Urban scale assessment of buildings’ liquefaction vulnerability

The extensive injury caused to buildings by liquefaction during past earthquakes, with the uneven spatial distribution of damage, raises the need for rapid predictive tools, applicable at a large scale, that comprehensively account for the properties of earthquake, subsoil and structure. A method is herein proposed to quantify the angular distortion of framed low-rise buildings based on a simple characterization of the above factors. The analysis moves from past literature criteria introduced to quantify the vulnerability of buildings under static conditions and extends their applicability to liquefaction assessment integrating parametric two-dimensional numerical analyses with recent literature predictive formulas and machine learning inference. The numerical calculation, performed for variable stratigraphic and mechanical characteristics of the subsoil, ground motion and equivalent flexural stiffness of the foundation, quantifies the role of each factor on the absolute settlement and angular distortion. Then the dependency on the different factors of the angular distortion is inferred with an artificial neural network (ANN), grouping parameters to limit the number of input variables and express results with charts that make prediction more accessible.