Estimation of Relative Pollutant Loads in a Lake Using Neural Network

概要

論文の詳細を見る
Pollution from diffuse sources in lakes and reservoirs has become a serious problem. The location of the diffuse source is still difficult to identify and the load from it is also difficult to estimate because of its inherent properties. The mechanism of the pollution from the diffuse sources is conceptually recognized, but the details, e. g., pathway to lakes and detention period in soil, are still obscure. Among the informative assets available, most of which are uncertain, observed water qualities and climatic conditions at some stations in lakes are certainly well quantified and reliable. This study aims to develop a method to estimate the relative pollutant loads of the diffuse sources using an artificial neural network, in which the observed water qualities and climate are used as keys to the solution. In addition, supplementary tutoring procedure to aid the training of the neural network is introduced to reduce the error in the estimation. The method developed is applied to Lake Biwa under some hypothetical conditions. The results show that the method successfully estimates the relative pollutant loads and hence its significant contribution to help water quality management of lakes will be expected.
日本雨水資源化システム学会の論文