No abstract

No abstract

No abstract

As urban systems become more highly sophisticated and interdependent, their vulnerability to earthquake events exhibits a significant level of uncertainties. Thus, community-level seismic risk assessments are indispensable to facilitate decision making for effective hazard mitigation and disaster responses. To this end, new frameworks for pre-and post-earthquake regional loss assessments are proposed using deep learning methods. First, to improve the accuracy of the response prediction of individual structures during the pre-earthquake loss assessment, a widely used nonlinear static procedure is replaced by the recently developed probabilistic deep neural network model. The variabilities of the nonlinear responses of a structural system given the seismic intensity can be quantified during the loss assessment process. Second, to facilitate near-real-time post-earthquake loss assessments, an adaptive algorithm, which identifies the optimal number and locations of sensors in a given urban area, is proposed. Using a deep neural network that estimates area-wide structural damage given the spatial distribution of the seismic intensity levels as a surrogate model, the algorithm adaptively places additional sensors at property lots at which errors from surrogate estimations of the structural damage are the greatest. Note that the surrogate model is constructed before earthquake events using simulated datasets. To test and demonstrate the proposed frameworks, the paper introduces thorough numerical investigations of two hypothetical urban communities. The proposed frameworks using the deep learning methods are expected to make critical advances in pre-and post-earthquake regional loss assessments. K E Y W O R D Sadaptive algorithm, deep learning, earthquake, optimal sensor placement, probabilistic seismic risk assessment, surrogate model

To accurately predict the seismic demands of structural systems, a proper set of ground motions representing the seismic hazard of a given site is needed. In general, such a set includes a large number of ground motions, and thus may result in high computational cost. To address this computational challenge without compromising the accuracy of structural fragility, this paper proposes a clustering‐based algorithm that can select a representative subset of ground motions adaptively from a given set of ground motions. First, critical features of ground motions that significantly affect seismic demands of the structural system are identified by Lasso regression of seismic responses of various single degree of freedom systems on existing intensity measures of ground motions. Second, ground motions are selected adaptively based on the hierarchical clustering of the critical features until the fragility curve converges. Applications to a reinforced concrete building and steel moment‐resisting frames demonstrate the improved efficiency and wide applicability of the proposed method. The results of the numerical examples confirm the robust performance of the proposed algorithm against various ground motions, structural types, and definitions of the limit‐states. The proposed algorithm enables us to obtain structural fragilities using a significantly reduced number of ground motions while keeping consistency with the available ground motion set.