RC shear walls are commonly used as lateral load-resisting elements in seismic regions, and the estimation of their strengths can become simultaneously design-critical complex when they have so-called squat geometries, i.e., height-to-length ratios less than two. This paper presents a study on training interpretation an advanced machine-learning model that strategically combines two algorithms for said purpose. To train model, comprehensive strength database 434 samples is utilized. First,...

Abstract Every year, earthquakes result in severe economic losses and a significant number of casualties worldwide. In limiting the that occur after these extreme events, timely accurate assessment seismic damages mobilizing proportionate post‐event relief efforts play crucial roles. Traditional on‐site investigation generally results prolonged evaluation windows. Several computational alternatives exist show promise addressing downsides traditional approach. Damage estimates based on...

Abstract Effective post‐earthquake response requires a prompt and accurate assessment of earthquake‐induced damage. However, existing damage methods cannot simultaneously meet these requirements. This study proposes framework for real‐time regional seismic that is based on Long Short‐Term Memory (LSTM) neural network architecture. The proposed not specially designed individual structural types, but offers rapid estimates at scale. built around workflow establishes high‐performance mapping...

Inelastic response of reinforced concrete columns to combined axial and flexural loading is characterized by plastic deformations localized in small regions, which are idealized as hinges. Under extreme events such earthquakes, the load-carrying deformation capacities beam/columns highly dependent on accuracy this idealization for hinge length a key parameter. From design perspective, column can only attain ductility characteristics prescribed its performance level if it provided with...

The capabilities of data-driven models based on machine learning (ML) algorithms in offering accurate predictions structural responses efficiently have been demonstrated numerous recent studies. However, efforts to date relied essentially deterministic approaches, and prediction confidence measures were either derived from verification data sets or completely ignored. This study examined the potential a new algorithm—natural gradient boosting (NGBoost)—that directly produces probabilistic...

Background Accurate simulation of wildfires can benefit pre-ignition mitigation and preparedness, post-ignition emergency response management. Aims We evaluated the performance Weather Research Forecast-Fire (WRF-Fire), a coupled fire-atmosphere wildland fire platform, in simulating large historic (2018 Camp Fire). Methods A baseline model based on setup typically used for WRF-Fire operational applications is utilised to simulate Fire. Simulation results are compared high-temporal-resolution...

Accurate estimation of fuels is essential for wildland fire simulations as well decision-making related to land management. Numerous research efforts have leveraged remote sensing and machine learning classifying cover mapping forest vegetation species. In most cases that focused on surface fuel mapping, the spatial scale interest was smaller than a few hundred square kilometers; thus, many small-scale site-specific models had be created landscape at national scale. The present work aims...

Abstract Structural seismic safety assessment is a critical task in maintaining the resilience of existing civil and infrastructures. This commonly requires accurate predictions structural responses under stochastic intensive ground accelerations via time‐costly numerical simulations. While numerous studies have attempted to use machine learning (ML) techniques as surrogate models alleviate this computing burden, large number simulations are still required for training ML models. Therefore,...

Abutment-backfill soil interaction can significantly influence the seismic response of bridges. In present study, we provide numerical simulation models that are validated using data from recent experiments on lateral typical abutment systems. Those tests involve well-compacted clayey silt and silty sand backfill materials. The methods considered include a method slices approach for materials with an assumed log-spiral failure surface coupled hyperbolic stress-strain relationships [referred...

Herein, we propose a method based on the existing second-order blind identification of underdetermined mixtures technique for identifying modal characteristics—namely, natural frequencies, damping ratio, and real-valued partial mode shapes all contributing modes—of structures with limited number sensors from recorded free/ambient vibration data. In approach, statistics signals are used to recover coordinates shapes. Conventional versions this approach require be equal or greater than active...

SUMMARY Dynamic characteristics of structures — viz. natural frequencies, damping ratios, and mode shapes are central to earthquake‐resistant design. These values identified from field measurements useful for model validation health‐monitoring. Most system identification methods require input excitations motions be measured the structural response; however, true seldom recordable. For example, when soil–structure interaction effects non‐negligible, neither free‐field nor recorded responses...

Advances in smart infrastructure produces a natural demand of system identification techniques for structural health and performance monitoring that can be scaled to regions large asset inventories. Conventional approaches require sensors installed, often long-term deployments, on the monitored systems, which is costly undertaking when thousands systems (e.g., bridges) need monitored. This paper presents novel mode shape method bridges uses data collected from moving vehicles as input—a...

Abstract Using results from 57 large‐scale physics‐based fault‐rupture and wave propagation simulations, this research aims to evaluate the seismic risk, loss, resilience of more than 16,000 reinforced concrete buildings in Zeytinburnu district Istanbul, Turkey. For each building under earthquake scenario, spatially varying site‐specific simulated ground motions were used for performing three‐dimensional nonlinear time‐history analyses. The resulting structural responses—such as peak story...

Multi-span reinforced concrete (RC) curved box-girder bridges are commonly designed to facilitate traffic flow at highway interchanges. The Aksemsettin Viaduct (henceforth, A for brevity) in Istanbul, Turkey, is an eleven-span interchange bridge with a total length of 596.8 m. Located high seismicity zone, the deck, multiple bearings that have different isolation mechanisms bents and directions, ten rectangular columns unequal heights, mix pile foundations spread footings. significant...