Applying a Multivariate Statistical Analysis Model to Evaluate the Water Quality of a Watershed

碩士 === 義守大學 === 土木與生態工程學系 === 101 ===   Multivariate statistics have been applied to evaluate the water quality data collected at 6 monitoring stations in Feitsui Reservoir watershed of Taipei, Taiwan. The objective is to evaluate the mutual correlations among the various water quality parameters in...

Full description

Bibliographic Details
Main Authors: Wei-Ting Lu, 呂威廷
Other Authors: Edward Ming-Yang Wu
Format: Others
Language:zh-TW
Published: 2013
Online Access:http://ndltd.ncl.edu.tw/handle/59629071260528839021
Description
Summary:碩士 === 義守大學 === 土木與生態工程學系 === 101 ===   Multivariate statistics have been applied to evaluate the water quality data collected at 6 monitoring stations in Feitsui Reservoir watershed of Taipei, Taiwan. The objective is to evaluate the mutual correlations among the various water quality parameters in order to reveal the primary factors that affect reservoir water quality, and the differences among the various water quality parameters in the watershed. In this study, using water quality samples collected over a period of two and half years will effectively raise the efficacy and reliability of the factor analysis result. This will be a valuable reference for managing water pollution in the watershed. Additionally, results obtained using the proposed theory and method to analyze and interpret statistical data must be examined to verify their similarity to field data collected on the stream geographical and geological characteristics, the physical and chemical phenomena of stream self-purification, and the stream hydrological phenomena. In this research, the water quality data has been collected over two and half years so that sufficient sets of water quality data are available to increase the stability, effectiveness, and reliability of the final factor analysis results. This can be valuable references for managing, regulating and remediating water pollution in a reservoir watershed.   In this study, the AMOS computer program was induced to verify the validation of the factor analysis model. This study has proved that the end of the orthogonal rotation hypothesis first proposed in the four factor model. Each reaction index distribution is not a problem. Its internal and external quality are very good.