Abstract
Regional damage simulation is a promising method to prepare organizations for the unforeseeable impact of a probable seismic natural hazard. Nonlinear time history analysis (NLTHA) of the finite element models (FEM) of the buildings in a region can provide resembling results to the actual buildings’ damages and responses. This approach requires large-scale computational resources, and to improve efficiency, parallel processing and representing building FEM models with lumped mass models are proposed. However, the computing complexity is still far-reaching when high-performance computing is not available. The building inventory of a region consists of numerous similar buildings with a limited number of distinct structures. In this paper, we propose a data-driven method that runs the NLTHA for the distinct structures exclusively and infers the damage and responses of other buildings using a surrogate model. Considering the skewed distribution of the buildings in a region, a novel informative sample selection method is proposed that is designed for bimodal sampling of the input domain. We use the Gaussian process regression as the surrogate model and compare the performance of different sample selection methods. The proposed method is able to approximate the results of the regional damage simulation regarding total economic loss estimation with 98.99% accuracy while reducing the computational demand to about 1/7th of the simulation processing time.
Highlights
Modeling the consequences of a major earthquake in a region can help us identify the vulnerabilities of buildings and communities, as well as plan emergency responses to reduce the expected loss (Afkhamiaghda et al, 2019)
We propose to use the representativeness and diversity (RD)-GSx method, which takes advantage of the immediate improvements of the RD method, and as the progress rate plateaus, it switches to the GSx method for adding the eccentric datapoints to the training set and further improves the overall predictive performance of the surrogate model
Based on the skewed distribution of buildings in a metropolitan area, a bimodal sampling strategy was proposed that selects the samples needed to train the surrogate model from the most informative datapoints
Summary
Modeling the consequences of a major earthquake in a region can help us identify the vulnerabilities of buildings and communities, as well as plan emergency responses to reduce the expected loss (Afkhamiaghda et al, 2019). We train the surrogate model using a limited number of NLTHA simulations, selected by the sampling method, and bypass the simulations for the majority of the buildings. This approach starts with gathering a dataset consisting building and ground motion variables in an attribute table. As we mentioned previously the sampling method needs to select from both ordinary buildings as well as the limited uncommon buildings If implemented successfully, this approach will return accurate damage estimations while reducing the computational demand of the regional damage and loss assessment considerably.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
