Sugeno fuzzy model with a fuzzification and a defuzzification processes. The consequent parameters are determined by least square method. The back‐propagation is applied to adjust weights of network. Then, the antecedent parameters of the membership function are updated accordingly by the gradient descent method. The GA was applied to select the fuzzy rule. The hybrid multi‐model was used to forecast the flood level at Chiang Mai (under the big flood 2005) and the Koriyama flood (2003) in Japan. The forecasting results are evaluated using standard global goodness of fit statistic, efficient index (EI), the root mean square error (RMSE) and the peak flood error. Moreover, the results are compared to the results of a neuro‐genetic model (NGO) and ANFIS model using the same input and output variables. It was found that the hybrid multi‐model can be used successfully with an efficiency index (EI) more than 0·95 (for Chiang Mai flood up to 12 h ahead forecasting) and more than 0·90 (for Koriyama flood up to 8 h ahead forecasting). In general, all of three models can predict the water level with satisfactory results. However, the hybrid model gave the best flood peak estimation among the three models. Therefore, the use of fuzzy rule base, which is selected by GA in the hybrid multi‐model helps to improve the accuracy of flood peak. Copyright © 2009 John Wiley & Sons, Ltd.     

Wavelet-ANFIS models for forecasting monsoon flows: Case study for the Gandak River (India)

WANFIS, a conjunction model of discreet wavelet transform (DWT) and adaptive neuro-fuzzy inference system (ANFIS) was developed for forecasting the current-day flow in a river when only available data are historical flows. Discreet wavelet transform decomposed the observed flow time series (OFTS) into wavelet components which captured useful information on three resolution levels. A smoothened flow time series (SFTS) was formed by filtering out the noise wavelet components and recombining the effective wavelet components. WANFIS model is essentially an ANFIS model with SFTS hydrograph as the input, while ANFIS and autoregression (AR) models, developed for comparison purpose, use OFTS hydrograph as input. For performance evaluation, the developed models were utilized for predicting daily monsoon flows for the Gandak River in Bihar state of India. During monsoon (June–October), this river carries large flows making the entire North Bihar unsafe for habitation or cultivation. Based on various performance indices, it was concluded that WANFIS models simulate the monsoon flows in the Gandak more reliably than ANFIS and AR models. The best performing WANFIS model, with four previous days’ flows as input, predicted the current-day Gandak flows with 80.7% accuracy while ANFIS and AR models predicted it with only 71.8 and 51.2% accuracies.     

A fusion-based neural network methodology for monthly reservoir inflow prediction using MODIS products

ABSTRACT

A model fusion approach was developed based on five artificial neural networks (ANNs) and MODIS products. Static and dynamic ANNs – the multi-layer perceptron (MLP) with one and two hidden layers, general regression neural network (GRNN), radial basis function (RBF) and nonlinear autoregressive network with exogenous inputs (NARX) – were used to predict the monthly reservoir inflow in Mollasadra Dam, Fars Province, Iran. Leaf area index and snow cover from MODIS, and rainfall and runoff data were used to identify eight different combinations to train the models. Statistical error indices and the Borda count method were used to verify and rank the identified combinations. The best results for individual ANNs were combined with MODIS products in a fusion model. The results show that using MODIS products increased the accuracy of predictions, with the MLP with two hidden layers giving the best performance. Also, the fusion model was found to be superior to the best individual ANNs.     

Predicting Diel,Diurnal and Nocturnal Dynamics of Dissolved Oxygen and Chlorophyll‐a Using Regression Models and Neural Networks

Human‐induced and natural interruptions with continuous streams of observational data necessitate the development of gap‐filling and prediction strategies towards better understanding, monitoring and management of aquatic systems. This study quantified the efficacy of multiple non‐linear regression (MNLR) versus artificial neural network (ANN) models as well as the temporal partitioning of diurnal versus nocturnal data for the predictions of chlorophyll‐a (chl‐a) and dissolved oxygen (DO) dynamics. The temporal partitioning increased the predictive performances of the best MNLR models of diurnal DO by 45% and nocturnal DO by 4%, relative to the best diel MNLR model of diel DO ($r_{{\rm adj}}^{2} = 68.8\%$ ). The ANN‐based predictions had a higher predictive power than the MNLR‐based predictions for both chl‐a and DO except for diurnal DO dynamics. The best ANNs based on independent validations were multilayer perceptron (MLP) for diel chl‐a, generalized feedforward (GFF) for diurnal and nocturnal chl‐a, MLP for diel DO, GFF for diurnal DO, and MLP for nocturnal DO.     

Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis

In this study, a new method of stand-alone short-term spring snowmelt river flood forecasting was developed based on wavelet and cross-wavelet analysis. Wavelet and cross-wavelet analysis were used to decompose flow and meteorological time series data and to develop wavelet based constituent components which were then used to forecast floods 1, 2, and 6 days ahead. The newly developed wavelet forecasting method (WT) was compared to multiple linear regression analysis (MLR), autoregressive integrated moving average analysis (ARIMA), and artificial neural network analysis (ANN) for forecasting daily stream flows with lead-times equal to 1, 2, and 6 days. This comparison was done using data from the Rideau River watershed in Ontario, Canada. Numerical analysis was performed on daily maximum stream flow data from the Rideau River station and on meteorological data (rainfall, snowfall, and snow on ground) from the Ottawa Airport weather station. Data from 1970 to 1997 were used to train the models while data from 1998 to 2001 were used to test the models. The most significant finding of this research was that it was demonstrated that the proposed wavelet based forecasting method can be used with great accuracy as a stand-alone forecasting method for 1 and 2 days lead-time river flood forecasting, assuming that there are no significant trends in the amplitude for the same Julian day year-to-year, and that there is a relatively stable phase shift between the flow and meteorological time series. The best forecasting model for 1 day lead-time was a wavelet analysis model. In testing, it had the lowest RMSE value (13.8229), the highest R² value (0.9753), and the highest EI value (0.9744). The best forecasting model for 2 days lead-time was also a wavelet analysis model. In testing, it had the lowest RMSE value (31.7985), the highest R² value (0.8461), and the second highest EI value (0.8410). It was also shown that the proposed wavelet based forecasting method is not particularly accurate for longer lead-time forecasting such as 6 days, with the ANN method providing more accurate results. The best forecasting model for 6 days lead-time was an ANN model, with the wavelet model not performing as well. In testing, the wavelet model had an RMSE of 57.6917, an R² of 0.4835, and an EI of 0.4366.     

Modelling evapotranspiration using discrete wavelet transform and neural networks

This study combines wavelet transforms and feed‐forward neural network methods for reference evapotranspiration estimation. The climatic data (air temperature, solar radiation, wind speed, relative humidity) from two stations in the United States was evaluated for estimating models. For wavelet and neural network (WNN) model, the input data was decomposed into wavelet sub‐time series by wavelet transformation. Later, the new series (reconstructed series) are produced by adding the available wavelet components and these reconstructed series are used as the input of the WNN model. This phase is pre‐processing of raw data and the main different of the WNN model. The performance of the WNN model was compared with classical neural networks approach [artificial neural network (ANN)], multi‐linear regression and Hargreaves empirical method. This study shows that the wavelet transforms and neural network methods could be applied successfully for evapotranspiration modelling from climatic data. Copyright © 2009 John Wiley & Sons, Ltd.     

The potential of different ANN techniques in evapotranspiration modelling

The potential of three different artificial neural network (ANN) techniques, the multi‐layer perceptrons (MLPs), radial basis neural networks (RBNNs) and generalized regression neural networks (GRNNs), in modelling of reference evapotranspiration (ET₀) is investigated in this paper. Various daily climatic data, that is, solar radiation, air temperature, relative humidity and wind speed from two stations, Pomona and Santa Monica, in Los Angeles, USA, are used as inputs to the ANN techniques so as to estimate ET₀ obtained using the FAO‐56 Penman–Monteith (PM) equation. In the first part of the study, a comparison is made between the estimates provided by the MLP, RBNN and GRNN and those of the following empirical models: The California Irrigation Management Information System (CIMIS) Penman (1985), Hargreaves (1985) and Ritchie (1990). In this part of the study, the empirical models are calibrated using the standard FAO‐56 PM ET₀ values. The estimates of the ANN techniques are also compared with those of the calibrated empirical models. Mean square errors, mean absolute errors and determination coefficient statistics are used as comparing criteria for the evaluation of the models' performances. Based on the comparisons, it is found that the MLP and RBNN techniques could be employed successfully in modelling the ET₀ process. In the second part of the study, the potential of ANN techniques and the empirical methods in ET₀ estimation using nearby station data is investigated. Among the models, the calibrated Hargreaves model is found to perform better than the others. Copyright © 2007 John Wiley & Sons, Ltd.