Application of optimized Support Vector Machine in monthly streamflow forecasting: using Autocorrelation Function for input variables estimation

2021 ◽  
Vol 7 (3) ◽  
Author(s):  
Kevin Christian ◽  
Andreas F. V. Roy ◽  
Doddi Yudianto ◽  
Danrong Zhang
Keyword(s):  
Support Vector Machine ◽  
Autocorrelation Function ◽  
Support Vector ◽  
Streamflow Forecasting ◽  
Monthly Streamflow ◽  
Input Variables ◽  
Monthly Streamflow Forecasting

scholarly journals Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models

2021 ◽  
Vol 13 (20) ◽  
pp. 4147
Author(s):  
Mohammed M. Alquraish ◽  
Mosaad Khadr
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Superior Performance ◽  
Support Vector ◽  
Streamflow Forecasting ◽  
Forecasting Models ◽  
Monthly Streamflow ◽  
Artificial Neural ◽  
Monthly Streamflow Forecasting

In this study, we aimed to investigate the hydrological performance of three gridded precipitation products—CHIRPS, RFE, and TRMM3B42V7—in monthly streamflow forecasting. After statistical evaluation, two monthly streamflow forecasting models—support vector machine (SVM) and artificial neural network (ANN)—were developed using the monthly temporal resolution data derived from these products. The hydrological performance of the developed forecasting models was then evaluated using several statistical indices, including NSE, MAE, RMSE, and R2. The performance measures confirmed that the CHIRPS product has superior performance compared to RFE 2.0 and TRMM data, and it could provide reliable rainfall estimates for use as input in forecasting models. Likewise, the results of the forecasting models confirmed that the ANN and SVM both achieved acceptable levels of accuracy for forecasting streamflow; however, the ANN model was superior (R2 = 0.898–0.735) to the SVM (R2 = 0.742–0.635) in both the training and testing periods.

scholarly journals Support Vector Machine and Neural Network based Model for Monthly Stream Flow Forecasting

2018 ◽  
Vol 7 (4.35) ◽  
pp. 683
Author(s):  
Nuratiah Zaini ◽  
Marlinda Abdul Malek ◽  
Marina Yusoff ◽  
Siti Fatimah Che Osmi ◽  
Nurul Hani Mardi ◽  
...  
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Hybrid Model ◽  
Peninsular Malaysia ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Design Development ◽  
Streamflow Forecasting ◽  
Monthly Streamflow ◽  
Bpnn Model

Accurate forecasting of streamflow is desired in many water resources planning and management, flood prevention and design development. In this study, the accuracy of two hybrid model, support vector machine - particle swarm optimization (SVM-PSO) and bat algorithm – backpropagation neural network (BA-BPNN) for monthly streamflow forecasting at Kuantan River located in Peninsular Malaysia are investigated and compared to regular SVM and BPNN model. Heuristic optimization namely PSO and BA are introduced to find the optimum SVM and BPNN parameters. The input parameters to the forecasting models are antecedent streamflow, historical rainfall and meteorological parameters namely evaporation, temperature, relative humidity and mean wind speed. Two performance evaluation measure, root mean square error (RMSE) and coefficient of determination (R2) were employed to evaluate the performance of developed forecasting model. It is found that, RMSE and R2 for hybrid SVM-PSO are 24.8267 m3/s and 0.9651 respectively while general SVM model yields RMSE of 27.5086 m3/s and 0.9305 of R2 for testing phase. Besides that, hybrid BA-BPNN produces RMSE, 17.7579 m3/s and R2, 0.7740 while BPNN model produces lower RMSE and R2 of 28.1396 m3/s and 0.5015 respectively. Therefore, the results indicate that hybrid model, SVM-PSO and Bat-BPNN yield better performance as compared to general SVM and BPNN, respectively in streamflow forecasting.

scholarly journals A multi-model integration method for monthly streamflow prediction: modified stacking ensemble strategy

2019 ◽  
Vol 22 (2) ◽  
pp. 310-326 ◽  
Author(s):  
Yujie Li ◽  
Zhongmin Liang ◽  
Yiming Hu ◽  
Binquan Li ◽  
Bin Xu ◽  
...  
Keyword(s):  
Integration Method ◽  
Model Integration ◽  
Support Vector ◽  
Climate Indices ◽  
Streamflow Forecasting ◽  
Forecast Performance ◽  
Extreme Gradient Boosting ◽  
Monthly Streamflow ◽  
Ensemble Strategy ◽  
Monthly Streamflow Forecasting

Abstract In this study, we evaluate elastic net regression (ENR), support vector regression (SVR), random forest (RF) and eXtreme Gradient Boosting (XGB) models and propose a modified multi-model integration method named a modified stacking ensemble strategy (MSES) for monthly streamflow forecasting. We apply the above methods to the Three Gorges Reservoir in the Yangtze River Basin, and the results show the following: (1) RF and XGB present better and more stable forecast performance than ENR and SVR. It can be concluded that the machine learning-based models have the potential for monthly streamflow forecasting. (2) The MSES can effectively reconstruct the original training data in the first layer and optimize the XGB model in the second layer, improving the forecast performance. We believe that the MSES is a computing framework worthy of development, with simple mathematical structure and low computational cost. (3) The forecast performance mainly depends on the size and distribution characteristics of the monthly streamflow sequence, which is still difficult to predict using only climate indices.

scholarly journals A Conjunction Method of Wavelet Transform-Particle Swarm Optimization-Support Vector Machine for Streamflow Forecasting

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Fanping Zhang ◽  
Huichao Dai ◽  
Deshan Tang
Keyword(s):  
Time Series ◽  
Support Vector Machine ◽  
Particle Swarm Optimization ◽  
Wavelet Transform ◽  
Correlation Coefficients ◽  
Support Vector ◽  
Streamflow Forecasting ◽  
Swarm Optimization ◽  
Svm Model ◽  
Monthly Streamflow

Streamflow forecasting has an important role in water resource management and reservoir operation. Support vector machine (SVM) is an appropriate and suitable method for streamflow prediction due to its best versatility, robustness, and effectiveness. In this study, a wavelet transform particle swarm optimization support vector machine (WT-PSO-SVM) model is proposed and applied for streamflow time series prediction. Firstly, the streamflow time series were decomposed into various details (Ds) and an approximation (A3) at three resolution levels (21-22-23) using Daubechies (db3) discrete wavelet. Correlation coefficients between eachDsubtime series and original monthly streamflow time series are calculated.Dscomponents with high correlation coefficients (D3) are added to the approximation (A3) as the input values of the SVM model. Secondly, the PSO is employed to select the optimal parameters,C,ε, andσ, of the SVM model. Finally, the WT-PSO-SVM models are trained and tested by the monthly streamflow time series of Tangnaihai Station located in Yellow River upper stream from January 1956 to December 2008. The test results indicate that the WT-PSO-SVM approach provide a superior alternative to the single SVM model for forecasting monthly streamflow in situations without formulating models for internal structure of the watershed.

scholarly journals Selected model fusion: an approach for improving the accuracy of monthly streamflow forecasting

2018 ◽  
Vol 20 (4) ◽  
pp. 917-933 ◽  
Author(s):  
Fereshteh Modaresi ◽  
Shahab Araghinejad ◽  
Kumars Ebrahimi
Keyword(s):  
Neural Network ◽  
Nearest Neighbor ◽  
Least Square ◽  
Support Vector ◽  
Generalized Regression Neural Network ◽  
Streamflow Forecasting ◽  
K Nearest Neighbor ◽  
Model Fusion ◽  
Monthly Streamflow ◽  
Monthly Streamflow Forecasting

Abstract Monthly streamflow forecasting plays an important role in water resources management, especially for dam operation. In this paper, an approach of model fusion technique named selected model fusion (SMF) is applied and assessed under two strategies of model selection in order to improve the accuracy of streamflow forecasting. The two strategies of SMF are: fusion of the outputs of best individual forecasting models (IFMs) selected by dendrogram analysis (S1), and fusion of the best outputs of all IFMs resulting from an ordered selection algorithm (S2). In both strategies, five data-driven models including: artificial neural network, generalized regression neural network, least square-support vector regression, K-nearest neighbor regression, and multiple linear regression with optimized structure are performed as IFMs. The SMF strategies are applied for forecasting the monthly inflow to Karkheh reservoir, Iran, owning various patterns between predictor and predicted variables in different months. Results show that applying SMF approach based on both strategies results in more accurate forecasts in comparison with fusion of all IFMs outputs (S3), as the benchmark. However, comparison of the two SMF strategies reveals that the implementation of strategy (S2) considerably improves the accuracy of forecasts than strategy (S1) as well as the best IFM results (S4) in all months.

scholarly journals Three-Dimensional Site Characterization Model of Bangalore Using Support Vector Machine

2012 ◽  
Vol 2012 ◽  
pp. 1-10
Author(s):  
Pijush Samui
Keyword(s):  
Support Vector Machine ◽  
Three Dimensional ◽  
Site Characterization ◽  
Standard Penetration Test ◽  
Support Vector ◽  
Characterization Model ◽  
Svm Model ◽  
Input Variables ◽  
Learning Machine ◽  
A Site

The main objective of site characterization is the prediction of in situ soil properties at any half-space point at a site based on limited tests. In this study, the Support Vector Machine (SVM) has been used to develop a three dimensional site characterization model for Bangalore, India based on large amount of Standard Penetration Test. SVM is a novel type of learning machine based on statistical learning theory, uses regression technique by introducing ε-insensitive loss function. The database consists of 766 boreholes, with more than 2700 field SPT values () spread over 220 sq km area of Bangalore. The model is applied for corrected () values. The three input variables (, , and , where , , and are the coordinates of the Bangalore) were used for the SVM model. The output of SVM was the data. The results presented in this paper clearly highlight that the SVM is a robust tool for site characterization. In this study, a sensitivity analysis of SVM parameters (σ, , and ε) has been also presented.

Sign in / Sign up

Export Citation Format

Share Document