Investigating a complex lake-catchment-river system using artificial neural networks: Poyang Lake (China)

被引:83
作者
Li, Y. L. [1 ]
Zhang, Q. [1 ,2 ]
Werner, A. D. [3 ,4 ]
Yao, J. [1 ]
机构
[1] Chinese Acad Sci, Nanjing Inst Geog & Limnol, Key Lab Watershed Geog Sci, Nanjing, Jiangsu, Peoples R China
[2] Jiangxi Normal Univ, Minist Educ, Key Lab Poyang Lake Wetland & Watershed Res, Nanchang, Peoples R China
[3] Flinders Univ S Australia, Natl Ctr Groundwater Res & Training, Adelaide, SA 5001, Australia
[4] Flinders Univ S Australia, Sch Environm, Adelaide, SA 5001, Australia
来源
HYDROLOGY RESEARCH | 2015年 / 46卷 / 06期
基金
中国国家自然科学基金;
关键词
artificial neural networks; lake river interaction; lake water level; Poyang Lake; Yangtze River; WATER-LEVEL FLUCTUATIONS; YANGTZE-RIVER; HYDRODYNAMIC MODEL; MODIS OBSERVATIONS; CLIMATE-CHANGE; FLOW; VARIABILITY; SIMULATION; PREDICTION; STREAMFLOW;
D O I
10.2166/nh.2015.150
中图分类号
TV21 [水资源调查与水利规划];
学科分类号
081501 ;
摘要
Lake hydrological simulations using physically based models are cumbersome due to extensive data and computational requirements. Despite an abundance of previous modeling investigations, realtime simulation tools for large lake systems subjected to multiple stressors are lacking. The back propagation neural network (BPNN) is applied as a first attempt to simulate the water-level variations of a large lake, exemplified by the Poyang Lake (China) case study. The BPNN investigation extends previous modeling efforts by considering the Yangtze River effect and evaluating the influence of the Yangtze River on the lake water levels. Results indicate that the effects of both the lake catchment and the Yangtze River are required to produce reasonable BPNN calibration statistics. Modeling results suggest that the Yangtze River plays a significant role in modifying the lake water-level changes. Comparison of BPNN models to a 2D hydrodynamic model (MIKE 21) shows that comparable accuracies can be obtained from both modeling approaches. This implies that the BPNN approach is well suited to long-term predictions of the water-level responses of Poyang Lake. The findings of this work demonstrate that BPNN can be used as a valuable and computationally efficient tool for future water resource planning and management of the Poyang Lake.
引用
收藏
页码:912 / 928
页数:17
相关论文
共 70 条
[1]   Forecasting surface water level fluctuations of lake van by artificial neural networks [J].
Altunkaynak, Adduesselam .
WATER RESOURCES MANAGEMENT, 2007, 21 (02) :399-408
[2]  
[Anonymous], 3 DIMENSIONAL ENV FL
[3]  
[Anonymous], 2007, MIKE 21 flow model: Hydrodynamic module user guide, P1
[4]  
Barua D. K., 2006, P 30 INT C COAST ENG, P1590
[5]  
Barzen J., 2009, Potential impacts of a water control structure on the abundance and distribution of wintering waterbirds at Poyang Lake, P1
[6]   An integrated catchment-coastal modelling system for real-time water quality forecasts [J].
Bedri, Zeinab ;
Corkery, Aisling ;
O'Sullivan, John J. ;
Alvarez, Marcos X. ;
Erichsen, Anders Chr. ;
Deering, Louise A. ;
Demeter, Katalin ;
O'Hare, Gregory M. P. ;
Meijer, Wim G. ;
Masterson, Bartholomew .
ENVIRONMENTAL MODELLING & SOFTWARE, 2014, 61 :458-476
[7]  
Bell A.K., 2005, P NAT HYDR SEM, P77
[8]  
Box G.E. P., 1994, TIME SERIES ANAL, P1
[9]   Predicting typhoon-induced storm surge tide with a two-dimensional hydrodynamic model and artificial neural network model [J].
Chen, W. -B. ;
Liu, W. -C. ;
Hsu, M. -H. .
NATURAL HAZARDS AND EARTH SYSTEM SCIENCES, 2012, 12 (12) :3799-3809
[10]   Comparison of ANN approach with 2D and 3D hydrodynamic models for simulating estuary water stage [J].
Chen, Wei-Bo ;
Liu, Wen-Cheng ;
Hsu, Ming-Hsi .
ADVANCES IN ENGINEERING SOFTWARE, 2012, 45 (01) :69-79