Abstract
This paper shows a newly developed liquefaction monitoring system. The methodology of the detection of liquefaction at boring point based on the observed and estimated peak ground acceleration on ground surface is proposed. The neural network is applied to the proposed methodology. It seems that the accuracy of the detected results is appropriate. Further, the case study in which the objective area is Amagasaki City is conducted and the accuracy of the proposed methodology is verified. Also because of the characteristic of knowledge update in the neural network, it is possible to develop the real-time system that can feedback the information of liquefaction just after earthquake.
