基于增强回归树的流域非点源污染影响因子分析

doi:10.13287/j.1001-9332.201603.020

应用生态学报 ›› 2016, Vol. 27 ›› Issue (3): 911-919.doi: 10.13287/j.1001-9332.201603.020

基于增强回归树的流域非点源污染影响因子分析

尹才^1,2,3, 刘淼^2*, 孙凤云^1,3, 李春林², 象伟宁³

¹华东师范大学地理科学学院, 上海 200241;
²中国科学院沈阳应用生态研究所, 沈阳 110016;
³上海市城市化生态过程与生态恢复重点实验室, 上海 200241

收稿日期:2015-07-01 出版日期:2016-03-18 发布日期:2016-03-18
通讯作者: * E-mail: lium@iae.ac.cn
作者简介:尹才,男,1990年生,硕士研究生.主要从事流域非点污染模拟及其评价管理研究.E-mail:shues_cyin@163.com
基金资助:
本文由国家自然科学基金面上项目(41171155,41501198)资助

Influencing factors of non-point source pollution of watershed based on boosted regression tree algorithm

YIN Cai^1,2,3, LIU Miao^2*, SUN Feng-yun^1,3, LI Chun-lin², XIANG Wei-ning³

¹School of Geography Sciences, East China Normal University, Shanghai 200241, China;
²Institute of Applied Ecology, Chinese Academy of Sciences, Shenyang 110164, China;
³Shanghai Key Laboratory for Urban Ecological Processes and Eco-Restoration, Shanghai 200241, China

Received:2015-07-01 Online:2016-03-18 Published:2016-03-18
Contact: * E-mail: lium@iae.ac.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (41171155,41501198)

摘要/Abstract

摘要： 地表水的非点源污染在点源污染不断得到控制的前提下已经成为水环境污染的首要问题.非点源污染影响因子的复杂性及不确定性一直是流域非点源污染研究的重点和难点.本文利用SWAT(Soil and Water Assessment Tool)模型,以辽河子流域汎河流域为例,模拟了2003—2012年的非点源污染状况,对其空间分布状况进行了分析,并应用增强回归树的方法定量分析各种影响因子(坡度、土地利用类型、高程和土壤类型)对该流域非点源污染的贡献率.结果表明: 在汎河流域,非点源污染呈现较高的空间异质性,其中总氮的空间分布差异较大,总磷的空间分布差异较小.坡度因子与载体泥沙、总氮和总磷均呈极显著正相关关系(P<0.01),对泥沙和总磷有显著影响,其贡献率分别为46.5%、38.2%;土地利用因子对载体泥沙、总磷的负荷量有重要影响,其贡献率分别达到27.2%、35.3%;高程较低、坡度较缓的耕地地区易产生较高的总磷负荷量;褐色土壤最易流失总磷,而草甸土易流失总磷,且易受泥沙侵蚀.本研究利用增强回归树模型克服了流域非点源污染影响因子的复杂性,可加深对非点源污染产生机制的理解.

Abstract: Non-point source (NPS) pollution has become a key water pollution problem under the condition of point source pollution was controlled. The complexity and uncertainty research of NPS pollution influential factors has always been important and difficult. This paper simulated NPS pollution of the Fanhe River watershed in 2003-2012 by the soil and water assessment tool (SWAT) and analyzed its spatial distribution. Meanwhile, the boosted regression tree (BRT) method was proposed to quantitatively analyze the corresponding influential factors including land use, soil, elevation and slope. The results showed that NPS pollution in the Fanhe River watershed had high spatial heterogeneity. The spatial distribution of total nitrogen (TN) had greater difference than that of total phosphorus (TP). The three pollutants, TN, TP and sediment, were all positively related to slope gradients (P<0.01). The slope gradients played the strongest role in determining the sediment and TP output with the contribution rate of 46.5% and 38.2%, respectively. Land use had important influence on sediment and TP loads, with the contribution rate of 27.2% and 35.3%, respectively. TN was produced abundantly in low-elevation and steep-slope locations and with cultivated land use. Cinnamon soil was most vulnerable to the TN load while meadow soil took the second place in terms of soil erosion and TP load. The paper overcame the complexity of influential factors for NPS pollution by BRT, and deepened the understanding of NPS pollution mechanism.

尹才, 刘淼, 孙凤云, 李春林, 象伟宁. 基于增强回归树的流域非点源污染影响因子分析[J]. 应用生态学报, 2016, 27(3): 911-919.

YIN Cai, LIU Miao, SUN Feng-yun, LI Chun-lin, XIANG Wei-ning. Influencing factors of non-point source pollution of watershed based on boosted regression tree algorithm[J]. Chinese Journal of Applied Ecology, 2016, 27(3): 911-919.

参考文献

[1] He C-H (贺缠生), Fu B-J (傅伯杰), Chen L-D (陈利顶). Non-point source pollution control and management. Environmental Science (环境科学), 1998, 19(5): 88-92, 97 (in Chinese)
[2] Griffith JA. Geographic techniques and recent applications of remote sensing to landscape-water quality stu-dies. Water, Air, and Soil Pollution, 2002, 138: 181-197
[3] Jin J-L (金婧靓), Wang F-E (王飞儿), Dai L-Y (戴露莹), et al. Characteristics of non-point source pollution in Tiaoxi watershed and related affecting factors. Chinese Journal of Applied Ecology (应用生态学报), 2011, 22(8): 2119-2125 (in Chinese)
[4] Yang A-L (杨爱玲), Zhu Y-M (朱颜明). The study of non-point source pollution of surface water environment. Advances in Environmental Science (环境科学进展), 1999, 7(5): 60-67 (in Chinese)
[5] Bacic ILZ, Rossiter DG, Bregt AK. Using spatial information to improve collective understanding of shared environmental problems at watershed level. Landscape and Urban Planning, 2006, 77: 54-66
[6] Graf A, Bogena HR, Drüe C, et al. Spatiotemporal relations between water budget components and soil water content in a forested tributary catchment. Water Resources Research, 2014, 50: 4837-4857
[7] Rui X-F (芮孝芳), Liang X (梁霄). Present situation and future of hydrology. Advances in Science and Technology of Water Resources (水利水电科技进展), 2011, 31(2): 1-4 (in Chinese)
[8] Chahor Y, Casali J, Gimenez R, et al. Evaluation of the AnnAGNPS model for predicting runoff and sediment yield in a small Mediterranean agricultural watershed in Navarre (Spain). Agricultural Water Management, 2014, 134: 24-37
[9] Zhang Z-Y (张展羽), Si H (司涵), Kong L-L (孔莉莉). Migration of non-point source nitrogen and phosphorus in small watershed based on SWAT model. Transa-ctions of the Chinese Society of Agricultural Engineering (农业工程学报), 2013, 29(2): 93-100 (in Chinese)
[10] Liu M-B (刘梅冰), Chen X-W (陈兴伟), Chen Y (陈莹). Multiple time scales analysis of spatial differentiation characteristics of non-point source nitrogen loss within watershed. Chinese Journal of Applied Ecology (应用生态学报), 2015, 26(7): 2183-2191 (in Chinese)
[11] Ma G-W (马广文), Wang S-R (王圣瑞), Wang Y-Y (王业耀), et al. Temporal and spatial distribution characteristics of nitrogen and phosphorus and diffuse source pollution load simulation of Poyang Lake Basin. Acta Scientiae Circumstantiae (环境科学学报), 2015, 35(5): 1285-1291 (in Chinese)
[12] Chang C-L, Lin Y-T. Using the VIKOR method to eva-luate the design of a water quality monitoring network in a watershed. International Journal of Environmental Science and Technology, 2014, 11: 303-310
[13] Kaiglova J, Langhammer J. Analysis of efficiency of pollution reduction measures in rural basin using MIKE Basin model. Case study: Olsava River Basin. Journal of Hydrology and Hydromechanics, 2014, 62: 43-54
[14] Luo Y-X (罗运祥), Su B-L (苏保林), Yang W-Z (杨武志), et al. Identification and assessment of non-point source pollution in the Chaihe reservoir catchment using SWAT. Journal of Beijing Normal University (Natural Science) (北京师范大学学报:自然科学版), 2012, 48(5): 510-514 (in Chinese)
[15] Geng R-Z (耿润哲), Wang X-Y (王晓燕), Duan S-H (段淑怀), et al. A tool for estimating best management practices effectiveness for agricultural non-point source pollution control based on the MS ACCESS. Acta Scientiae Circumstantiae (环境科学学报), 2013, 33(12): 3292-3300 (in Chinese)
[16] Aslan A, Trauth KM. Development and demonstration of a gis-based cumulative effectiveness approach to buffer design and evaluation. Journal of Irrigation and Drai-nage Engineering, 2014, 140: 575-575
[17] Chen L, Zhong Y, Wei G, et al. Development of an integrated modeling approach for identifying multilevel non-point-source priority management areas at the watershed scale. Water Resources Research, 2014, 50: 4095-4109
[18] Neshat A, Pradhan B, Dadras M. Groundwater vulnerability assessment using an improved DRASTIC method in GIS. Resources Conservation and Recycling, 2014, 86: 74-86
[19] Wilkinson SN, Dougall C, Kinsey-Henderson AE, et al. Development of a time-stepping sediment budget model for assessing land use impacts in large river basins. Science of the Total Environment, 2013, 468: 1210-1224
[20] Yu W-J (余文君), Nan Z-T (南卓铜), Zhao Y-B (赵彦博), et al. Improvement of snowmelt implementation in the SWAT hydrologic model. Acta Ecologica Sinica (生态学报), 2013, 33(21): 6992-7001 (in Chinese)
[21] Wei C (魏冲), Song X (宋轩), Chen J (陈杰). Sensitivity analysis of swat model on changes of landscape pattern: A case study from Lao Guanhe Watershed in Danjiangkou Reservoir area. Acta Ecologica Sinica (生态学报), 2014, 34(2): 517-525 (in Chinese)
[22] Yuan Y-Z (袁宇志), Zhang Z-D (张正栋), Meng J-H (蒙金华). Impact of changes in land use and climate on the runoff in Liuxihe watershed based on SWAT model. Chinese Journal of Applied Ecology (应用生态学报), 2015, 26(4): 989-998 (in Chinese)
[23] Li C-L (李春林), Hu Y-M (胡远满), Liu M (刘淼), et al. Urban non-point source pollution: Research progress. Chinese Journal of Ecology (生态学杂志), 2013, 32(3): 492-500 (in Chinese)
[24] Hao F-H (郝芳华), Chen L-Q (陈利群), Liu C-M (刘昌明), et al. Impact of land use change on runoff and sediment yield. Journal of Soil and Water Conservation (水土保持学报), 2004, 18(3): 5-8 (in Chinese)
[25] Zhang X-S (张雪松), Hao F-H (郝芳华), Yang Z-F (杨志峰), et al. Runoff and sediment yield modeling in meso-scale watershed based on SWAT model. Research of Soil and Water Conservation (水土保持研究), 2003, 10(4): 38-42 (in Chinese)
[26] Hu X-T (胡雪涛), Chen J-N (陈吉宁), Zhang T-Z (张天柱). A study on non-point source pollution models. Environmental Science (环境科学), 2002, 23(3): 124-128 (in Chinese)
[27] Gorgan D, Bacu V, Mihon D, et al. Grid based calibration of SWAT hydrological models. Natural Hazards and Earth System Science, 2012, 12: 2411-2423
[28] Liu M, Hu Y, Zhang W, et al. Application of land-use change model in guiding regional planning: A case study in Hun-Taizi River watershed, Northeast China. Chinese Geographical Science, 2011, 21: 609-618
[29] Zhu J-J (朱君君), Hu Y-M (胡远满), Liu M (刘淼), et al. Landscape change and its driving forces in Hun-Tai river basin. Chinese Journal of Ecology (生态学杂志), 2011, 30(1): 112-118 (in Chinese)
[30] Elith J, Leathwick JR, Hastie T. A working guide to boosted regression trees. Journal of Animal Ecology, 2008, 77: 802-813
[31] Parisien MA, Moritz MA. Environmental controls on the distribution of wildfire at multiple spatial scales. Ecological Monographs, 2009, 79: 127-154
[32] Nash JE, Sutcliffe JV. River flow forecasting through conceptual models part I : A discussion of principles. Journal of Hydrology, 1970, 10: 282-290
[33] Moriasi DN, Arnold JG, Van Liew MW, et al. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the American Society of Agricultural and Biological Engineers, 2007, 50: 885-900
[34] Castillo CR, Guneralp I, Guneralp B. Influence of changes in developed land and precipitation on hydrology of a coastal Texas watershed. Applied Geography, 2014, 47: 154-167
[35] Xiao Y (肖洋), Lu Q (陆奇), Cheng H-K (成浩科), et al. Surface properties of sediments and its effect on phosphorus adsorption. Journal of Sediment Research (泥沙研究), 2011(6): 64-68 (in Chinese)
[36] Bermudez-Couso A, Fernandez-Calvino D, Alvarez-Enjo MA, et al. Pollution of surface waters by metalaxyl and nitrate from non-point sources. Science of the Total Environment, 2013, 461: 282-289
[37] Good AG, Beatty PH. Fertilizing Nature: A Tragedy of Excess in the Commons. PLoS Biology, 2011, 9(8): e1001124
[38] Wang L-M (王良民), Wang Y-H (王彦辉). Research and application advances on vegetative filter strip. Chinese Journal of Applied Ecology (应用生态学报), 2008, 19(9): 2074-2080 (in Chinese)
[39] Wang Q-C (王庆成), Yu H-L (于红丽), Yao Q (姚琴), et al. Retaining and transform action of incoming soil N from highland to adjacent terrestrial water body in riparian buffer zone. Chinese Journal of Applied Ecology (应用生态学报), 2007, 18(11): 2611-2617 (in Chinese)

基于增强回归树的流域非点源污染影响因子分析

Influencing factors of non-point source pollution of watershed based on boosted regression tree algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价