Satellite and street view images are widely used in various disciplines as a source of information for understanding the built environment. In natural hazard engineering, high-quality building inventory data sets are crucial for the simulation of hazard impacts and for supporting decision-making. Screening the building stocks to gather the information for simulation and to detect potential structural defects that are vulnerable to natural hazards is a time-consuming and labor-intensive task. This paper presents an automated method for extracting building information through the use of satellite and street view images. The method is built upon a novel transformer-based deep neural network we developed. Specifically, a multidomain learning approach is employed to develop a single compact model for multiple image-based deep learning information extraction tasks using multiple data sources (e.g., satellite and street view images). Our multidomain Vision Transformer is designed as a unified architecture that can be effectively deployed for multiple classification tasks. The effectiveness of the proposed approach is demonstrated in a case study in which we use pretrained models to collect regional-scale building information that is related to natural hazard risks.
28 October 2022 in Resilient Cities and Structures
Understanding and assessing the spatial extent of liquefaction requires that the spatial dependence of soil properties to be taken into account. In this work, a cone penetration test (CPT)-based approach for the evaluation of liquefaction potential is presented where the soil spatial variability is explicitly considered through internally-consistent probabilistic models developed at multiple scales. The novelty of the proposed work comes from the integration of the classical empirically-developed liquefaction criteria with tools in geostatistics and novel multiscale random-field models. A unique feature of the proposed work is its ability to refine and obtain higher resolution random fields for soil properties in critical areas, such as those adjacent to important infrastructure or in areas with detailed small-scale field data. An illustrative example assessing the liquefaction potential at various shaking levels in the Marina District of San Francisco is used to demonstrate the capability of the ...
1 April 2017 in Soil Dynamics and Earthquake Engineering