| Summary: | 碩士 === 國立臺灣大學 === 農業工程學研究所 === 87 === The study applies the factor analysis, which may provide the general direction by summarizing, frimming and classifying the original data, to evaluate the groundwater pollution in the coastal area of Yun-Lin. The results show that the seawater salinization factor including EC, TDS, Cl-, SO42-, Na+, K+, and Mg2+, and the arsenic pollutant factor including Alk, TOC, and As, are two major influential factors on the groundwater quality in the coastal area of Yun-Lin. These factors consist of 78% representation for the groundwater quality .
Back-Propagation（BP）neural network which has the characteristics of self-organizing, self-learning and nonlinearity is applied to forecast future variation of groundwater quality. The influence of hidden nodes to the water quality forcasting is discussed first, the accuracy of the water quality forcasting results using different BP network input model are also analyzed. The results show that the hidden nodes are not a significant factor to BP network training and forcasting. Using recent variations data with high relativity in the input layer gives better results on network forcasting. Besides, the confidence intervals of each forcasting value are also computed. The results indicate that the neural network is capable to describe the complex variation of groundwater quality and provide good forecasting reliability.
|
|---|
