Impact of land use on water quality in buffer zones at different scales in the Poyang Lake, middle reaches of the Yangtze River basin

被引:31
作者
Wang, Wenyu [1 ]
Yang, Peng [1 ]
Xia, Jun [2 ]
Huang, Heqing [1 ]
Li, Jiang [3 ]
机构
[1] China Univ Geosci, Sch Geog & Informat Engn, Wuhan 430074, Peoples R China
[2] Wuhan Univ, State Key Lab Water Resources & Hydropower Engn Sc, Wuhan 430000, Peoples R China
[3] Informat Ctr, Dept Nat Resources Hubei Prov, Wuhan 430071, Peoples R China
关键词
Poyang Lake; Water quality inversion; In fluencing factors; Land use; POTENTIAL DRIVERS; TIME-SERIES; CATCHMENT; NITROGEN; CHINA;
D O I
10.1016/j.scitotenv.2023.165161
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The water quality of Poyang Lake (PYL) is significantly influenced by land use which is a crucial factor that can exhibit complex changes in the environment and can serve as an indicator of the intensity of human activity. Therefore, this study analyzed the spatial and temporal distribution characteristics of nutrients and investigated the effects of landuse factors on water quality in the PYL during 2016-2019. The main conclusions are as follows: (1) Although there was some variation in the accuracy of the water quality inversion models (random forest (RF), support vector machine (SVM), and multiple statistical regression models), they were homogeneous. In particular, ammonia nitrogen (NH3-N) concentration from band (B) 2 and B2-B10 regression model was more consistent with each other. In contrast, the overall concentration levels from the combined B9/(B2-B4) triple-band regression model were relatively low, with approximately 0.03 mg/L in most areas of PYL. (2) The optimal inversion method varied for different water quality parameters. For instance, RF obtained better inversion of total phosphorus (TP) and total nitrogen (TN), with the fitting coefficient (r2) of 0.78 and 0.81, respectively; SVM had higher accuracy in the inversion of permanganate index (CODMn), with r2 of approximately 0.61; the accuracy of multi-band combined regression model in the inversion of each water quality parameter was at a higher level. (3) The influence of land use on water quality at different scales of buffer zone was different. In general, the correlation between water quality parameters and land use was higher at large spatial scales (1000-5000 m) than at small spatial scales (100 m, 500 m). A common feature of all hydrological stations was the significant negative correlation between crops, buildings, and water quality at all buffer scales. This study is of great practical significance for promoting water environment management and water quality health in the PYL.
引用
收藏
页数:14
相关论文
共 56 条
[1]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[2]   Machine learning-based inversion of water quality parameters in typical reach of the urban river by UAV multispectral data [J].
Chen, Botao ;
Mu, Xi ;
Chen, Peng ;
Wang, Biao ;
Choi, Jaewan ;
Park, Honglyun ;
Xu, Sheng ;
Wu, Yanlan ;
Yang, Hui .
ECOLOGICAL INDICATORS, 2021, 133
[3]   Abrupt spatiotemporal land and water changes and their potential drivers in Poyang Lake, 2000-2012 [J].
Chen, Lifan ;
Michishita, Ryo ;
Xu, Bing .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 98 :85-93
[4]   A Red-Shifted Chlorophyll [J].
Chen, Min ;
Schliep, Martin ;
Willows, Robert D. ;
Cai, Zheng-Li ;
Neilan, Brett A. ;
Scheer, Hugo .
SCIENCE, 2010, 329 (5997) :1318-1319
[5]   The comprehensive evaluation of how water level fluctuation and temperature change affect vegetation cover variations at a lake of ecological importance (Poyang Lake), China [J].
Chen, Minghao ;
Zeng, Sidong ;
Jiang, Bo ;
Wen, Zhaofei ;
Wu, Jian ;
Xia, Jun .
ECOLOGICAL INDICATORS, 2023, 148
[6]  
Chen Xiaoling, 2013, Hupo Kexue, V25, P643
[7]   Biogeochemical hotspots: Role of small water bodies in landscape nutrient processing [J].
Cheng, Frederick Y. ;
Basu, Nandita B. .
WATER RESOURCES RESEARCH, 2017, 53 (06) :5038-5056
[8]   SUPPORT-VECTOR NETWORKS [J].
CORTES, C ;
VAPNIK, V .
MACHINE LEARNING, 1995, 20 (03) :273-297
[9]   Strategic assessment of the magnitude and impacts of sand mining in Poyang Lake, China [J].
de Leeuw, Jan ;
Shankman, David ;
Wu, Guofeng ;
de Boer, Willem Frederik ;
Burnham, James ;
He, Qing ;
Yesou, Herve ;
Xiao, Jing .
REGIONAL ENVIRONMENTAL CHANGE, 2010, 10 (02) :95-102
[10]   RANDOM FOREST AND SUPPORT VECTOR MACHINE ON FEATURES SELECTION FOR REGRESSION ANALYSIS [J].
Dewi, Christine ;
Chen, Rung-Ching .
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2019, 15 (06) :2027-2037