Abstract
At Unzen Volcano, debris flows have frequently occurred in the Mizunashi River and caused severe damage in the downstream by depositing large amount of sands and stones. Therefore it is great important to estimate the amount of deposits for protecting the area from the disasters. In this study, the neural networks which can learn a general rule from given examples is used to estimate the amount of deposits due to rainfall. The results of the predictions lead to the conclusion that the neural networks is applicable to estimate the amount of debris flow.
