Search

The purpose of this study is to develop the analysis method for debris flow with soft computing. The soft computing methods which embrace neural networks and/or genetic algorithms (GA) are expected to solve problems which are defined imprecisely from a complex phenomena.The neural network combined with the GA was introduced into the analysis for the occurrence condition of debris flow. Training data sets to the LVQ network are optimized by the GA. Theprocedure was used to examine a characteristic change in occurrence condition of debris flow. Runoff analysis of debris flow by the use of GMDH was proposed. These methods were applied to the data for the Mizunashi River in the Unzen Volcano. The results led that the soft computing methods are useful for data analysis of the debris flow.

Unzen volcano began to erupt in November 1990 after 198 years of dormancy and was in violent activity. Continuous growth of lava dome and falls of lava rocks resulted in frequent pyroclastic flows. As a great volume of volcanic material deposited and scattered by the pyroclastic flows, debris flows frequently occurred along the Mizunashi River and damaged many houses in 1991-93. In 1995, the volcanic activity has become calm and no pyloclastic flow has been observed from March, 1995.With the change of the volcanic activity, the occurrence condition of debris flow is expected to change. The result of the data analysis indicates the abrupt change in the critical rainfall for occurrence of debris flow in July, 1993. The relation between rainfall and runoff of debris flow is also changed in the same period of the time.