A fully-online Neuro-Fuzzy model for flow forecasting in basins with limited data

被引:42
作者
Ashrafi, Mohammad [1 ]
Chua, Lloyd Hock Chye [1 ,2 ]
Quek, Chai [3 ]
Qin, Xiaosheng [1 ,4 ]
机构
[1] Nanyang Technol Univ, Sch Civil & Environm Engn, 50 Nanyang Ave, Singapore 639798, Singapore
[2] Deakin Univ, Fac Sci Engn & Built Environm, Sch Engn, Locked Bag 20000, Geelong, Vic 3220, Australia
[3] Nanyang Technol Univ, Sch Comp Sci & Engn, Computat Intelligence Lab, 50 Nanyang Ave, Singapore 639798, Singapore
[4] Nanyang Technol Univ, EPMC, NEWRI, 1 Cleantech Loop, Singapore 637141, Singapore
关键词
Runoff forecasting; Online; Neuro-fuzzy model; Self-Evolving Takagi-Sugeno-Kang; Mekong River; TIME; RAINFALL; NETWORK; IDENTIFICATION;
D O I
10.1016/j.jhydrol.2016.11.057
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Current state-of-the-art online neuro fuzzy models (NFMs) such as DENFIS (Dynamic Evolving Neural Fuzzy Inference System) have been used for runoff forecasting. Online NFMs adopt a local learning approach and are able to adapt to changes continuously. The DENFIS model however requires upper/ lower bound for normalization and also the number of rules increases monotonically. This requirement makes the model unsuitable for use in basins with limited data, since a priori data is required. In order to address this and other drawbacks of current online models, the Generic Self-Evolving Takagi-SugenoKang (GSETSK) is adopted in this study for forecast applications in basins with limited data. GSETSK is a fully-online NFM which updates its structure and parameters based on the most recent data. The model does not require the need for historical data and adopts clustering and rule pruning techniques to generate a compact and up-to-date rule-base. GSETSK was used in two forecast applications, rainfall runoff (a catchment in Sweden) and river routing (Lower Mekong River) forecasts. Each of these two applications was studied under two scenarios: (i) there is no prior data, and (ii) only limited data is available (1 year for the Swedish catchment and 1 season for the Mekong River). For the Swedish Basin, GSETSK model results were compared to available results from a calibrated HBV (Hydrologiska Byrans Vattenbalansavdelning) model. For the Mekong River, GSETSK results were compared against the URBS (Unified River Basin Simulator) model. Both comparisons showed that results from GSETSK are comparable with the physically based models, which were calibrated with historical data. Thus, even though GSETSK was trained with a very limited dataset in comparison with HBV or URBS, similar results were achieved. Similarly, further comparisons between GSETSK with DENFIS and the RBF (Radial Basis Function) models highlighted further advantages of GSETSK as having a rule-base (compared to opaque RBF) which is more compact, up-to-date and more easily interpretable. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码:424 / 435
页数:12
相关论文
共 39 条
[1]   An approach to Online identification of Takagi-Suigeno fuzzy models [J].
Angelov, PP ;
Filev, DP .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2004, 34 (01) :484-498
[2]  
[Anonymous], STAT DIGITAL SIGNAL
[3]   A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runoff [J].
Aqil, Muhammad ;
Kita, Ichiro ;
Yano, Akira ;
Nishiyama, Soichi .
JOURNAL OF HYDROLOGY, 2007, 337 (1-2) :22-34
[4]   A nonlinear spatio-temporal lumping of radar rainfall for modeling multi-step-ahead inflow forecasts by data-driven techniques [J].
Chang, Fi-John ;
Tsai, Meng-Jung .
JOURNAL OF HYDROLOGY, 2016, 535 :256-269
[5]   Watershed rainfall forecasting using neuro-fuzzy networks with the assimilation of multi-sensor information [J].
Chang, Fi-John ;
Chiang, Yen-Ming ;
Tsai, Meng-Jung ;
Shieh, Ming-Chang ;
Hsu, Kuo-Lin ;
Sorooshian, Soroosh .
JOURNAL OF HYDROLOGY, 2014, 508 :374-384
[6]   A counterpropagation fuzzy-neural network modeling approach to real time streamflow prediction [J].
Chang, FJ ;
Chen, YC .
JOURNAL OF HYDROLOGY, 2001, 245 (1-4) :153-164
[7]   Comparison of several flood forecasting models in Yangtze river [J].
Chau, KW ;
Wu, CL ;
Li, YS .
JOURNAL OF HYDROLOGIC ENGINEERING, 2005, 10 (06) :485-491
[8]   The strategy of building a flood forecast model by neuro-fuzzy network [J].
Chen, SH ;
Lin, YH ;
Chang, LC ;
Chang, FJ .
HYDROLOGICAL PROCESSES, 2006, 20 (07) :1525-1540
[9]   Developing a hybrid multi-model for peak flood forecasting [J].
Chidthong, Yupa ;
Tanaka, Hitoshi ;
Supharatid, Seree .
HYDROLOGICAL PROCESSES, 2009, 23 (12) :1725-1738
[10]   Hydrological time-series modelling using an adaptive neuro-fuzzy inference system [J].
Firat, Mahmut ;
Gungor, Mahmud .
HYDROLOGICAL PROCESSES, 2008, 22 (13) :2122-2132