Neural Network Expression for Water Purification in a River and the Application to Tamagawa in Tokyo

We discuss water purification in a river through cities, where indexes of the water quality are BOD, COD, T-N and T-P. To express changes of the quality, we introduce a model for purify functions in a river. The function is complex and non-linear. So, we use multi-layer neural networks and construct a function in the network, and use the derivatives for the cause and the effect of water quality. As for the learning and test data, we use ideal data derived from observations of the Tamagawa in Tokyo and add uniform random numbers to them. Since the model calculations represent river purification well, we apply the model to the Tamagawa. Thus, we can estimate the water purification functions, and find the river has no decomposing power for the nitrogen substances today.