Applicability of ε-Support Vector Machine and Artificial Neural Network for Flood Forecasting in Humid, Semi-Humid and Semi-Arid Basins in China

Bafitlhile, Thabo Michael; Li, Zhijia

doi:10.3390/w11010085

Cited by 73 publications

(36 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mahmud et al [12] 31 March 2018 2 4 1 1 Rhee and Yang [13] 14 June 2018 2 2 0 0 Khan et al [14] 27 July 2018 2 2 1 1 Mousavi et al [15] 16 October 2018 2 3 1 1 Amnatsan et al [16] 9 November 2018 3 3 0 0 Bafitlhile and Li [17] 6 January 2019 3 3 1 1 Pan et al [18] 22 January 2019 2 2 0 0 Ávila et al [19] 22 February 2019 4 5 2 1 Pham et al [20] 3 March 2019 3 3 1 1 Tung et al [21] 8 March 2019 2 2 0 0 Dawley et al [22] 5 April 2019 3 3 0 0 Zhang and Wang [23] 4 June 2019 2 5 0 0 Mehmood et al [24] 14 June 2019 3 5 0 0…”

Section: Overview Of the Special Issue Contributionsmentioning

confidence: 99%

“…Owing to the importance of reservoir inflow forecasting for appropriate reservoir management, especially in the flood season, the variation analogue method (VAM), the W-ANN, and the weighted mean analogue method (WMAM) were used to forecast reservoir inflows by Amnatsan et al [16]. In another study, Bafitlhile and Li [17] applied ε-Support Vector Machine (ε-SVM) and ANN for the simulation and forecasting streamflow of three catchments with humid, semi-humid and semi-arid climates. To optimize the ANN and SVM sensitive parameters, the Evolutionary Strategy (ES) optimization method was used.…”

Section: Case Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Statistical Analysis and Stochastic Modelling of Hydrological Extremes

Tabari

2019

Water

View full text Add to dashboard Cite

Analysis of hydrological extremes is challenging due to their rarity and small sample size and the interconnections between different types of extremes and gets further complicated by an untrustworthy representation of meso-scale processes involved in extreme events by coarse spatial and temporal scale models as well as biased or missing observations due to technical difficulties during extreme conditions. The special issue “Statistical Analysis and Stochastic Modelling of Hydrological Extremes”—motivated by the need to apply and develop innovative stochastic and statistical approaches to analyze hydrological extremes under current and future climate conditions —encompass 13 research papers. Case studies presented in the papers exploit a wide range of innovative techniques for hydrological extremes analyses. The papers focus on six topics: Historical changes in hydrological extremes, projected changes in hydrological extremes, downscaling of hydrological extremes, early warning and forecasting systems for drought and flood, interconnections of hydrological extremes and applicability of satellite data for hydrological studies. This Editorial provides an overview of the covered topics and reviews the case studies relevant for each topic.

show abstract

Section: Overview Of the Special Issue Contributionsmentioning

confidence: 99%

Section: Case Studiesmentioning

confidence: 99%

Statistical Analysis and Stochastic Modelling of Hydrological Extremes

Tabari

2019

Water

View full text Add to dashboard Cite

show abstract

“…This may have been due to the fact that the representativeness of the forecast dataset is not strong, and that the correlation between the Arid-Pa and runoff series is unstable. In fact, many potential factors are involved in runoff generation (Bafitlhile & Li, 2019), thus the forecasting deviations are unavoidable, and there are many reasons for these deviations. It is worth noting that the model does not select the soil surface characteristics as input factors, which has an impact on runoff generation (Ribolzi et al, 2007), and may even exceed the slope (Descroix, Gonzalez Barrios, Vandervaere, Viramontes, & Bollery, 2002).…”

Section: Discussionmentioning

confidence: 99%

Research and application of an intelligent networking model for flood forecasting in the arid mountainous basins

Yuan

Zhang

Tian

2020

J Flood Risk Management

View full text Add to dashboard Cite

Storm floods occur frequently and have complex characteristics in arid mountainous areas, which for a long time has been a weak link in flood forecasting. The application of an artificial intelligent model and physically-based hydrological model has some limitations on flood forecasting in arid mountainous areas with scarce data. In this article, the ANN model and Muskingum-Cunge method are combined to propose an intelligent networking model for flood forecasting (FFIN model) in arid mountainous areas with scarce data, which BR-ANN model is used to forecast the flood in the catchment sub-basin with runoff data, while the General Regression Neural Network model is used to carry out flood parallel forecast in the catchment sub-basin without runoff data. The Muskingum-Cunge method is used to connect the sub-basins and form a confluence network, so as to simulate the flood routing process in river. The verification and comparison results in study area show that the FFIN model has a superior overall forecasting ability. For the forecasting period, the evaluation index Kling-Gupta efficiency is 0.88, Nash efficiency coefficient is 0.982 and forecasting deviation of flood peak flow is 7.15%. The FFIN model can be effectively applied to flood forecasting in arid mountainous areas with scarce runoff data.

show abstract

“…With the rapid development of computer technology, data-driven models have gained more applications in the field of hydrological forecasting (Bafitlhile & Li 2019). The artificial neural networks (ANNs), a common data-driven model based on artificial intelligence, were applied in flood forecasting at the end of the last century already (Hsu et al 1995;Shamseldin 1997;Abdellatif et al 2013).…”

Section: Introductionmentioning

confidence: 99%

Application of temporal convolutional network for flood forecasting

et al. 2024

Artificial Intelligence in Hydrology

View full text Add to dashboard Cite

Rainfall–runoff modeling is a complex nonlinear time-series problem in the field of hydrology. Various methods, such as physical-driven and data-driven models, have been developed to study the highly random rainfall–runoff process. In the past 2 years, with the advancement of computing hardware resources and algorithms, deep-learning methods, such as temporal convolutional network (TCN), has been shown good prospects in time-series prediction tasks. The aim of this study is to develop a prediction model based on TCN structure to simulate the hourly rainfall–runoff relationship. We use two datasets in the Jingle and Kuye watersheds to test the model under different network structures and compare with the other four models. The results show that the TCN model outperforms the EIESM, artificial neural network, and long short-term memory and improves the flood forecasting accuracy at different foreseeable periods. It is shown that the TCN has a faster convergence rate and is an effective method for hydrological forecasting.

show abstract

Applicability of ε-Support Vector Machine and Artificial Neural Network for Flood Forecasting in Humid, Semi-Humid and Semi-Arid Basins in China

Cited by 73 publications

References 68 publications

Statistical Analysis and Stochastic Modelling of Hydrological Extremes

Statistical Analysis and Stochastic Modelling of Hydrological Extremes

Research and application of an intelligent networking model for flood forecasting in the arid mountainous basins

Application of temporal convolutional network for flood forecasting

Contact Info

Product

Resources

About