Integrating Support Vector Regression and a geomorphologic Artificial Neural Network for daily rainfall-runoff modeling

Hosseini, Seiyed Mossa; Mahjouri, Najmeh

doi:10.1016/j.asoc.2015.09.049

Cited by 82 publications

(56 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chen et al [15] used SVMs to predict daily precipitation in the Hanjiang basin. The SVM technique has also been successful recently in solving forestry problems [16], in determining the solar irradiation [17], in predicting the real-time flood [18], and in predicting the daily rainfall-runoff [19]. An extensive review of the SVM applications in the field of hydrology is provided by Raghavendra and Deka [20].…”

Section: Introductionmentioning

confidence: 99%

Support Vector Regression for Rainfall-Runoff Modeling in Urban Drainage: A Comparison with the EPA’s Storm Water Management Model

Granata

Gargano

Marinis

2016

Water

129

View full text Add to dashboard Cite

Abstract:Rainfall-runoff models can be classified into three types: physically based models, conceptual models, and empirical models. In this latter class of models, the catchment is considered as a black box, without any reference to the internal processes that control the transformation of rainfall to runoff. In recent years, some models derived from studies on artificial intelligence have found increasing use. Among these, particular attention should be paid to Support Vector Machines (SVMs). This paper shows a comparative study of rainfall-runoff modeling between a SVM-based approach and the EPA's Storm Water Management Model (SWMM). The SVM is applied in the variant called Support Vector regression (SVR). Two different experimental basins located in the north of Italy have been considered as case studies. Two criteria have been chosen to assess the consistency between the recorded and predicted flow rates: the root-mean square error (RMSE) and the coefficient of determination. The two models showed comparable performance. In particular, both models can properly model the hydrograph shape, the time to peak and the total runoff. The SVR algorithm tends to underestimate the peak discharge, while SWMM tends to overestimate it. SVR shows great potential for applications in the field of urban hydrology, but currently it also has significant limitations regarding the model calibration.

show abstract

Section: Introductionmentioning

confidence: 99%

Support Vector Regression for Rainfall-Runoff Modeling in Urban Drainage: A Comparison with the EPA’s Storm Water Management Model

Granata

Gargano

Marinis

2016

Water

129

View full text Add to dashboard Cite

show abstract

“…polynomial, sigmoid or RBF, can be used in nonlinear case. RBF and sigmoid kernels used in this paper are defined as presented in [11,[15][16][17][18]:…”

Section: Support Vector Machines For Regressionmentioning

confidence: 99%

“…Grenata et al (2015) applied SVMs for rainfall-runoff modelling using the SVM regression variant called Support Vector Regression (SVR) for two experimental basins located in northern Italy [14]. Hosseini and Mahjouri (2016) presented a new rainfall-runoff model called SVR-GANN, where the SVR model is combined with a geomorphology-based ANN model in a case study of three sub-basins located in a semiarid region in Iran [15]. Gizaw and Gun (2016) developed the Regional Flood Frequency Analysis (RFFA) model based on SVR to estimate regional flood quantiles for two study areas in Canada [16].…”

Section: Introductionmentioning

confidence: 99%

Application of artificial neural networks for hydrological modelling in Karst

Lakušić¹

2018

JCE

View full text Add to dashboard Cite

Application of artificial neural networks for hydrological modelling in karstThe possibility of short-term water flow forecasting in a karst region is presented in this paper. Four state-of-the-art machine learning algorithms are used for the one day ahead forecasting: multi-layer perceptron neural network, radial basis function neural network, support vector machines for regression (SVR), and adaptive neuro fuzzy inference system (ANFIS). The results show that the ANFIS model outperforms other algorithms when the root mean square error and mean absolute error are used as quality indicators. Primjena neuronskih mreža za hidrološko modeliranje u krškom području U ovom radu je razmatrana mogućnost kratkoročnog predviđanja protoka vode u krškom području. Četiri suvremena algoritma strojnog učenja su korištena za predviđanje protoka jedan dan unaprijed i to: neuronska mreža s višeslojnim perceptronom, neuronska mreža s radijalnom aktivacijskom funkcijom, metoda potpornih vektora za regresiju (SVR), adaptivni neuroneizraziti (fuzzy) sustav zaključivanja (ANFIS). Rezultati pokazuju da ANFIS model nadmašuje ostale algoritme kada se korijen srednje kvadratne popogreške i srednja apsolutna pogreška upotrijebe kao mjere kvalitete.

show abstract

“…However, it is known that ANN models incur the disadvantages of local minima and problems of overfitting. The SVM can overcome these drawbacks (Hosseini and Mahjouri 2016). Comparative studies on the SVM and the ANN have been performed in the context of GWL prediction.…”

Section: Introductionmentioning

confidence: 99%

Short-term prediction of groundwater level using improved random forest regression with a combination of random features

et al. 2018

View full text Add to dashboard Cite

To solve the problem where by the available on-site input data are too scarce to predict the level of groundwater, this paper proposes an algorithm to make this prediction called the canonical correlation forest algorithm with a combination of random features. To assess the effectiveness of the proposed algorithm, groundwater levels and meteorological data for the Daguhe River groundwater source field, in Qingdao, China, were used. First, the results of a comparison among three regressors showed that the proposed algorithm is superior in terms of forecasting variations in groundwater level. Second, the results of experiments were used to show the comparative superiority of the proposed method in terms of training time and complexity of parameter optimization. Third, using the proposed algorithm, the highest prediction accuracy was achieved by employing precipitation P(t − 2), temperature T(t), and groundwater level H(t) as the best time lag. This improved random forest regression model yielded higher accuracy in forecasting the variation in groundwater level. The proposed algorithm can also be applied to cases involving low-dimensional data.

show abstract

Integrating Support Vector Regression and a geomorphologic Artificial Neural Network for daily rainfall-runoff modeling

Cited by 82 publications

References 55 publications

Support Vector Regression for Rainfall-Runoff Modeling in Urban Drainage: A Comparison with the EPA’s Storm Water Management Model

Support Vector Regression for Rainfall-Runoff Modeling in Urban Drainage: A Comparison with the EPA’s Storm Water Management Model

Application of artificial neural networks for hydrological modelling in Karst

Short-term prediction of groundwater level using improved random forest regression with a combination of random features

Contact Info

Product

Resources

About