Comparative study on stream flow prediction using the GMNN and wavelet-based GMNN (original) (raw)
Related papers
A wavelet neural network approach to predict daily river discharge using meteorological data
Measurement and Control, 2019
This paper reports some part of modelling and data analysis work carried out within the frame of a comprehensive project on the web-based development of watershed information system. This work basically aims to present the daily discharge predictions from the actual discharge along with the meteorological data using a wavelet neural network approach, which combines two methods: discrete wavelet transform and artificial neural networks. The wavelet-artificial neural network model developed provides a good fit with the measured data, in particular with zero discharge in the summer months and also with the peaks and sudden changes in discharge on the test data collected throughout the year. The results indicate that the wavelet-artificial neural network model based predictions are distinctly superior to that of conventional artificial neural network model that corresponds up to an 80% reduction in the mean-squared error between the artificial neural network model and measured data.
Daily river flow forecasting using wavelet ANN hybrid models
Journal of Hydroinformatics, 2010
Advance time step stream flow forecasting is of paramount importance in controlling flood damage. During the past few decades, artificial neural network (ANN) techniques have been used extensively in stream flow forecasting and have proven to be a better technique than other forecasting methods such as multiple regression and general transfer function models. This study uses discrete wavelet transformation functions to preprocess the time series of the flow data into wavelet coefficients of different frequency bands. Effective wavelet coefficients are selected from the correlation analysis of the decomposed wavelet coefficients of all frequency bands with the observed flow data. Neural network models are proposed for 1-, 2- and 3-day flow forecasting at a site of Brahmani River, India. The effective wavelet coefficients are used as input to the neural network models. Both the wavelet and ANN techniques are employed to form a loose type of wavelet ANN hybrid model (NW). The hybrid mo...
Polish Journal of Environmental Studies
Climate change, population growth, industrialization, and environmental impacts cause spatiotemporal changes in the availability of regional water resources [1, 2]. In particular, climate change will affect the streamflow, temperature, amount of precipitation, and variability, which are the main components of the hydrological cycle [3-5]. For example, Jiao and Wang [6] state in their study that the streamflow and rainfall are in a decreasing trend while the temperature is in an increasing trend in the last decades. Modeling and outlining streamflow is a crucial process in water management and planning, and accurate streamflow prediction is a vital tool for optimal water quantity and quality management [7]. Studies on accurate projections of temporal streamflow patterns can aid in understanding the properties of hydrological processes in basins and improving basin modeling [8]. Many studies have been conducted that examined the relationship of streamflow with precipitation and temperature, and evaluated its changes and forecasts [9, 10]. Xu et al. [11] found that periodic changes in streamflow were closely correlated with temperature
Time Series Modeling of River Flow Using Wavelet Neural Networks
A new hybrid model which combines wavelets and Artificial Neural Network (ANN) called wavelet neural network (WNN) model was proposed in the current study and applied for time series modeling of river flow. The time series of daily river flow of the Malaprabha River basin (Karnataka state, India) were analyzed by the WNN model. The observed time series are decomposed into sub-series using discrete wavelet transform and then appropriate sub-series is used as inputs to the neural network for forecasting hydrological variables. The hybrid model (WNN) was compared with the standard ANN and AR models. The WNN model was able to provide a good fit with the observed data, especially the peak values during the testing period. The benchmark results from WNN model applications showed that the hybrid model produced better results in estimating the hydrograph properties than the latter models (ANN and AR).
Water Resources Management, 2017
Considering network topologies and structures of the artificial neural network (ANN) used in the field of hydrology, one can categorize them into two different generic types: feedforward and feedback (recurrent) networks. Different types of feedforward and recurrent ANNs are available, but multilayer perceptron type of feedforward ANN is most commonly used in hydrology for the development of wavelet coupled neural network (WNN) models. This study is conducted to compare performance of the various wavelet based feedforward artificial neural network (ANN) models. The feedforward ANN types used in the study include the multilayer perceptron neural network (MLPNN), generalized feedforward neural network (GFFNN), radial basis function neural network (RBFNN), modular neural network (MNN) and neuro-fuzzy neural network (NFNN) models. The rainfallrunoff data of four catchments located in different hydro-climatic regions of the world is used in the study. The discrete wavelet transformation (DWT) is used in the present study to decompose input rainfall data using db8 wavelet function. A total of 220 models are developed in this study to evaluate the performance of various feedforward neural network models. Performance of the developed WNN models is compared with their counterpart simple models developed without applying wavelet transformation (WT). The results of the study are further compared with-multiple linear regression (MLR) model which suggest that the WNN models outperformed their counterpart simple models. The hybrid wavelet models developed using MLPNN, the GFFNN and the MNN models performed best among the six selected data driven Water Resour Manage
A wavelet-neural network hybrid modelling approach for estimating and predicting river monthly flows
Hydrological Sciences Journal, 2013
A wavelet-neural network (WNN) hybrid modelling approach for monthly river flow estimation and prediction is developed. This approach integrates discrete wavelet multi-resolution decomposition and a backpropagation (BP) feed-forward multilayer perceptron (FFML) artificial neural network (ANN). The Levenberg-Marquardt (LM) algorithm and the Bayesian regularization (BR) algorithm were employed to perform the network modelling. Monthly flow data from three gauges in the Weihe River in China were used for network training and testing for 48-month-ahead prediction. The comparison of results of the WNN hybrid model with those of the single ANN model show that the former is able to significantly increase the prediction accuracy.
Journal of Hydroinformatics
Streamflow forecasting is highly crucial in the domain of water resources. For this study, we coupled the Wavelet Transform (WT) and Artificial Neural Network (ANN) to forecast Gilgit streamflow at short-term (T0.33 and T0.66), intermediate-term (T1), and long-term (T2, T4, and T8) monthly intervals. Streamflow forecasts are uncertain due to stochastic disturbances caused by variations in snow-melting routines and local orography. To remedy this situation, decomposition by WT was undertaken to enhance the associative relation between the input and target sets for ANN to process. For ANN modeling, cross-correlation was used to guide input selection. Corresponding to six intervals, nine configurations were developed. Short-term intervals performed best, especially for T0.33; intermediate intervals showed decreasing performance. However, interestingly, performance regains back to a decent level for long-term forecasting. Almost all the models underestimate high flows and slightly overe...
Journal of Hydroinformatics, 2012
This study developed a wavelet transformation and nonlinear autoregressive (NAR) artificial neural network (ANN) hybrid modeling approach to improve the prediction accuracy of river discharge time series. Daubechies 5 discrete wavelet was employed to decompose the time series data into subseries with low and high frequency, and these subseries were then used instead of the original data series as the input vectors for the designed NAR network (NARN) with the Bayesian regularization (BR) optimization algorithm. The proposed hybrid approach was applied to make multi-step-ahead predictions of monthly river discharge series in the Weihe River in China. The prediction results of this hybrid model were compared with those of signal NARNs and the traditional Wavelet-Artificial Neural Network hybrid approach (WNN). The comparison results revealed that the proposed hybrid model could significantly increase the prediction accuracy and prediction period of the river discharge time series in the current case study.
Water Level Prediction in Nan River, Thailand Using Wavelet Neural Network
2010
Accurate prediction of water levels in a river is an important factor for effective flood prevention and mitigation. In this study, Artificial Neural Networks (ANNs) with Wavelet Decomposition has been applied to predict water levels in Nan River of Thailand at N.64 and N.1 gauging stations. These stations are located in Nan province of Thailand. A feed forward neural network with early stopping method of training is adopted to train and generalize the network in order to prevent the network from overfitting the training data. Discrete wavelet analysis is used as the data pre-processing technique to decompose the input data into their detail (high frequency) component and approximation (low frequency) component. The Haar wavelet, the simplest and the oldest of all wavelets (Vidakovic and Mueller 1991) is used to decompose the data in this study. Both original and decomposed data are used as the input of the ANN model. The integration of wavelet analysis and ANN is called the wavelet...
A combined generalized regression neural network wavelet model for monthly streamflow prediction
KSCE Journal of Civil Engineering, 2011
The ability of a combined model, Wavelet-Generalized Regression Neural Network (WGRNN), is investigated in the current study for the prediction of monthly streamflows. The WGRNN model is obtained by combining two methods, Discrete Wavelet Transform (DWT) and Generalized Regression Neural Network (GRNN), for one-month-ahead streamflow forecasting. The monthly flow data of two stations, the Gerdelli Station on the Canakdere River and the Isakoy Station on the Goksudere River, in the Eastern Black Sea region of Turkey are used in the study. The forecasts of the WGRNN model are tested using the Root Mean Square Error (RMSE), Variance Account For (VAF) and correlation coefficient (R) statistics and the results are compared with those of the single GRNN and Feed Forward Neural Network (FFNN). The comparison results revealed that the WGRNN performs better than the GRNN and FFNN models in monthly streamflow prediction. For the Gerdelli and Isakoy stations, it is found that the WGRNN models with RMSE = 5.31 m 3 /s, VAF = 52.3%, R = 0.728 and RMSE = 3.36 m 3 /s, VAF = 55.1%, R = 0.742 in the test period are superior in forecasting monthly streamflows than the best accurate GRNN models with RMSE = 6.39 m 3 /s, VAF = 30.1%, R = 0.553 and RMSE = 4.19 m 3 /s, VAF = 30.1%, R = 0.549, respectively.