基于水沙组合分类的黄河中下游水沙变化特点研究
|
摘要
为进一步揭示黄河中下游水沙关系及变化规律,本文通过自组织映射(Self-Organizing Map)-K均值聚类(K-means clustering)耦合方法,利用黄河中游潼关水文站1919—2018年的年径流量及年输沙量数据,对该站的水沙组合进行分类。结果表明:潼关站水沙类型有沙多水多、沙多水中、沙中水中及沙少水中4种。结合新中国成立后黄河流域水土保持事业的发展情况,以1960年及2000年为时间节点将研究时段分为3个阶段,分析了上述4种类型在3个阶段的出现频率及变化特点。考虑到黄河水沙条件的变化,又对1986年以来潼关站的水沙组合进行分类。结果表明:该站在1986年后的水沙类型有沙中水中及沙少水中2种。两种时间序列下的分类结果略有差异,体现出黄河水沙变化的复杂性。
A coupled clustering method of the Self-Organizing Map and K-means clustering is developed and adopted on the annual runoff and sediment load data(1919-2018) at Tongguan(TG) station to further reveal the runoff-sediment patterns of the middle and lower Yellow River. The results indicate that the runoff-sediment patterns of TG station can be divided into four types and their occurrence frequencies vary significantly in the three characteristic periods of the Yellow River. Moreover,considering the variation of annual runoff and sediment load in the Yellow River after 1986,the annual runoff and sediment load data at TG station from 1987 to 2018 are also analyzed and divided into two types using the coupled clustering method. The difference between the two sets results reflects that the rows of runoff and sediment load variation in the Yellow River are very complicated.
A coupled clustering method of the Self-Organizing Map and K-means clustering is developed and adopted on the annual runoff and sediment load data(1919-2018) at Tongguan(TG) station to further reveal the runoff-sediment patterns of the middle and lower Yellow River. The results indicate that the runoff-sediment patterns of TG station can be divided into four types and their occurrence frequencies vary significantly in the three characteristic periods of the Yellow River. Moreover,considering the variation of annual runoff and sediment load in the Yellow River after 1986,the annual runoff and sediment load data at TG station from 1987 to 2018 are also analyzed and divided into two types using the coupled clustering method. The difference between the two sets results reflects that the rows of runoff and sediment load variation in the Yellow River are very complicated.
引文
[1]许炯心.黄河下游泥沙淤积的经验统计关系[J].地理研究,1997,16(1):23-30.
[2]胡明思,骆承政.中国历史大洪水[M].北京:中国书店,1992.
[3]张红武,李振山,安催花,等.黄河下游河道与滩区治理研究的趋势与进展[J].人民黄河,2016,38(12):1-10.
[4]高季章,胡春宏,陈绪坚.论黄河下游河道的改造与“二级悬河”的治理[J].中国水利水电科学研究院学报,2004,2(1):8-18.
[5]张红武,张俊华,钟德钰,等.黄河下游游荡型河段的治理方略[J].水利学报,2011,42(1):8-13.
[6]田勇,孙一,李勇,等.新时期黄河下游滩区治理方向研究[J].人民黄河,2019,41(3):16-20,35.
[7]胡春宏,张晓明.论黄河水沙变化趋势预测研究的若干问题[J].水利学报,2018,49(9):1028-1039.
[8]尹学良.黄河下游冲淤特性及其改造问题[J].泥沙研究,1980(复刊号):75-82.
[9]刘善均.典型泥沙年的选择[J].泥沙研究,1984(3):75-77.
[10]邰淑彩.用模式识别法选取典型水沙年初探[J].武汉水利电力学院学报,1989,22(1):108-113.
[11]信忠保,余新晓,甘敬,等.黄河中游河龙区间植被覆盖变化与径流输沙关系研究[J].北京林业大学学报,2009,31(5):1-7.
[12]马丽梅,王万忠,焦菊英,等.黄河中游输沙与减沙的时空分异特征[J].水土保持研究,2010,17(4):67-72.
[13]赵跃中,穆兴民,严宝文,等.延河流域植被恢复对径流泥沙的影响[J].泥沙研究,2014,(4):67-73.
[14]蒋观滔,高鹏,穆兴民,等.退耕还林(草)对北洛河上游水沙变化的影响[J].水土保持研究,2015,22(6):1-6.
[15] KALTEH A M,HJORTH P,BERNDTSSON R. Review of the self-organizing map(SOM)approach in water resources:Analysis,modelling and application[J]. Environmental Modelling&Software,2008,23:835-845.
[16]李荣峰.人工神经网络及其在水科学研究中的应用[J].山西水利科技,2003(4):50-53.
[17]伊璇,周丰,王心宇,等.基于SOM的流域分类和无资料区径流模拟[J].地理科学进展,2014,33(8):1109-1116.
[18]张红武,张欧阳,徐向舟,等.黄土高原沟道坝系相对稳定原理与工程规划研究[M].郑州:黄河水利出版社,2010.
[19] KOHONEN T. Self-organized formation of topologically correct feature maps[J]. Biological Cybernetics,1982,43:59-69.
[20]陈伯成,梁冰,周越博,等.自组织映射神经网络(SOM)在客户分类中的一种应用[J].系统工程理论与实践,2004(3):8-14.
[21] KOHONEN T. Essentials of the self-organizing map[J]. Neural Networks,2013,37:52-65.
[22] SOM Toolbox team. SOM Toolbox for Matlab 5[EB/OL]. http://www.cis.hut.fi/projects/somtoolbox/download/.
[23] MELSSEN W J,SMITS J R M,BUYDENS L M C,et al. Using artificial neural networks for solving chemical problems:Part II. Kohonen self-organising feature maps and Hopfield networks[J]. Chemometrics and Intelligent Laboratory Systems,1994,23:267-291.
[24] LIN G F,CHEN L H. Identification of homogeneous regions for regional frequency analysis using the self-organizing map[J]. Journal of Hydrology,2006,324:1-9.
[25] ABRAHART R J,SEE L. Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments[J]. Hydrological Processes,2000,14:2157-2172.
[26] PARASURAMAN K,ELSHORBAGY A,CAREY S K. Spiking modular neural networks:A neural network modeling approach for hydrological processes[J]. Water Resources Research,2006,42:W05412.
[27] KOHONEN T. Self-Organizing Maps[M]. Verlag Berlin Heidelberg:Springer,2001.
[28] LIU Y G,WEISBERG R H,MOOERS C N K. Performance evaluation of the self-organizing map for feature extraction[J]. Journal of Geophysical Research Oceans,2006,111:C05018.
[29]王熙照,王亚东,湛燕,等.学习特征权值对K-均值聚类算法的优化[J].计算机研究与发展,2003,40(6):869-873.
[30] JAMES G,WITTEN D,HASTIE T,et al. An Introduction to Statistical Learning:With Applications in R[M].New York:Springer,2013.
[31]张发明.一种融合SOM与K-means算法的动态信用评价方法及应用[J].运筹与管理,2014,23(6):186-192.
[32]刘靖明,韩丽川,侯立文.基于粒子群的K均值聚类算法[J].系统工程理论与实践,2005(6):54-58.
[33] BARGE J T,SHARIF H O. An ensemble empirical mode decomposition,self-organizing map,and linear genetic programming approach for forecasting river streamflow[J]. Water,2016,8:247.
[34] LIU W B,WANG L,CHEN D L,et al. Large-scale circulation classification and its links to observed precipitation in the eastern and central Tibetan Plateau[J]. Climate Dynamics,2016,46(11/12):3481-3497.
[35] MathWorks. Silhouette[EB/OL]. https://cn.mathworks. com/help/stats/silhouette.html?s_tid=srchtitle.
[36]江衍坤.黄河流域水土保持工作基本情况和今后意见的报告[J].土壤,1960(1):9-15.
[37]黄河水利委员会,黄河中游治理局.黄河水土保持志[M].郑州:河南人民出版社,1993.
[38]张含英.在总路线的光辉照耀下,为了保卫三门峡水库,为了发展黄土高原的生产,迅速掀起一个水土保持运动的新高潮![J].土壤,1960(1):4-5.
[39]刘瑞龙.政治挂帅,依靠人民公社,把水土保持运动推向新的高潮![J].黄河建设,1960(2):41-42.
[40] WANG H J,YANG Z S,SAITO Y,et al. Interannual and seasonal variation of the Huanghe(Yellow River)water discharge over the past 50years:Connections to impacts from ENSO events and dams[J]. Global and Planetary Change,2006,50:212-225.
[41]赵业安,张红武,温善章.论黄河大柳树水利枢纽工程的战略地位与作用[J].人民黄河,2002,24(2):1-4.
[42]赵新泉,马艳娥.退耕还林的生态作用及实施措施[J].林业资源管理,1999(3):36-39.
[43]吴斡宁.三峡库区坡耕地退耕还林初探[J].人民长江,1999,30(8):17-19.
[44]靳少波,白晓龙.黄河上游近30年径流变化特点及影响因素[J].甘肃水利水电技术,2018,54(1):8-12.
[45]姚文艺,高亚军,安催花,等.百年尺度黄河上中游水沙变化趋势分析[J].水利水电科技进展,2015,35(5):112-120.
[46]中华人民共和国水利部.水利水电工程设计洪水计算规范:SL44-2006[S].北京:中国水利水电出版社,2006.
[47]王远见,傅旭东,王光谦.黄河流域降雨时空分布特征[J].清华大学学报(自然科学版),2018,58(11):972-978.
[48]刘晓燕,马思远,党素珍.黄河流域近百年产沙情势变化[J].泥沙研究,2017,42(5):1-6.
[2]胡明思,骆承政.中国历史大洪水[M].北京:中国书店,1992.
[3]张红武,李振山,安催花,等.黄河下游河道与滩区治理研究的趋势与进展[J].人民黄河,2016,38(12):1-10.
[4]高季章,胡春宏,陈绪坚.论黄河下游河道的改造与“二级悬河”的治理[J].中国水利水电科学研究院学报,2004,2(1):8-18.
[5]张红武,张俊华,钟德钰,等.黄河下游游荡型河段的治理方略[J].水利学报,2011,42(1):8-13.
[6]田勇,孙一,李勇,等.新时期黄河下游滩区治理方向研究[J].人民黄河,2019,41(3):16-20,35.
[7]胡春宏,张晓明.论黄河水沙变化趋势预测研究的若干问题[J].水利学报,2018,49(9):1028-1039.
[8]尹学良.黄河下游冲淤特性及其改造问题[J].泥沙研究,1980(复刊号):75-82.
[9]刘善均.典型泥沙年的选择[J].泥沙研究,1984(3):75-77.
[10]邰淑彩.用模式识别法选取典型水沙年初探[J].武汉水利电力学院学报,1989,22(1):108-113.
[11]信忠保,余新晓,甘敬,等.黄河中游河龙区间植被覆盖变化与径流输沙关系研究[J].北京林业大学学报,2009,31(5):1-7.
[12]马丽梅,王万忠,焦菊英,等.黄河中游输沙与减沙的时空分异特征[J].水土保持研究,2010,17(4):67-72.
[13]赵跃中,穆兴民,严宝文,等.延河流域植被恢复对径流泥沙的影响[J].泥沙研究,2014,(4):67-73.
[14]蒋观滔,高鹏,穆兴民,等.退耕还林(草)对北洛河上游水沙变化的影响[J].水土保持研究,2015,22(6):1-6.
[15] KALTEH A M,HJORTH P,BERNDTSSON R. Review of the self-organizing map(SOM)approach in water resources:Analysis,modelling and application[J]. Environmental Modelling&Software,2008,23:835-845.
[16]李荣峰.人工神经网络及其在水科学研究中的应用[J].山西水利科技,2003(4):50-53.
[17]伊璇,周丰,王心宇,等.基于SOM的流域分类和无资料区径流模拟[J].地理科学进展,2014,33(8):1109-1116.
[18]张红武,张欧阳,徐向舟,等.黄土高原沟道坝系相对稳定原理与工程规划研究[M].郑州:黄河水利出版社,2010.
[19] KOHONEN T. Self-organized formation of topologically correct feature maps[J]. Biological Cybernetics,1982,43:59-69.
[20]陈伯成,梁冰,周越博,等.自组织映射神经网络(SOM)在客户分类中的一种应用[J].系统工程理论与实践,2004(3):8-14.
[21] KOHONEN T. Essentials of the self-organizing map[J]. Neural Networks,2013,37:52-65.
[22] SOM Toolbox team. SOM Toolbox for Matlab 5[EB/OL]. http://www.cis.hut.fi/projects/somtoolbox/download/.
[23] MELSSEN W J,SMITS J R M,BUYDENS L M C,et al. Using artificial neural networks for solving chemical problems:Part II. Kohonen self-organising feature maps and Hopfield networks[J]. Chemometrics and Intelligent Laboratory Systems,1994,23:267-291.
[24] LIN G F,CHEN L H. Identification of homogeneous regions for regional frequency analysis using the self-organizing map[J]. Journal of Hydrology,2006,324:1-9.
[25] ABRAHART R J,SEE L. Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments[J]. Hydrological Processes,2000,14:2157-2172.
[26] PARASURAMAN K,ELSHORBAGY A,CAREY S K. Spiking modular neural networks:A neural network modeling approach for hydrological processes[J]. Water Resources Research,2006,42:W05412.
[27] KOHONEN T. Self-Organizing Maps[M]. Verlag Berlin Heidelberg:Springer,2001.
[28] LIU Y G,WEISBERG R H,MOOERS C N K. Performance evaluation of the self-organizing map for feature extraction[J]. Journal of Geophysical Research Oceans,2006,111:C05018.
[29]王熙照,王亚东,湛燕,等.学习特征权值对K-均值聚类算法的优化[J].计算机研究与发展,2003,40(6):869-873.
[30] JAMES G,WITTEN D,HASTIE T,et al. An Introduction to Statistical Learning:With Applications in R[M].New York:Springer,2013.
[31]张发明.一种融合SOM与K-means算法的动态信用评价方法及应用[J].运筹与管理,2014,23(6):186-192.
[32]刘靖明,韩丽川,侯立文.基于粒子群的K均值聚类算法[J].系统工程理论与实践,2005(6):54-58.
[33] BARGE J T,SHARIF H O. An ensemble empirical mode decomposition,self-organizing map,and linear genetic programming approach for forecasting river streamflow[J]. Water,2016,8:247.
[34] LIU W B,WANG L,CHEN D L,et al. Large-scale circulation classification and its links to observed precipitation in the eastern and central Tibetan Plateau[J]. Climate Dynamics,2016,46(11/12):3481-3497.
[35] MathWorks. Silhouette[EB/OL]. https://cn.mathworks. com/help/stats/silhouette.html?s_tid=srchtitle.
[36]江衍坤.黄河流域水土保持工作基本情况和今后意见的报告[J].土壤,1960(1):9-15.
[37]黄河水利委员会,黄河中游治理局.黄河水土保持志[M].郑州:河南人民出版社,1993.
[38]张含英.在总路线的光辉照耀下,为了保卫三门峡水库,为了发展黄土高原的生产,迅速掀起一个水土保持运动的新高潮![J].土壤,1960(1):4-5.
[39]刘瑞龙.政治挂帅,依靠人民公社,把水土保持运动推向新的高潮![J].黄河建设,1960(2):41-42.
[40] WANG H J,YANG Z S,SAITO Y,et al. Interannual and seasonal variation of the Huanghe(Yellow River)water discharge over the past 50years:Connections to impacts from ENSO events and dams[J]. Global and Planetary Change,2006,50:212-225.
[41]赵业安,张红武,温善章.论黄河大柳树水利枢纽工程的战略地位与作用[J].人民黄河,2002,24(2):1-4.
[42]赵新泉,马艳娥.退耕还林的生态作用及实施措施[J].林业资源管理,1999(3):36-39.
[43]吴斡宁.三峡库区坡耕地退耕还林初探[J].人民长江,1999,30(8):17-19.
[44]靳少波,白晓龙.黄河上游近30年径流变化特点及影响因素[J].甘肃水利水电技术,2018,54(1):8-12.
[45]姚文艺,高亚军,安催花,等.百年尺度黄河上中游水沙变化趋势分析[J].水利水电科技进展,2015,35(5):112-120.
[46]中华人民共和国水利部.水利水电工程设计洪水计算规范:SL44-2006[S].北京:中国水利水电出版社,2006.
[47]王远见,傅旭东,王光谦.黄河流域降雨时空分布特征[J].清华大学学报(自然科学版),2018,58(11):972-978.
[48]刘晓燕,马思远,党素珍.黄河流域近百年产沙情势变化[J].泥沙研究,2017,42(5):1-6.