|
|
|
| Support vector regression based model for predicting water level of Dongting Lake |
| WANG Mengmeng1, DAI Lingquan1, DAI Huichao1,2, MAO Jingqiao2, LIANG Lu3 |
| 1.College of Hydraulic and Environmental Engineering, China Three Gorges University, Yichang, Hubei 443002, China; 2.College of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing, Jiangsu 210098, China; 3.Shenzhen Water Planning & Design Institute Co. Ltd., Shenzhen, Guangdong 518036, China |
|
|
|
|
Abstract To predict the water level of Dongting Lake rapidly and accurately under the influence of the impoundment of Three Gorges Reservoir(TGR), a model was established based on support vector regression(SVR)method. The average daily discharges of TGR, Qingjiang and the other four rivers connected to Dongting Lake in 2006—2009 were used as input variables to train and test the model. The water levels at Chenglingji Station and the other five representative stations in the east, south and west of the lake were selected as output variables. It was shown that the mean squared errors(MSE)of the trained and tested data sets are 6.130×10-4 and 1.477×10-3, respectively, and the coefficient of determination is 0.980 7. To analyze effects caused by the impoundment of TGR quantitatively, the discharge of TGR was replaced with the inflow rate but the discharges from the rest sources remain unchanged to train the model. The well-trained model was utilized to restore the water level variation process without any regulation of TGR and the simulated results were contrasted with the measured water levels. The results showed that the water level at Chenglingji Station which is in the north of the lake and Nanzui Station which is in the north of the west Dongting Lake are significantly influenced by the impoundment of TGR because these stations are near Yangtze River and have closely hydraulic interaction with it. Contrarily, the water level in the south Dongting Lake region is less affected.
|
|
Received: 06 June 2017
|
|
|
|
| [1]YUAN Yujie, ZENG Guangming, LIANG Jie, et al. Variation of water level in Dongting Lake over a 50-year period: implications for the impacts of anthropogenic and climatic factors[J]. Journal of hydrology, 2015,525:450-456.[2]李义天, 郭小虎, 唐金武, 等. 三峡水库蓄水后荆江三口分流比估算[J]. 天津大学学报, 2008,41(9):1027-1034. LI Yitian, GUO Xiaohu, TANG Jinwu, et al. Estimation of flow of Three Diversions in the Jingjiang river after the operation of the Three Gorges Reservoir[J]. Journal of Tianjin University, 2008,41(9):1027-1034.(in Chinese)[3]朱玲玲, 许全喜, 戴明龙. 荆江三口分流变化及三峡水库蓄水影响[J]. 水科学进展, 2016,27(6):822-831. ZHU Lingling, XU Quanxi, DAI Minglong. Runoff diverted from the Jingjiang reach to the Dongting lake and the effect of Three Gorges Reservoir[J]. Advances in water science, 2016,27(6):822-831.(in Chinese)[4]宫平, 杨文俊. 三峡水库建成后对长江中下游江湖水沙关系变化趋势初探Ⅱ.江湖关系及槽蓄影响初步研究[J]. 水力发电学报, 2009,28(6):120-125. GONG Ping, YANG Wenjun. Preliminary study of river-lake evolution effect due to Three Gorges project. Part 2: the effect on river-lake relation and channel storage capacity[J]. Journal of hydroelectric engineering, 2009,28(6):120-125.(in Chinese)[5]方春明, 胡春宏, 陈绪坚. 三峡水库运用对荆江三口分流及洞庭湖的影响[J]. 水利学报, 2014,45(1):36-41. FANG Chunming, HU Chunhong, CHEN Xujian. Impacts of Three Georges Reservoir’s operation on outflow of the three outlets of Jingjiang river and Dongting lake[J]. Journal of hydraulic engineering, 2014,45(1):36-41.(in Chinese)[6]黄维, 王为东. 三峡工程运行后对洞庭湖湿地的影响[J]. 生态学报, 2016,36(20):6345-6352. HUANG Wei, WANG Weidong. Effects of Three Gorges dam project on Dongting lake wetlands[J]. Acta ecologica sinica, 2016,36(20):6345-6352.(in Chinese)[7]LI Zhongwu, NIE Xiaodong, ZHANG Yan, et al. Assessing the influence of water level on schistosomiasis in Dongting lake region before and after the construction of Three Gorges Dam[J]. Environmental monitoring and assessment, 2016,188(1):1-10.[8]XIE Yonghong, TANG Yue, CHEN Xinsheng, et al. The impact of Three Gorges Dam on the downstream eco-hydrological environment and vegetation distribution of East Dongting Lake[J]. Ecohydrology, 2015,8(4):738-746.[9]DAI Zhijun, DU Jinzhou, CHU Ao, et al. Groundwater discharge to the Changjiang River, China, during the drought season of 2006: effects of the extreme drought and the impoundment of the Three Gorges Dam[J]. Hydrogeology journal, 2010,18(2):359-369.[10]丛振涛, 肖鹏, 章诞武, 等. 三峡工程运行前后城陵矶水位变化及其原因分析[J]. 水力发电学报, 2014,33(3):23-28. CONG Zhentao, XIAO Peng, ZHANG Danwu, et al. Water stage at Chenglingji before and after the Three Gorges project[J]. Journal of hydroelectric engineering, 2014,33(3):23-28.(in Chinese)[11]张细兵, 卢金友, 王敏, 等. 三峡工程运用后洞庭湖水沙情势变化及其影响初步分析[J]. 长江流域资源与环境, 2010,19(6):640-643. ZHANG Xibing, LU Jinyou, WANG Min, et al. Preliminary study on flow and sediment changing and influence on Dongting Lake after the Three Gorges Project operation[J]. Resources and environment in the Yangtze basin, 2010,19(6):640-643.(in Chinese)[12]CHEN Yongcan, WANG Zhiyong, LIU Zhaowei, et al. 1D-2D coupled numerical model for shallow-water flows[J]. Journal of hydraulic engineering, 2012,138(2):122-132.[13]LAI Xijun, LIANG Qiuhua, JIANG Jiahu, et al. Impoundment effects of the Three-Gorges-Dam on flow regimes in two China′s largest freshwater lakes[J]. Water resources management, 2014,28(14):5111-5124.[14]马乐宽, 邱瑀, 赵越, 等. 基于改进的神经网络与支持向量机的小流域日径流量预测研究[J]. 水资源与水工程学报, 2016,27(5):23-27. MA Lekuan, QIU Yu, ZHAO Yue, et al. Prediction of daily runoff in a small watershed based on improved neural network and support vector machine(SVM)[J]. Journal of water resources & water engineering, 2016,27(5):23-27.(in Chinese)[15]孙占东, 黄群, 姜加虎, 等. 洞庭湖近年干旱与三峡蓄水影响分析[J]. 长江流域资源与环境, 2015,24(2):251-256. SUN Zhandong, HUANG Qun, JIANG Jiahu, et al. Recent hydrological droughts in Dongting Lake and its association with the operation of Three Gorges Reservoir[J]. Resources and environment in the Yangtze basin, 2015,24(2):251-256.(in Chinese)[16]于国强, 张茂省, 王根龙, 等. 支持向量机和BP神经网络在泥石流平均流速预测模型中的比较与应用[J]. 水利学报, 2012,43(S2):105-110. YU Guoqiang, ZHANG Maosheng, WANG Genlong, et al. Application and comparison of prediction models of support vector machines and back-propagation artificial neural network for debris flow average velocity[J]. Journal of hydraulic engineering, 2012,43(S2):105-110.(in Chinese)[17]BABANGIDA N M, MUSTAFA M, YUSUF K W, et al. Prediction of pore-water pressure response to rainfall using support vector regression[J]. Hydrogeology journal, 2016,24(7):1821-1833.[18]刘广东. 基于支持向量机的地面驱动螺杆泵井工况诊断技术[J]. 排灌机械工程学报, 2014,32(2):125-129. LIU Guangdong. Working conditions diagnosis of surface-driving progressive cavity pump wells based on support vector machine[J]. Journal of drainage and irrigation machinery engineering, 2014,32(2):125-129.(in Chinese)[19]陈海涛, 梁富山. 基于支持向量机的地下水位预测[J]. 华北水利水电学院学报, 2011,32(2):11-14. CHEN Haitao, LIANG Fushan. Underground water level prediction based on support vector machine[J]. Journal of North China Institute of Water Conservancy and Hydroelectric Power, 2011,32(2):11-14.(in Chinese)[20]丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011,40(1):2-10. DING Shifei, QI Bingjuan, TAN Hongyan. An overview on theory and algorithm of support vector machines[J]. Journal of University of Electronic Science and Technology of China, 2011,40(1):2-10.(in Chinese)[21]PATEL S S, RAMACHANDRAN P. A comparison of machine learning techniques for modeling river flow time series: the case of upper Cauvery river basin[J]. Water resources management, 2015,29(2):589-602.[22]王霞, 王占岐, 金贵, 等. 基于核函数支持向量回归机的耕地面积预测[J]. 农业工程学报, 2014,30(4):204-211. WANG Xia, WANG Zhanqi, JIN Gui, et al. Land reserve prediction using different kernel based support vector regression[J]. Transactions of the CSAE, 2014,30(4):204-211.(in Chinese)[23]水利部长江水利委员会水文局. 长江流域洪水预报方案汇编[R]. 武汉: 水利部长江水利委员会水文局, 2005.[24]DAI Lingquan, DAI Huichao, MAO Jingqiao, et al. A coupled model for predicting the effect of the Three Gorges Reservoir on downstream river-connected lakes[J]. Disaster advances, 2013,6(12):78-83. |
|
|
|
