Abstract
Australia is a relatively stable continental region but not tectonically inert, having geological conditions that are susceptible to liquefaction when subjected to earthquake ground motion. Liquefaction hazard assessment for Australia was conducted because no Australian liquefaction maps that are based on modern AI techniques are currently available. In this study, several conditioning factors including Shear wave velocity (Vs30), clay content, soil water content, soil bulk density, soil thickness, soil pH, distance from river, slope and elevation were considered to estimate the liquefaction potential index (LPI). By considering the Probabilistic Seismic Hazard Assessment (PSHA) technique, peak ground acceleration (PGA) was derived for 50 yrs period (500 and 2500 yrs return period) in Australia. Firstly, liquefaction hazard index (LHI) (effects based on the size and depth of the liquefiable areas) was estimated by considering the LPI along with the 2% and 10% exceedance probability of earthquake hazard. Secondly, ground acceleration data from the Geoscience Australia projecting 2% and 10% exceedance rate of PGA for 50 yrs were used in this study to produce earthquake induced soil liquefaction hazard maps. Thirdly, deep neural networks (DNNs) were also exerted to estimate liquefaction hazard that can be reported as liquefaction haz-ard base maps for Australia with an accuracy of 94% and 93%, respectively. As per the results, very-high liquefaction hazard can be observed in Western and Southern Australia including some parts of Victoria. This research is the first ever country-scale study to be considered for soil liquefaction hazard in Australia using geospatial information in association with PSHA and deep learning techniques. This study used an earthquake design magnitude threshold of Mw 6 using the source model characterization. The resulting maps present the earthquake-triggered liquefaction hazard and are intending to establish a conceptual structure to guide more detailed investigations as may be required in the future. The limitations of deep learning models are complex and require huge data, knowledge on topology, parameters, and training method whereas PSHA follows few assumptions. The advantages deal with the reusability of model codes and its transferability to other similar study areas. This research aims to support stakeholders' on decision making for infrastructure investment, emergency planning and prioritisation of post-earthquake reconstruction projects. (c) 2022 China University of Geosciences (Beijing) and Peking University.