Search for: All records

Real-time Hybrid Simulation (RTHS) is a technique wherein a structural system is divided into an analytical and an experimental substructure. The former is modeled numerically while the latter is physically present in the laboratory. The two substructures are kinematically linked together at their interface degrees of freedom (DOFs) and the equations of motion are solved in real-time to determine the structure’s response. One of the main challenges of RTHS is to include the effects of soil–foundation–structure interaction (SFSI), which can have a substantial effect on the overall response. The soil domain cannot be modeled experimentally due to the large payload size. On the other hand, modeling the soil domain numerically, using a continuum-based approach, in real-time is challenging due to the associated computational cost. To address these issues, this paper presents a framework for seismic RTHS of SFSI systems using a Neural Network (NN)-based macroelement model of the soil–foundation system. A coupled SFSI model is used to train the NN model and the loss function is based on dynamic equilibrium at the interface between the foundation and the structure. The framework is demonstrated using a three-story building with the lateral load resisting system comprised of moment resisting and damped brace frames. The proposed framework ensures a stable and accurate RTHS, accounting for SFSI by incorporating: (a) spring elements at the output DOFs of the NN model to remove rigid body modes; (b) dashpot elements at the output DOFs of the NN model to mitigate spurious higher frequencies of vibration; and (c) regularization in the NN model’s architecture with data augmentation to reduce overfitting. 

Abstract The Ice-sheet and Sea-level System Model (ISSM) provides numerical solutions for ice sheet dynamics using finite element and fine mesh adaption. However, considering ISSM is compatible only with central processing units (CPUs), it has limitations in economizing computational time to explore the linkage between climate forcings and ice dynamics. Although several deep learning emulators using graphic processing units (GPUs) have been proposed to accelerate ice sheet modeling, most of them rely on convolutional neural networks (CNNs) designed for regular grids. Since they are not appropriate for the irregular meshes of ISSM, we use a graph convolutional network (GCN) to replicate the adapted mesh structures of the ISSM. When applied to transient simulations of the Pine Island Glacier (PIG), Antarctica, the GCN successfully reproduces ice thickness and velocity with a correlation coefficient of approximately 0.997, outperforming non-graph models, including fully convolutional network (FCN) and multi-layer perceptron (MLP). Compared to the fixed-resolution approach of the FCN, the flexible-resolution structure of the GCN accurately captures detailed ice dynamics in fast-ice regions. By leveraging 60–100 times faster computational time of the GPU-based GCN emulator, we efficiently examine the impacts of basal melting rates on the ice sheet dynamics in the PIG. 

Abstract Airborne radar sensors capture the profile of snow layers present on top of an ice sheet. Accurate tracking of these layers is essential to calculate their thicknesses, which are required to investigate the contribution of polar ice cap melt to sea-level rise. However, automatically processing the radar echograms to detect the underlying snow layers is a challenging problem. In our work, we develop wavelet-based multi-scale deep learning architectures for these radar echograms to improve snow layer detection. These architectures estimate the layer depths with a mean absolute error of 3.31 pixels and 94.3% average precision, achieving higher generalizability as compared to state-of-the-art snow layer detection networks. These depth estimates also agree well with physically drilled stake measurements. Such robust architectures can be used on echograms from future missions to efficiently trace snow layers, estimate their individual thicknesses, and thus support sea-level rise projection models.