台灣地區生活用水量推估研究

Estimation for the Domestic Water Demand in Taiwan

許盈松(Yin-Sung Hsu) ； 郭雅煴(Ya-Yun Kuo) ； 陳昶憲(Chang-Sian Chen) ； 葉昭憲(Chao-Hsien Yeh) ； 王國樑(Kuo-Liang Wang)

《農業工程學報》 54卷4期 (2008/12) Pp. 33-43

https://doi.org/10.29974/JTAE.200812.0003

摘要

台灣地區四面環海，地狹人稠，降雨量豐枯不勻，加上缺乏足夠蓄水容積，致使水資源之有效利用率偏低。名手台灣在內的許多國家，目前都面臨水資源需求不斷增加，而現有水源卻有限的棘手問題。爲強化水資源管理工作，必須先對台灣地區各項用水標的供需現況，及未來之供需變化趨勢有所掌握。本研究針對台灣地區過去生活用水量之變動趨勢、影響因子與影響機制，詳加研究：建立生活用水量類神經綱路推估方法，研究結果顯示類神經綱路有很好的模擬效果，可提供生活用水量之需求推估，並作爲水資源規劃與管理之重要參據。

關鍵字

生活用水量 ； 用水量推估 ； 類神經綱路模式

並列摘要

Water-use efficiency in Taiwan is low because geo-morphologically Taiwan is a mountainous island, with dense population clustered along the narrow habitable perimeter of the island, and inadequate topographic features for storing sufficient water volumes. When the demand for water-resources increases as societies become more modernized, many countries including Taiwan are faced with the problems of limited water resources. In order to optimize water resources management, it is necessary to inventory the demand and supply of various water-use categories in all areas on the island and be able to predict their trends in the future. Domestic water is therefore the focus of this research project. Trend in the past, factors and mechanisms controlling domestic water use have been analyzed; and an artificial neural network (ANN) model has been developed to estimate the water demand needed for domestic water use. It is demonstrated that the ANN model has been successfully adopted to simulate the demand and supply trend in domestic water use. Therefore, the results from this study can be used as an important reference for the planning and management of water resources of Taiwan.

並列關鍵字

Domestic water use ； Water demand estimation ； Artificial Neural Networks model