{"title":"Optimized regression-based machine learning models for predicting chloride diffusion in concrete","authors":"Fatima Kechroud, Ali Benzaamia, Mohamed Ghrici","doi":"10.1007/s42107-025-01326-7","DOIUrl":"10.1007/s42107-025-01326-7","url":null,"abstract":"<div><p>Accurately predicting chloride diffusion in concrete is critical for assessing the durability and service life of reinforced concrete structures exposed to aggressive environments. Traditional models, particularly those relying on Fick’s second law of diffusion, struggle to capture the intricate, time-dependent characteristics of chloride transport. To address these limitations, this study investigates the predictive capabilities of five regression-based machine learning models—K-Nearest Neighbors Regressor (KNNR), Decision Tree Regressor (DTR), Random Forest Regressor (RFR), AdaBoost Regressor (AdaBR), and LightGBM Regressor (LGBMR)—for estimating the chloride diffusion coefficient (CDC) in concrete. A comprehensive dataset, compiled from multiple experimental studies, was used to train and evaluate the models. Bayesian optimization via the Optuna framework was employed to systematically tune hyperparameters and enhance model performance. The findings demonstrate that ensemble learning techniques, especially boosting-based models, provide superior predictive performance compared to conventional regression approaches. LightGBM achieved the highest predictive accuracy, with an R<sup>2</sup> of 0.95 and the lowest RMSE of 0.83 × 10⁻<sup>12</sup> m<sup>2</sup>/s in the test phase. Feature importance analysis revealed that the water-to-binder ratio and binder content were the most influential factors governing chloride diffusion, while exposure time, fly ash percentage, and curing time exhibited relatively lower impact. These findings highlight the potential of machine learning as a powerful tool for chloride transport modeling, providing a data-driven approach to improve the durability assessment of concrete structures.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 6","pages":"2513 - 2526"},"PeriodicalIF":0.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Revolutionizing bridge rehabilitation through artificial intelligence: a comprehensive review and future directions","authors":"Salma Ouhmida, Hanane Moulay Abdelali, Nouzha Lamdouar","doi":"10.1007/s42107-025-01322-x","DOIUrl":"10.1007/s42107-025-01322-x","url":null,"abstract":"<div><p>Bridge rehabilitation is essential for maintaining and restoring existing bridges, addressing safety deficiencies, and reducing life-cycle maintenance costs. Innovative solutions are crucial with aging infrastructure increasingly vulnerable to structural damage from natural disasters and climate change. This review examines the role of Artificial Intelligence (AI) in transforming bridge rehabilitation, offering enhanced resilience through optimized repair procedures, cost reduction, and improved public safety. AI technologies, including machine learning, neural networks, and computer vision, enable real-time monitoring, early detection of structural issues, and precise data analysis. The study synthesizes existing literature, emphasizing AI’s potential to enhance the assessment, design, and execution phases of rehabilitation while also reducing reliance on manual, subjective inspections. It highlights the integration of AI with digital twins, IoT devices, and predictive models, which enable autonomous inspection systems and data-driven decision-making. Additionally, the review explores future research directions, such as improving model interpretability and data quality. The findings underscore AI’s transformative impact on bridge rehabilitation, contributing to sustainable practices and extending the service life of critical infrastructure while ensuring safety and efficiency in transportation systems.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 6","pages":"2287 - 2301"},"PeriodicalIF":0.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A review of multi objective optimization in sustainable architecture: enhancing energy efficiency through dynamic facades","authors":"Jamshed V. Bhote, Trupti Ravindra Chauhan","doi":"10.1007/s42107-025-01331-w","DOIUrl":"10.1007/s42107-025-01331-w","url":null,"abstract":"<div><p>As urbanization fuels a 50% rise in global building energy demand since 2000, façades have become critical for sustainable architecture, supporting UN Sustainable Development Goals (SDGs) 7 (Affordable and Clean Energy) and 11 (Sustainable Cities). While multi-objective optimization (MOO) enables the balancing of energy efficiency, daylighting, and thermal comfort in façade design, its application remains limited in real-time adaptability and high-energy contexts like India’s hospitality sector. This study offers a novel bibliometric review of MOO in sustainable façade design, drawing publication trends from a Scopus dataset of 9,581 papers (2001–2024), which show a surge from 504 papers in 2001–2009 to 3,673 in 2010–2019, and 5,404 in 2020–2024. Detailed analysis, however, was conducted on 1,598 unique papers from an earlier Scopus dataset of 7,250 + articles, using VOSviewer and scientometric tools. Results indicate that the USA and China dominate (45% of output), while India contributes less than 5% despite its cooling demands. Evolutionary algorithms are prevalent (e.g., 6,122 mentions of ‘thermal’ optimization), yet gaps in dynamic shading (64 mentions) and life-cycle assessment persist. This review addresses these gaps, providing a roadmap for climate-responsive design in energy-intensive typologies by leveraging evolutionary algorithms, promoting dynamic shading integration, and advocating for real-time optimization frameworks tailored to regional climates. While the reliance on Scopus may limit coverage, the large datasets mitigate bias by capturing diverse trends. By highlighting MOO’s potential to reduce hotel cooling loads by up to 15.27% (Agharid et al. Energy Engineering, 121(12), 3549–3571,2024), this study advances performance-driven architecture, fostering sustainable urban development through innovative façade solutions.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 6","pages":"2319 - 2330"},"PeriodicalIF":0.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Flexural strengthening of concrete beams using prefabricated mortar laminates reinforced with GFRP bars and hybrid fibers","authors":"Reza Khaleghi, Mehrzad TahamouliRoudsari","doi":"10.1007/s42107-025-01330-x","DOIUrl":"10.1007/s42107-025-01330-x","url":null,"abstract":"<div><p>In this study, the flexural behavior of reinforced concrete beams strengthened with prefabricated mortar laminates reinforced with high-performance fiber-reinforced cementitious composite (PML-HPFRCC) was examined both numerically and experimentally. In addition to conducting bending tests on reinforced concrete beams, the performance of prefabricated mortar laminates was examined under both static and cyclic loading conditions. Three reinforced concrete beams were analyzed, including one reference beam and two reinforced with polymer fiber-reinforced prefabricated mortar laminates, featuring volume percentages of micro steel and polyvinyl alcohol contents of 1.8% and 0.5%, respectively. Numerical studies were conducted to evaluate the effects of the height of the strengthening plate and the percentage of reinforcement bars. The results from four-point bending tests demonstrated that the load-bearing capacity of beams reinforced with three and four polymer bars increased by 189% and 284%, respectively. Additionally, elastic stiffness increased by 28% and 92%, while energy absorption capacity decreased by 43% and 2.6%.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 6","pages":"2585 - 2604"},"PeriodicalIF":0.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Manish Sharma, Srishti Singh, Prahlad Prasad, Vishwajit Anand, Nazrul Islam
{"title":"Correlation analysis of ground motion intensity measures for seismic damage assessment: insights from near and far field records","authors":"Manish Sharma, Srishti Singh, Prahlad Prasad, Vishwajit Anand, Nazrul Islam","doi":"10.1007/s42107-025-01289-9","DOIUrl":"10.1007/s42107-025-01289-9","url":null,"abstract":"<div><p>This study examines the relationship between various earthquake ground motion parameters, offering valuable insights into structural behaviour. The analysis utilizes the horizontal components of motion from 71 pairs of far-field and 98 pairs of near-field ground motion records sourced from the PEER NGA West-2 Database. Factors such as event magnitude, source-to-site distance, and geological conditions at recording sites are carefully taken into account. Seism Signal software is employed to determine the ground motion parameters. A particular focus is placed on investigating the correlation between different ground motion parameters, especially the ratio of peak ground acceleration (PGA) to peak ground velocity (PGV), which is a critical parameter for classifying ground motion suites in nonlinear time history analyses of structures. Using Pearson correlation, the study highlights that mean time exhibits the strongest correlation with the PGA/PGV ratio for far-source earthquakes. Additionally, it identifies a more pronounced correlation between the PGA/PGV ratio and specific ground motion parameters in near-source earthquakes compared to far-source events.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 5","pages":"1973 - 2004"},"PeriodicalIF":0.0,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Koyndrik Bhattacharjee, Arijit Kumar Banerji, MD. Hamjala Alam, Chanchal Das
{"title":"Leakage detection in pipeline systems using machine learning","authors":"Koyndrik Bhattacharjee, Arijit Kumar Banerji, MD. Hamjala Alam, Chanchal Das","doi":"10.1007/s42107-025-01320-z","DOIUrl":"10.1007/s42107-025-01320-z","url":null,"abstract":"<div><p>The reliability of pipeline systems as a criterion is of enormous significance in sustainable pipeline operation and the protection of the environment. In their basic form, conventional leak detection techniques are often slow and not sensitive enough to suit many purposes, particularly in the early detection and control of leaks in large distributed systems. In this paper, we examine the application of machine learning—One-Class Support Vector Machine (SVM)—to the existing pipeline leak detection systems. Using both COMSOL Multiphysics for simulation and MATLAB for data analysis, this work proves that machine learning is applicable to improve leakage assessment. Using detailed simulations under various operational conditions, the k coefficients of the One-Class SVM model pinpoint pressure, temperature, and velocity abnormalities that suggest leakage. The results also clearly indicate the model’s effectiveness in accurately identifying leak locations in addition to simply identifying their presence, making it a significant improvement over current approaches by increasing response speed while decreasing possible losses and threats to the environment.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 6","pages":"2465 - 2473"},"PeriodicalIF":0.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Seismic analysis of a multi-storied irregular steel building with different types of dampers and base isolation systems","authors":"Anuradha R. Babar, S. N. Patil","doi":"10.1007/s42107-025-01324-9","DOIUrl":"10.1007/s42107-025-01324-9","url":null,"abstract":"<div><p>This study investigates the seismic performance of a G + 10 multi-storied irregular steel building with L-shaped and T-shaped configurations, focusing on the effectiveness of damping and base isolation systems. The research aims to analyze the structural response of the building under various seismic conditions using ETABS software, considering damping mechanisms (viscous and friction dampers) and base isolation techniques (friction pendulum system and lead plug bearing). The study explores different seismic zones (II, III, IV, and V) and soil conditions (rock, medium, and soft soil) to assess parameters such as storey drift, storey displacement, and base shear. The findings reveal that hybrid combinations of damping and base isolation techniques significantly enhance seismic resilience, with friction pendulum bearings and lead plug bearings providing superior performance. The application of hybrid systems led to a reduction in seismic responses by up to 50% in high-risk zones. The T-shaped buildings exhibited higher seismic responses than L-shaped structures due to their geometric irregularity, but optimized damping and isolation systems mitigated these effects. The research also highlights the critical role of soil-structure interaction, with soft soil amplifying seismic forces by 40–50%. These findings emphasize the need for advanced seismic mitigation strategies, particularly for irregular steel structures in earthquake-prone areas. The results offer valuable insights for structural engineers and policymakers, advocating for the integration of hybrid damping and base isolation systems in seismic design codes.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 6","pages":"2499 - 2512"},"PeriodicalIF":0.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohammad Ali Khasawneh, Ibrahim Khalil Umar, Ahmad Ali Khasawneh
{"title":"Explainable artificial intelligence model for accident severity modeling","authors":"Mohammad Ali Khasawneh, Ibrahim Khalil Umar, Ahmad Ali Khasawneh","doi":"10.1007/s42107-025-01318-7","DOIUrl":"10.1007/s42107-025-01318-7","url":null,"abstract":"<div><p>Accident severity prediction is a critical challenge in traffic safety management, emergency response, and urban mobility planning. Road accidents remain a leading cause of fatalities worldwide, yet existing accident analysis frameworks often lack predictive accuracy, interpretability, and real-time decision-making capabilities. Traditional statistical models fail to capture complex interactions between vehicle attributes, driver behavior, and environmental factors, limiting their effectiveness in accident severity assessment. This study addresses these gaps by developing an explainable artificial intelligence (XAI) framework for accident severity prediction, leveraging machine learning models (Random Forest, Extreme Gradient Boosting, Support Vector Machine, and Naïve Bayes) and SHapley Additive exPlanations (SHAP) analysis to enhance model transparency. The dataset, sourced from the Fatality Analysis Reporting System (FARS), consists of 7394 recorded crashes and incorporates key predictors such as airbag deployment, control devices, seatbelt usage, and driver demographics. Experimental results demonstrate that XGBoost outperforms other models, achieving the highest accuracy (80.8%), recall (80.8%), and F1-score (81.0%), making it the most reliable classifier for distinguishing between severe and non-severe accidents. SHAP analysis reveals that airbag deployment, seatbelt usage, and control devices significantly impact accident severity outcomes, providing valuable insights into policy-driven interventions and traffic management strategies. Despite its effectiveness, the study highlights limitations such as data imbalance, lack of real-time behavioral factors, and exclusion of non-fatal crashes, suggesting deep learning integration, real-time telematics, and hybrid AI models in future research. The proposed framework offers a data-driven approach to accident severity prediction, improving road safety policies, vehicle design enhancements, and emergency response efficiency.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 6","pages":"2433 - 2445"},"PeriodicalIF":0.0,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Vulnerability assessment of vertical irregularities in medium-rise reinforced concrete structures using lead rubber bearing","authors":"Sonal A. Chavan, Nilesh U. Mate","doi":"10.1007/s42107-024-01260-0","DOIUrl":"10.1007/s42107-024-01260-0","url":null,"abstract":"<div><p>Medium-rise reinforced concrete structures with vertical irregularities experience vulnerable behavior during seismic forces. To mitigate this vulnerable behavior, the base isolation technique is more effective than the strategies used to protect the civil structure against seismic excitation, as Iuliis (2008) stated. Base isolation is a technique to separate the structure from the seismic effect developed in the form of ground acceleration. The acceleration parameter, base shear, story displacement at the top and ground floors, story drift ratios, and target periods are considered for parametric study. The results demonstrate that the base isolator with stiffness coefficient reduces the structure's base shear and top floor displacement.</p><p>Similarly, the combined effects of base isolation and SSI create a more complex system that does not behave straightforwardly compared to simpler models. The use of LRB shows results similar to those of medium-stiff soil strata during building analysis. The LRB reduces the sudden increase in the inter-story drift at the stiffness irregularity location.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 5","pages":"2255 - 2273"},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Enhancing structural health monitoring with AI-ML algorithms: a focus on crack detection and prediction","authors":"Ahmad Bader, Amir Shtayat, Bara’ Al-Mistarehi","doi":"10.1007/s42107-024-01261-z","DOIUrl":"10.1007/s42107-024-01261-z","url":null,"abstract":"<div><p>SHM is a very important process in terms of the safety and durability of infrastructure. Traditional SHM often faces problems detecting minor structural defects and handling large datasets. Therefore, certain more advanced approaches are called for. The paper discussed the applications of AI and ML algorithms, such as CatBoost and the African Vultures Optimization Algorithm, for such challenges. The research is based on a unique dataset of 8,541 rows and diverse features, developing a predictive framework that enhances crack detection and forecast capabilities. The approach mainly deals with heterogeneous data using the CatBoost algorithm, given its capability for high-accuracy predictions, while AVOA optimizes feature selection, reduces the computational cost, and guarantees no loss in model performance. This methodology has resulted in a significant enhancement of the prediction accuracy, which states the importance of AI-ML integration in SHM. The key results demonstrate the effectiveness of the model in detecting structural anomalies and crack propagation to enable proactive maintenance strategies. This study’s contributions have gone toward advancing SHM with scalable and efficient AI-ML frameworks, enabling real-time monitoring for better infrastructure management. Such development might have a transforming potential to cut down on maintenance costs and enhance operational safety, thus further encouraging sustainable infrastructure systems.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 5","pages":"1907 - 1918"},"PeriodicalIF":0.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}