Support Vector Machines Identification for Runoff Modelling

Han, Da; Cluckie, ID

doi:10.1142/9789812702838_0197

Cited by 20 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on previous studies (Dibike et al 2001;Sivapragasam et al 2001;Choy and Chan 2003;Han and Cluckie 2004;Yu et al 2004;Seo et al 2015b), RBF was chosen as the kernel function to build up the SVM and WPSVM models. Meanwhile, the accuracy of the SVM and WPSVM models significantly depends on the appropriate selection of their parameters.…”

Section: Discussionmentioning

confidence: 99%

River Stage Forecasting Using Wavelet Packet Decomposition and Machine Learning Models

Seo

Kim

Kisi

et al. 2016

Water Resour Manage

View full text Add to dashboard Cite

This study develops and applies three hybrid models, including wavelet packetartificial neural network (WPANN), wavelet packet-adaptive neuro-fuzzy inference system (WPANFIS) and wavelet packet-support vector machine (WPSVM), combining wavelet packet decomposition (WPD) and machine learning models, ANN, ANFIS and SVM models, for forecasting daily river stage and evaluates their performance. The WPANN, WPANFIS and WPSVM models using inputs decomposed by the WPD are found to produce higher efficiency based on statistical performance criteria than the ANN, ANFIS and SVM models using original inputs. Performance evaluation for various mother wavelets indicates that the model Water Resour Manage performance is dependent on mother wavelets and the WPD using Symmlet-10 and Coiflet-18 is more effective to enhance the efficiency of the conventional machine learning models than other mother wavelets. It is found that the WPANFIS model outperforms the WPANN and WPSVM models, and the WPANFIS14-coif18 model produces the best performance among all other models in terms of model efficiency. Therefore, the WPD can significantly enhance the accuracy of the conventional machine learning models, and the conjunction of the WPD and machine learning models can be an effective tool for forecasting daily river stage accurately .

show abstract

Section: Discussionmentioning

confidence: 99%

River Stage Forecasting Using Wavelet Packet Decomposition and Machine Learning Models

Seo

Kim

Kisi

et al. 2016

Water Resour Manage

View full text Add to dashboard Cite

show abstract

“…Dibike et al (2001), Han and Cluckie (2004) explained the benefits of the radial basis function over other kernel functions. Additionally, many works in hydrological modeling and forecasting have demonstrated the successful application of the radial basis function in SVR (e.g.…”

Section: Methodology Support Vector Regressionmentioning

confidence: 99%

Pruning of support vector networks on flood forecasting

Chen

2007

Journal of Hydrology

View full text Add to dashboard Cite

“…Dibike et al (2001) applied different kernels in SVR to rainfall-runoff modeling and demonstrated that the radial basis function outperforms other kernel functions. Han and Cluckie (2004) indicated that the centralized feature of the radial basis function enables it effectively to model the regression process. Also, many works on the use of SVR in hydrological modeling and forecasting have demonstrated the favorable performance of the radial basis function (Liong and Sivapragasam, 2002;Choy and Chan, 2003;Yu et al, 2004).…”

Section: Calibrating Parametersmentioning

confidence: 99%