National Taiwan Ocean University Institutional Repository:Item 987654321/52017
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 28611/40652
造访人次 : 772608      在线人数 : 45
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 进阶搜寻


题名: A data-mining framework for exploring the multi-relation between fish species and water quality through self-organizing map
作者: Wen-Ping Tsai
Shih-Pin Huang
Su-Ting Cheng
Kwang-Tsao Shao
Fi-John Chang
关键词: Eco-hydrological environments
Water quality
Flow regime
Fish community
Artificial neural network (ANN)
Self-organizing map (SOM)
日期: 2016-02
上传时间: 2019-01-15T07:24:04Z
出版者: Science of the Total Environment
摘要: Abstract: The steep slopes of rivers can easily lead to large variations in river water quality during typhoon seasons in Taiwan, which may poses significant impacts on riverine eco-hydrological environments. This study aims to investigate the relationship between fish communities and water quality by using artificial neural networks (ANNs) for comprehending the upstream eco-hydrological system in northern Taiwan. We collected a total of 276 heterogeneous datasets with 8 water quality parameters and 25 fish species from 10 sampling sites. The self-organizing feature map (SOM) was used to cluster, analyze and visualize the heterogeneous datasets. Furthermore, the structuring index (SI) was adopted to determine the relative importance of each input variable of the SOM and identify the indicator factors. The clustering results showed that the SOM could suitably reflect the spatial characteristics of fishery sampling sites. Besides, the patterns of water quality parameters and fish species could be distinguishably (visually) classified into three eco-water quality groups: 1) typical upstream freshwater fishes that depended the most on dissolved oxygen (DO); 2) typical middle-lower reach riverine freshwater fishes that depended the most on total phosphorus (TP) and ammonia nitrogen; and 3) low lands or pond (reservoirs) freshwater fishes that depended the most on water temperature, suspended solids and chemical oxygen demand. According to the results of the SI, the representative indicators of water quality parameters and fish species consisted of DO, TP and Onychostoma barbatulum. This grouping result suggested that the methodology can be used as a guiding reference to comprehensively relate ecology to water quality. Our methods offer a cost-effective alternative to more traditional methods for identifying key water quality factors relating to fish species. In addition, visualizing the constructed topological maps of the SOM could produce detailed inter-relation between water quality and the fish species of stream habitat units.
關聯: 579 pp.474-483
显示于类别:[海洋文化研究所] 期刊論文


档案 描述 大小格式浏览次数



著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈