2nd Croatian Conference on Earthquake Engineering 2CroCEE

Based on the dataset of the liquefaction case histories collected in Canterbury, New Zealand, the artificial neural network was developed and applied to the data collected in the Petrinja earthquake.
CPTU testing covers many aspects of soil behaviour and allows for the estimation of parameters needed in liquefaction susceptibility analysis. During the 2010-2011 series of earthquakes in Christchurch and Canterbury in New Zealand, a very rich dataset was collected, connecting data on soil obtained by CPTU, data on the earthquakes, and the manifestations on the site – or lack of it. An artificial neural network was developed from these data.
The data collected after the Petrinja earthquake – obtained from CPTU tests and from analysis of the manifestations of liquefaction and the available data on the earthquake – are used in the developed artificial neural network.
Apart from the location and time description, the data comprise CPTU measurements, earthquakes’ magnitudes, medial of the peak ground acceleration, its standard deviation, depth of the water table, and classification of the liquefaction manifestation on the ground surface.
The experiences earned and conclusions on the versatility of such an approach are presented.