Data-Driven Modeling of Lateral and Cracking Loads in Confined Masonry Walls Using Machine Learning DOI Creative Commons

Hamza Mahamad Bile,

Kadir Güler

Buildings, Journal Year: 2024, Volume and Issue: 14(12), P. 4016 - 4016

Published: Dec. 18, 2024

Confined masonry (CM) is becoming a widely adopted construction building method even in earthquake-prone regions due to its economic viability, simplicity, and material availability. However, existing empirical models for predicting lateral cracking loads often fall short varied properties, detailing of confining elements practices. In this study, machine learning (ML) algorithms, such as Extreme Gradient Boosting (XGB), Random Forest (RF), Extremely Randomized Tree (ERT), were employed predict the seismic performance CM walls, focusing on maximum load capacity based an experimental dataset from 84 published studies, with 59 samples training 25 testing. Different material, load, geometrical, reinforcement detailing, related CM, considered. This study also compares equations against proposed ML models. The demonstrated strong predictive capabilities, outperforming both predictions, XGBoost yielding highest accuracy, reflected by R2 values 0.903 0.876 lowest RMSE (28.742 23.982 load). Additionally, comparative analysis shows that while some produce reasonably accurate most exhibit significant deviations results. finally employs Partial Dependence Plot (PDP) explain importance contribution factors influence strength, concludes models, especially XGBoost, are highly effective capturing complex behavior walls under vertical loads, making them valuable tools enhancing accuracy evaluations.

Language: Английский

A systematic review of trustworthy artificial intelligence applications in natural disasters DOI Creative Commons
A. S. Albahri, Yahya Layth Khaleel, Mustafa Abdulfattah Habeeb

et al.

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 118, P. 109409 - 109409

Published: June 29, 2024

Artificial intelligence (AI) holds significant promise for advancing natural disaster management through the use of predictive models that analyze extensive datasets, identify patterns, and forecast potential disasters. These facilitate proactive measures such as early warning systems (EWSs), evacuation planning, resource allocation, addressing substantial challenges associated with This study offers a comprehensive exploration trustworthy AI applications in disasters, encompassing management, risk assessment, prediction. research is underpinned by an review reputable sources, including Science Direct (SD), Scopus, IEEE Xplore (IEEE), Web (WoS). Three queries were formulated to retrieve 981 papers from earliest documented scientific production until February 2024. After meticulous screening, deduplication, application inclusion exclusion criteria, 108 studies included quantitative synthesis. provides specific taxonomy disasters explores motivations, challenges, recommendations, limitations recent advancements. It also overview techniques developments using explainable artificial (XAI), data fusion, mining, machine learning (ML), deep (DL), fuzzy logic, multicriteria decision-making (MCDM). systematic contribution addresses seven open issues critical solutions essential insights, laying groundwork various future works trustworthiness AI-based management. Despite benefits, persist In these contexts, this identifies several unused used areas disaster-based theory, collects ML, DL techniques, valuable XAI approach unravel complex relationships dynamics involved utilization fusion processes related Finally, extensively analyzed ethical considerations, bias, consequences AI.

Language: Английский

Citations

48
RAGN-R: A multi-subject ensemble machine-learning method for estimating mechanical properties of advanced structural materials DOI
Farzin Kazemi, Aybike Özyüksel Çiftçioğlu, Torkan Shafighfard

et al.

Computers & Structures, Journal Year: 2025, Volume and Issue: 308, P. 107657 - 107657

Published: Jan. 27, 2025

Language: Английский

Citations

13
Compressive strength prediction models for concrete containing nano materials and exposed to elevated temperatures DOI Creative Commons
Hany A. Dahish, Ahmed D. Almutairi

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 103975 - 103975

Published: Jan. 1, 2025

Language: Английский

Citations

5
Data-Driven Machine-Learning-Based Seismic Response Prediction and Damage Classification for an Unreinforced Masonry Building DOI Creative Commons
Nagavinothini Ravichandran, Butsawan Bidorn, Oya Mercan

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 1686 - 1686

Published: Feb. 7, 2025

Unreinforced masonry buildings are highly vulnerable to earthquake damage due their limited ability withstand lateral loads, compared other structures. Therefore, a detailed assessment of the seismic response and resultant associated with such becomes necessary. The present study employs machine learning models effectively predict classify level for benchmark unreinforced building. In this regard, eight regression-based models, namely, Linear Regression (LR), Stepwise (SLR), Ridge (RR), Support Vector Machine (SVM), Gaussian Process (GPR), Decision Tree (DT), Random Forest (RF), Neural Networks (NN), were used building’s responses. Additionally, classification-based Naïve Bayes (NB), Discriminant Analysis (DA), K-Nearest Neighbours (KNN), Adaptive Boosting (AB), DT, RF, SVM, NN, explored purpose categorizing states material properties intensity considered as input parameters. results from regression indicate that GPR model efficiently predicts larger coefficients determination smaller root mean square error values than models. Among AB, NN accuracy levels 92.9%, 91.1%, 92.6%, respectively. conclusion, overall performance non-parametric GPR, was found be better parametric

Language: Английский

Citations

1
A state-of-the-art analysis of base isolation systems and future directions for developing a novel multi-directional smart-hybrid isolation system integrated with earthquake early warning system for building structures DOI Creative Commons
TARIQ H. R. BERMANY, Siti Aminah Osman, Mohd Yazmil Md Yatim

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: 25, P. 104501 - 104501

Published: March 1, 2025

Language: Английский

Citations

1
Fragility assessment of steel jacket offshore platforms using time series prediction with deep learning methods DOI

Rashid Ali,

Hamed Rahman Shokrghozar

Ships and Offshore Structures, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 16

Published: March 3, 2025

Language: Английский

Citations

0
Forecasting Earthquake-induced Ground Movement under Seismic Activity Using Response Surface DOI Creative Commons
Kennedy C. Onyelowe, Denise‐Penelope N. Kontoni,

Fortune K. C. Onyelowe

et al.

Published: March 24, 2025

This study employs Response Surface Methodology (RSM) to model and optimize earthquake-induced ground movements in gravelly geohazard-prone environments. RSM efficiently evaluates the interactions of seismic parameters, including soil type, fault distance, peak acceleration (PGA), reducing computational experimental efforts. A dataset 234 entries encompassing 11 stress variables was curated analyzed, yielding a high-precision predictive with an R² 0.9997. The resulting closed-form equation facilitates accurate risk assessment, structural safety optimization, resilience planning. By identifying critical thresholds nonlinear relationships, supports cost-effective mitigation strategies, infrastructure design, retrofitting earthquake-prone regions.

Language: Английский

Citations

0
Predicting Pull-out Strength and Failure Modes of Metal Anchors Embedded in Masonry Structures Using Explainable Machine Learning Models and Empirical Equations DOI Creative Commons

Aryan Baibordy,

Mohammad Yekrangnia

Results in Engineering, Journal Year: 2025, Volume and Issue: 26, P. 105287 - 105287

Published: May 11, 2025

Language: Английский

Citations

0
A spatial building damage inventory of the 2022 Luding Earthquake and its preliminary vulnerability analysis DOI
Chenxiao Tang,

Xi Feng

Journal of Mountain Science, Journal Year: 2025, Volume and Issue: 22(5), P. 1691 - 1706

Published: May 1, 2025

Language: Английский

Citations

0
Innovative approach to estimate structural damage using linear regression and K-nearest neighbors machine learning algorithms DOI Creative Commons
Vasile Calofir,

Ruben-Iacob Munteanu,

Mircea Ştefan Simoiu

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102250 - 102250

Published: May 14, 2024

Conventional structural design methodologies often utilize elastic analysis techniques, such as the equivalent static force method and response spectrum method. While these methods are known for their simplicity computational efficiency, they prove inadequate in capturing extent of damage caused by seismic forces. Additionally, employing nonlinear dynamic to estimate represents a challenging intricate task, posing difficulties many designers. Consequently, objective this paper is present an innovative methodology evaluating moment-resisting frame structures. This involves utilization machine learning algorithms, which have been trained tested on large data set generated using newly developed numerically efficient simulation procedure. The algorithms employ both linear regression K-nearest neighbors approaches accurately replicate Park-Ang index.

Language: Английский

Citations

3