A wavelet-SARIMA-ANN hybrid model for precipitation forecasting (original) (raw)
Related papers
Monthly Rainfall Prediction Using Wavelet Neural Network Analysis
Water Resources Management, 2013
Rainfall is one of the most significant parameters in a hydrological model. Several models have been developed to analyze and predict the rainfall forecast. In recent years, wavelet techniques have been widely applied to various water resources research because of their timefrequency representation. In this paper an attempt has been made to find an alternative method for rainfall prediction by combining the wavelet technique with Artificial Neural Network (ANN). The wavelet and ANN models have been applied to monthly rainfall data of Darjeeling rain gauge station. The calibration and validation performance of the models is evaluated with appropriate statistical methods. The results of monthly rainfall series modeling indicate that the performances of wavelet neural network models are more effective than the ANN models.
2014
Since 2000, western drought caused sharp drop by about 100 feet in the largest reservoir of North America, Lake Mead. About 97% of inflow into Lake Mead is supplied by Colorado River Basin which is extremely sensitive to changes in precipitation and temperature. Oceans play an important role on earth's climate via oceanic-atmospheric interactions known as climate teleconnections, which deeply affect the terrestrial precipitation patterns. This issue signifies the necessity of developing a modern hydroinformatics tool-precipitation forecasting model-to account for teleconnection signals from climate change and mitigate drought hazards impact on lake water, quantitatively and qualitatively, which cannot be achieved by using traditional Global Circulation Model. Therefore, understanding the relationship between precipitation and teleconnection patterns could be the first step for precipitation forecasting. However, highly non-linear and non-stationary nature of teleconnection patterns result in large uncertainties in estimates, since simple linear analyses failed to capture underlying trends at sub-continental scales. For this purpose, high-resolution remote sensing imagery, spectral analysis techniques, and wavelet analysis were integrated to explore the nonstationary and nonlinear behavior of teleconnection signals between the Pacific and Atlantic sea surface temperature (SST) on a short-term basis (10 years) from which the precipitation pattern shift in the Upper Colorado River Basin can be elucidated. These processes lead to the creation of correlation maps which specify index regions within the Atlantic and Pacific Oceans where SST anomaly can be statistically significant in correlation with terrestrial precipitation. These indexed regions delivering some kind of memory effects of SST were extracted to be inputs into an Artificial Neural Network (ANN). Advances in Wavelet-based Empirical Orthogonal Function and Artificial Neural Network (WEOF-ANN) model for rainfall prediction assists the local water management agencies to mitigate the drought impacts and obtain sustainable development strategies a month ahead of the time in urban drinking water infrastructure assessment plan around Lake Mead area.
In this study, three different neural network algorithms (feed forward back propagation, FFBP; radial basis function; generalized regression neural network) and wavelet transformation were used for daily precipitation predictions. Different input combinations were tested for the precipitation estimation. As a result, the most appropriate neural network model was determined for each station. Also linear regression model performance is compared with the wavelet neural networks models. It was seen that the wavelet FFBP method provided the best performance evaluation criteria. The results indicate that coupling wavelet transforms with neural network can provide significant advantages for estimation process. In addition, global wavelet spectrum provides considerable information about the structure of the physical process to be modeled.
Modelling hydrological time series data using wavelet neural network analysis
2009
Time series analysis requires mapping complex relationships between input(s) and output(s), because the forecasted values are mapped as a function of patterns observed in the past. In order to improve the precision of the forecasts, a Wavelet Neural Network (WNN) model, based on a combination of wavelet analysis and Artificial Neural Network (ANN), has been proposed. The WNN and ANN models have been applied to daily streamflow and monthly groundwater levels series where there is a scarcity of other hydrological time series data. The calibration and validation performance of the models is evaluated with appropriate statistical indices. The results of daily streamflow and monthly groundwater level series modelling indicated that the performances of WNN models are more effective than the ANN models. This paper also highlights the capability of WNN models in estimating low and high values in the hydrological time series data.
Hydrological Time Series Forecasting Using Anfis Models with Aid of Wavelet Transform
The Journal of The University of Duhok, 2017
The precise and accurate models of hydrological time series that are embedded with high complexity, nonstationarity, and non-linearity in both spatial and temporal scales can provide important information for decision-making in water resources management and environmental related issues. Hybrid wavelet transform (WT) and adaptive neuro-fuzzy inference system (ANFIS) has been used in this study to improve the forecasting capability of ANFIS model by decomposing the time series into sub-time series (approximation and details) using wavelet transform then combining the effective and significant time lags of sub-time series to form a set of input variables. The present study attempts to add the effective and significant time lags of original time series as extra variables to the input variables set. In addition, different combinations of variables, 1-3, from the set of input variables as inputs to the ANFIS model were used to forecast the time series. To examine the potential of the approach for practical applications, the model is applied to forecast, one step-ahead, the monthly data of hydrological time series (rainfall, evaporation, minimum and maximum temperature, average wind speed and reservoir inflow) for Kirkuk, Sulaimani, Dokan and Darbandikhan meteorological stations in Iraq. The best fit models were selected using the coefficient of determination () and root mean square error (). Based on the results, the proposed model has high performance in forecasting the monthly minimum and maximum temperature, evaporation and reservoir inflow with values ranged from 0.93 to 0.99 and relatively good performances in forecasting the monthly rainfall and average wind speed with values ranged from 0.77 to 0.93.
Journal of Hydrologic Engineering, 2003
Droughts are destructive climatic extreme events, which may cause significant damages both in natural environments and human lives. Drought forecasting plays an important role in the control and management of water resources systems. In this study, a conjunction model is presented to forecast droughts. The proposed conjunction model is based on dyadic wavelet transforms and neural networks. Neural networks have shown great ability in modeling and forecasting nonlinear and nonstationary time series in a water resources engineering, and wavelet transforms provide useful decompositions of an original time series. The wavelettransformed data aids in improving the model performance by capturing helpful information on various resolution levels. Neural networks were used to forecast decomposed sub-signals in various resolution levels and reconstruct forecasted sub-signals. The performance of the conjunction model was measured using various forecast skill criteria. The model was applied to forecast droughts in the Conchos River Basin in Mexico, which is the most important tributary of the Lower Rio Grande/Bravo. The results indicate that the conjunction model significantly
Forecasting of meteorological drought using Wavelet- ANFIS hybrid model for different time steps
Drought is accounted as one of the most natural hazards. Studying on drought is important for designing and managing of water resources systems. This research is carried out to evaluate the ability of Wavelet-ANN and adaptive neuro-fuzzy inference system (ANFIS) techniques for meteorological drought forecasting in southeastern part of East Azerbaijan province, Iran. The Wavelet-ANN and ANFIS models were first trained using the observed data recorded from 1952 to 1992 and then used to predict meteorological drought over the test period extending from 1992 to 2011. The performances of the different models were evaluated by comparing the corresponding values of root mean squared error coefficient of determination (R 2) and Nash-Sutcliffe model efficiency coefficient. In this study, more than 1,000 model structures including artificial neural network (ANN), adaptive neural-fuzzy inference system (ANFIS) and Wavelet-ANN models were tested in order to assess their ability to forecast the meteorological drought for one, two, and three time steps (6 months) ahead. It was demonstrated that wavelet transform can improve meteorological drought modeling. It was also shown that ANFIS models provided more accurate predictions than ANN models. This study confirmed that the optimum number of neurons in the hidden layer could not be always determined using specific formulas; hence, it should be determined using a trial-and-error method. Also, decomposition level in wavelet transform should be delineated according to the periodicity
Water, 2021
Accurate rainfall forecasting in watersheds is of indispensable importance for predicting streamflow and flash floods. This paper investigates the accuracy of several forecasting technologies based on Wavelet Packet Decomposition (WPD) in monthly rainfall forecasting. First, WPD decomposes the observed monthly rainfall data into several subcomponents. Then, three data-based models, namely Back-propagation Neural Network (BPNN) model, group method of data handing (GMDH) model, and autoregressive integrated moving average (ARIMA) model, are utilized to complete the prediction of the decomposed monthly rainfall series, respectively. Finally, the ensemble prediction result of the model is formulated by summing the outputs of all submodules. Meanwhile, these six models are employed for benchmark comparison to study the prediction performance of these conjunction methods, which are BPNN, WPD-BPNN, GMDH, WPD-GMDH, ARIMA, and WPD-ARIMA models. The paper takes monthly data from Luoning and Zuoyu stations in Luoyang city of China as the case study. The performance of these conjunction methods is tested by four quantitative indexes. Results show that WPD can efficiently improve the forecasting accuracy and the proposed WPD-BPNN model can achieve better prediction results. It is concluded that the hybrid forecast model is a very efficient tool to improve the accuracy of mid-and long-term rainfall forecasting.
Journal of Hydrologic Engineering, 2019
A novel wavelet-artificial neural network hybrid model (WA-ANN) for short-term daily inflow forecasting is proposed, using for the first time Tropical Rainfall Measuring Mission (TRMM) data together with inflow data, which were transformed using mother-wavelets to improve the model performance. The models were assessed using the inflow records to a Brazilian reservoir named Três Marias, located in the São Francisco River basin, and daily rainfall estimates from the TRMM both for the period of 1998-2012. Several combinations of inputs for both regular and hybrid artificial neural networks (ANN) were assessed to forecast inflows seven days ahead, and it was proved that the WA-ANN had a superior performance. Even the WA-ANN model, which uses only the approximation at level three of rainfall data, provided a higher performance than the regular ANN, which uses the raw inflow data [r increase 16%, Nash-Sutcliffe model efficiency coefficient (NASH) increase 35%, and root-mean-square deviation (RMSD) decrease 47%]. It was also found the best model was the WA-ANN with transformed rainfall and inflow data as input (r increase 20%, NASH increase 44%, and RMSD decrease 69%).