Water eutrophication evaluation based on rough set and petri nets: A case study in Xiangxi-River, Three Gorges Reservoir

被引:55
作者
Yan Huyong [1 ]
Huang Yu [1 ]
Wang Guoyin [1 ]
Zhang Xuerui [1 ]
Shang Mingsheng [1 ]
Feng Lei [1 ]
Dong Jianhua [1 ]
Shan Kun [1 ]
Wu Di [1 ]
Zhou Botian [1 ]
Yuan Ye [1 ]
机构
[1] Chinese Acad Sci, Big Data Min & Applicat Ctr, Chongqing Inst Green & Intelligent Technol, Chongqing 400714, Peoples R China
关键词
Xiangxi River; Rough set theory; Petri nets; Eutrophication; CHI2; ALGORITHM; DISCRETIZATION; SELECTION; MODELS; FLOOD; AREA;
D O I
10.1016/j.ecolind.2016.05.010
中图分类号
X176 [生物多样性保护];
学科分类号
090705 ;
摘要
After impoundment of the Three Gorges Reservoir (TGR), the water area of Xiangxi River becomes a typical area of reservoir tributaries where eutrophication develops and water bloom occurs. In order to assess the eutrophication status in Xiangxi River faster and more accurate, an integrated model (RSPN) for eutrophication assessment based on eleven monitoring sections samples in Xiangxi River from 2015 to 2016, which integrates rough set theory (RST) and petri nets (PN), is presented. Firstly, RST was employed to remove redundant eutrophication features and simple eutrophication information, so that the minimal eutrophication assessment rules can be obtained and the eutrophication rank was roughly assessed. Secondly, the PN structure was built and the eutrophication rank was completely realized through matrix operation of PN. Finally, comparison using RSPN and other classical classification algorithms was performed. The results reveal that the RSPN model can accurately and efficiently analyze the relation between condition indicators and variations of eutrophication degree. Therefore, the RSPN model is a promising alternative method to develop a water eutrophication information system and offers decision rules base for the utility management as well as operations staff. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:463 / 472
页数:10
相关论文
共 37 条
[1]  
[Anonymous], 1986, MACHINE LEARNING DAT
[2]  
Breiman L.I., 2012, LECT NOTES COMPUT SC, V110, P79
[3]  
Cai Qing-Hua, 2006, Acta Hydrobiologica Sinica, V30, P7
[4]  
Chao DY, 2014, IEEE INT C NETW SENS, P572, DOI 10.1109/ICNSC.2014.6819689
[5]   Data mining framework based on rough set theory to improve location selection decisions: A case study of a restaurant chain [J].
Chen, Li-Fei ;
Tsai, Chih-Tsung .
TOURISM MANAGEMENT, 2016, 53 :197-206
[6]   Business failure prediction using rough sets [J].
Dimitras, AI ;
Slowinski, R ;
Susmaga, R ;
Zopounidis, C .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 1999, 114 (02) :263-280
[7]  
Gaj J., 2016, POSSIBILITIES CONTRO
[8]  
Hu Zheng-Yu, 2006, Acta Hydrobiologica Sinica, V30, P1
[9]   Research on Intelligent Fault Diagnosis Method Based on Rough Set Theory and Fuzzy Petri Nets [J].
Li, Lanyun ;
Yang, Zhuanzhao ;
He, Zhi .
ADVANCED MECHANICAL ENGINEERING, PTS 1 AND 2, 2010, 26-28 :77-+
[10]  
Li P., 2011, CHINA ENV MONIT ASSE, V184, P4841