ABSTRACT
A new artificial neural network (ANN) system was developed for assessing the damage risk due to liquefaction during an earthquake, based only on seismic records. Compared to conventional technology that requires information about the soil properties and constitution, there is a great advantage in being able to estimate damage from seismic records alone. Further, if small- and medium-level intensity earthquake records can be used to determine the risk of liquefaction in advance, preventive measures can be taken to avoid it. Here, we introduce the results of applying this system to the liquefaction damage observed during the 2011 Great East Japan Disaster in the Kanto area of Japan. In addition, we have made the system available to the public via the Internet, so we will also discuss how to use it.
