RC shear walls are commonly used as lateral load-resisting elements in seismic regions, and the estimation of their shear strengths can become simultaneously design-critical and complex when they have so-called squat geometries, i.e., height-to-length ratios less than two. This paper presents a study on the training and interpretation of an advanced machine-learning model that strategically combines two algorithms for the said purpose. To train the model, a comprehensive shear strength database of 434 samples of squat RC walls is utilized. First, the eXtreme Gradient Boosting (XGBoost) algorithm is used to establish a predictive model for estimating the shear strength, wherein 70% and 30% of the data are respectively used for training and validation. This effort resulted in an approximately 97% validation accuracy, which well exceeds current mechanics-based/semiempirical models. Second, the SHapley Additive exPlanations (SHAP) algorithm is used to estimate the relative importance of the factors affecting XGBoost’s shear strength estimates. This step thus enabled physical and quantitative interpretations of the input-output dependencies, which are nominally hidden in conventional machine-learning approaches. Through this setup, several squat wall attributes are identified as being critical in shear strength estimates.

Effective post‐earthquake response requires a prompt and accurate assessment of earthquake‐induced damage. However, existing damage assessment methods cannot simultaneously meet these requirements. This study proposes a framework for real‐time regional seismic damage assessment that is based on a Long Short‐Term Memory (LSTM) neural network architecture. The proposed framework is not specially designed for individual structural types, but offers rapid estimates at regional scale. The framework is built around a workflow that establishes high‐performance mapping rules between ground motions and structural damage via region‐specific models. This workflow comprises three main parts—namely, region‐specific database generation, LSTM model training and verification, and model utilization for damage prediction. The influence of various LSTM architectures, hyperparameter selection, and dataset resampling procedures are systematically analyzed. As a testbed for the established framework, a case study is performed on the Tsinghua University campus buildings. The results demonstrate that the developed LSTM framework can perform damage assessment in real time at regional scale with high prediction accuracy and acceptable variance.

Abutment-backfill soil interaction can significantly influence the seismic response of bridges. In the present study, we provide numerical simulation models that are validated using data from recent experiments on the lateral response of typical abutment systems. Those tests involve well-compacted clayey silt and silty sand backfill materials. The simulation methods considered include a method of slices approach for the backfill materials with an assumed log-spiral failure surface coupled with hyperbolic soil stress-strain relationships [referred to as “log-spiral hyperbolic (LSH) model”] as well as detailed finite-element models, both of which were found to compare well with test data. Through parametric studies on the validated LSH model, we develop equations for the lateral load-displacement backbone curves for abutments of varying height for the two aforementioned backfill types. The equations describe a hyperbolic relationship between lateral load per unit width of the abutment wall and the wall defl...