Study on Runoff and Sediment Variation of the Dongting Lake Based on PPR and SVM Model
Abstract: The Dongting Lake is very important for flood storage and water sources in the midstream of the Yangtze River. Due to the dual effects of nature and human activities, several major changes have been taken place on the runoff and sediment conditions and the relationships between rivers and lakes successively. In order to explore the relationships of runoff and sediment in and out the lake, the existing hydrologic and sediment and other observation data of the Dongting Lake area are fully used, and two non-linear simulation models, Projection Pursuit Regression (PPR) and Support Vector Machine (SVM) are established. The simulation errors are also compared. The results show that the Support Vector Machine (SVM) has better validity and credibility, which could be used as an effective tool to simulate the complicated river system. This finding provides theoretical support and scientific basis for comprehensive improvement and ecological restoration of the Dongting Lake.
文章引用: 赵 姗 , 周念清 , 李正最 (2012) 基于PPR和SVM模型研究洞庭湖径流与输沙量变化。 水资源研究， 1， 347-352. doi: 10.12677/JWRR.2012.15053
 毛北平, 梅军亚, 张金辉, 等. 洞庭湖三口洪道水沙输移变化分析[J]. 人民长江, 2010, 2: 38-42. MAO Beiping, MEI Junya, ZHANG Jinhui, et al. Analysis of water and sediments transportation of three river-outlets flood chnnels from Yangtze River to Dongting Lake. Yangtze River, 2010, 2: 38-42. (in Chinese)
 吴作平, 杨国录, 甘明辉. 荆江–洞庭湖水沙模型研究[J]. 水利学报, 2003, 7: 96-100. WU Zuoping, YANG Guolu and GAN Minghui. Mathematical model for flow-sediment transportation of Jingjiang River- Dongting Lake network. Journal of Hydraulic Engineering, 2003, 7: 96-100. (in Chinese)
 FRIEDMAN, J. H., TUKEY, J. W. A projection pursuit algorithm or exploratory data analysis. IEEE Transactions on Computer, 1974, 23(9): 881-890.
 KRUSCAL, J. B. Toward a practical method which helps uncover the structure of a set of multivariate observations by finding the linear transformation which optimizes a new index of condensations. Statistical Computer, New York: Academic, 1969.
 FREIMAN, J. H., STUEZLE, W. Projection pursuit regression. Journal of American Statistic Association, 1989, 76: 817-823.
 李景保. 洞庭湖区1996年特大洪涝灾害的特点与成因分析[J]. 地理学报, 1998, 53(2): 166-173. LI Jingbao. A study on the features and causes of the flood dis-asters in Dongting Lake plain in 1996. Acta Geographica Sinica, 1998, 53(2): 166-173. (in Chinese)
 王顺久, 侯玉, 张欣莉, 等. 流域水资源承载能力的综合评价方法[J]. 水利学报, 2003, 1: 88-92. WANG Shunjiu, HOU Yu, ZHANG Xinli, et al. Comprehensive evaluation method for water resources carrying capacity in river basins. Journal of Hydraulic engineering, 2003, 1: 88-92. (in Chinese)
 刘卫林. 遗传投影寻踪回归模型在地下水环境脆弱性评价中的应用[J]. 南昌工程学院, 2011, 30(3): 1-5. LIU Weilin. Application of projection pursuit model based on genetic algorithm to evaluation of the groundwater environmental vulnerability. Journal of Nangchang Institute of Technology, 2011, 30(3): 1-5. (in Chinese)
 童潜明. 三峡水库运行后对洞庭湖防洪和生态的思考[J]. 国土资源科技管理, 2001, 3: 1-6. TONG Qianming. Management of land reflections on flood control and ecology of Dongting Lake after operation of the three gorges reservoir. Scientific and Technological Management of Land and Resources, 2001, 3: 1-6. (in Chinese)
 VAPNIK, V. N. The nature of statistic learning theory. New York: Spring Verlag, 1995.
 甘明辉, 刘卡波, 杨大文, 等. 洞庭湖四口河系防洪、水资源与水环境研究[J]. 2011, 30(5): 5-9. GAN Minghui, LIU Kabo, YANG Dawen, et al. Analysis on the flood control, water supply and water environment projection in the region of Dongting Lake along Yangtze River. Journal of Hydroelectric Engineering, 2011, 30(5): 5-9. (in Chinese)
 ZHANG, X. G. On statistical learning theory and support vector machine. Acta Automatica Sinica, 2000, 26(1): 32-42.
 穆锦斌, 张小峰. 荆江–洞庭湖水沙变化影响分析[J]. 水利水运工程学报, 2011, 1: 84-91. MU Jinbin, ZHANG Xiaofeng. Analysis on water-sediment tran- sportation variation of Jingjiang River-Dongting Lake. Hydro- Science and Engineering, 2011, 1: 84-91. (in Chinese)
 李正最, 谢悦波, 徐冬梅. 基于支持向量机的洞庭湖水量交换模型[J]. 水电能源科学, 2009, 27(5): 18-20. LI Zhegnzui, XIE Yuebo and XU Dongmei. Water exchange model in Dongting Lake based on support vector machine. Water Resources and Power, 2009, 27(5): 18-20. (in Chinese)
 李正最, 谢悦波. 基于支持向量机的洞庭湖区域水沙模拟[J]. 水文, 2010, 30(2): 44-49. LI Zhegnzui, XIE Yuebo. Simulation of water and sediment in Dongting Lake based on support vector machine. Journal of China Hydrology, 2010, 30(2): 44-49. (in Chinese)
 田盛丰, 黄厚宽. 基于支持向量机的数据库学习算法[J]. 计算机研究与发展, 2000, 37(1): 17-22. TIAN Shengfeng, HUANG Houkuan. Database learning algorithms based on supportive machine. Journal of Computer Research & Development, 2000, 37(1): 17-22. (in Chinese)
 苏高利, 邓芳萍. 关于支持向量回归机的模型选择[J]. 科技通报, 2006, 22(2): 154-158. SU Gaoli, DENG Fangping. Introduction to model selection of SVM regression. Bulletin of Science and Technology, 2006, 22(2): 154-158. (in Chinese)
 李景保, 代勇, 欧朝敏, 等. 长江三峡水库蓄水运用对洞庭湖水沙特性的影响[J]. 水土保持学报, 2011, 25(3): 215-219. LI Jingbao, DAI Yong, OU Chaomin, et al. Effects of store water application of the Three-Gorges Reservoir on Yangtze River on water and sediment characteristics in the Dongting Lake. Journal of Soil and Water Conservation, 2011, 25(3): 215-219. (in Chinese)
 潘庆燊. 下荆江人工裁弯30年[J]. 人民长江, 2001, 32(5): 27- 29. PAN Qingshen. Over 30 years about the artificial cut-off project on the lower Jingjiang River. Yangtze River, 2001, 32(5): 27-29. (in Chinese)
 马元旭, 来红州. 荆江与洞庭湖区近50年水沙变化的研究[J]. 水土保持研究, 2005, 12(4): 103-106. MA Yuanxu, LAI Hongzhou. Research on the variations of the water and sediment for recent 50 years in the Jingjiang River and Dongting Lake Area. Research of Soil and Water Conservation, 2005, 12(4): 103-106. (in Chinese)