工业工程最新文献

{"title":"Knowledge and practice of earthquake management among apartment dwellers: A case study of Jakarta City, Indonesia","authors":"Fatmah ,&nbsp;Irene Sondang Fitrinitia ,&nbsp;Sumiaty Ambran","doi":"10.1016/j.jnlssr.2025.100225","DOIUrl":"10.1016/j.jnlssr.2025.100225","url":null,"abstract":"<div><div>Urban city apartments and flat dwellers face increasing threats from earthquakes, and the current understanding and implementation of earthquake risk reduction techniques in high-rise housing communities remain lacking. Therefore, this study examined the relationships between earthquake management practices and demographic characteristics, vertical housing features, earthquake management knowledge, and emergency response plans. The research employed a cross-sectional study design and included 215 participants from 14 selected apartments. The findings indicated that (1) earthquake management practices vary among individuals aged 35–54, types of dwelling units, dwelling sizes, numbers of rooms, those who have resided in an apartment for 3–5 years, emergency response plans, and knowledge regarding earthquake management (before, during, and after); (2) earthquake management knowledge levels (including mitigation and self-rescue knowledge during an earthquake) are low; (3) emergency response and earthquake management practices are insufficient; and (4) apartment dwellers with moderate knowledge levels of earthquake self-rescue are 12.2 times more likely to have moderate earthquake management practices than those without (OR = 12.2, <em>p</em> = 0.000). The study recommends that the National Disaster Management Authority and the Jakarta City Disaster Risk Reduction Forum collaborate with building managers to develop an annual earthquake mitigation programme to enhance knowledge levels regarding earthquake risk reduction.</div></div>","PeriodicalId":62710,"journal":{"name":"安全科学与韧性(英文)","volume":"7 1","pages":"Article 100225"},"PeriodicalIF":3.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145018430","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":"Optimizing urban infrastructure resilience: Analyzing cascading failures and critical node dependencies through multilayer network models","authors":"Cong Lu ,&nbsp;Jianjun She ,&nbsp;Hezhi Pan ,&nbsp;Zihao Guo ,&nbsp;Xuanling Zhou ,&nbsp;Zhijian Li","doi":"10.1016/j.jnlssr.2025.100245","DOIUrl":"10.1016/j.jnlssr.2025.100245","url":null,"abstract":"<div><div>As urbanization and industrialization progress, urban infrastructure systems grow increasingly complex, heightening their vulnerability to cascading failures from natural disasters and human-induced disruptions. Strengthening the resilience of these systems is critical for sustainable urban development and sustaining residents’ quality of life. This study introduces a novel framework to analyze cascading failure propagation within infrastructure networks. Utilizing the implicit interdependency model, we construct a multilayer network that delineates interconnections and dependencies across infrastructure sectors. The PageRank algorithm is used to identify critical nodes by evaluating their network centrality, thereby highlighting key components within the system. Through simulations of random, PageRank-based, and betweenness-based attack scenarios, we explore failure dynamics and their propagation patterns. Additionally, we evaluate mitigation strategies, with the community periphery augmentation strategy proving most effective, enhancing resilience by linking peripheral nodes between communities. This research systematically connects the significance of key nodes to cascading effects, uncovering vulnerabilities and providing actionable insights for disaster response and recovery planning.</div></div>","PeriodicalId":62710,"journal":{"name":"安全科学与韧性(英文)","volume":"7 1","pages":"Article 100245"},"PeriodicalIF":3.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144890530","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":"Prediction of wheat stem biomass using a new unified model driven by phenological variable under remote-sensed canopy vegetation index constraints","authors":"Weinan Chen ,&nbsp;Guijun Yang ,&nbsp;Yang Meng ,&nbsp;Haikuan Feng ,&nbsp;Hongrui Wen ,&nbsp;Aohua Tang ,&nbsp;Jing Zhang ,&nbsp;Hao Yang ,&nbsp;Heli Li ,&nbsp;Xingang Xu ,&nbsp;Changchun Li ,&nbsp;Zhenhong Li","doi":"10.1016/j.aiia.2025.11.007","DOIUrl":"10.1016/j.aiia.2025.11.007","url":null,"abstract":"<div><div>Timely and accurate prediction of stem dry biomass (SDB) is crucial for monitoring crop growing status. However, conventional biomass estimation models are often limited by the influence of crop growth phase, which significantly restricts their temporal and spatial transferability. This study aimed to develop a semi-mechanistic stem biomass prediction model (PVWheat-SDB) using phenological variable (PV) to accurately predict winter wheat SDB across different growth stages. The core of the model is to predict SDB using PV under remote-sensed canopy vegetation indices (VIs) constraint. The results demonstrated that VIs can quantify the variations in stem growth equations under different planting conditions and varieties. The developed a PVWheat-SDB model using normalized difference red edge (NDRE) and accumulated growing degree days (AGDD) performed well for SDB predictions, with R², RMSE, nRMSE and MAE values of 0.88, 75.48 g/m², 8.04 % and 55.36 g/m² for the validation datasets of field spectral reflectance, and 0.82, 81.76 g/m², 11.22 % and 62.82 g/m² when transferred to unmanned aerial vehicle (UAV) hyperspectral images. Furthermore, the model can not only estimate SDB at the current growth stage, but also predict SDB of subsequent phenological stages. The growth stage stacking strategy indicated that the model accuracy improves significantly as more growth stages are incorporated, especially during the reproductive stages. These results all highlight the robustness and transferability of the PVWheat-SDB model in accurately predicting SDB across different growing seasons and growth stages.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 658-671"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145924151","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":"Hydrochar supported Mg–Fe layered double hydroxide hybrid for efficient and reusable removal of tetracyclines from water","authors":"Jeffrey Saúl Cedeño-Muñoz ,&nbsp;Bryan Jesus Zumarraga-Valencia ,&nbsp;Jaime E. Cevallos-Mendoza ,&nbsp;Bryan Fernando Rivadeneira-Mendoza ,&nbsp;Iris B. Pérez-Almeida ,&nbsp;Krishna Kumar Yadav ,&nbsp;María Dolores Saquete ,&nbsp;Nuria Boluda-Botella ,&nbsp;Joan Manuel Rodríguez-Díaz","doi":"10.1016/j.emcon.2025.100623","DOIUrl":"10.1016/j.emcon.2025.100623","url":null,"abstract":"<div><div>A hybrid photocatalyst, Mg–Fe-LDH@HC (layered double hydroxide supported on corn-stalk hydrochar), was synthesized via coprecipitation and evaluated for the removal and photodegradation of tetracyclines in water. X-ray diffraction (XRD) confirmed the formation of a hydrotalcite-like phase with partial amorphous carbon contribution, while SEM–EDS mapping evidenced a uniform dispersion of Mg–Fe-LDH over the hydrochar surface. The hybrid exhibited an apparent optical bandgap of 1.81 eV, favoring visible-light absorption. Under ultraviolet irradiation and optimized operational conditions (H₂O₂ = 5.4 μM, pH = 6.0, 25 °C), Mg–Fe-LDH@HC achieved 99.09 % total tetracycline degradation after 120 min. Kinetic fitting followed a pseudo-second-order model (R² &gt; 0.94), indicating a chemisorption-dominated mechanism coupled with reactive oxygen species (ROS) generation. Radical scavenging and EDTA inhibition tests demonstrated that photogenerated electrons and •OH radicals were the main oxidative agents, with additional contributions from a heterogeneous Fenton pathway with no evidence of a homogeneous Fenton mechanism. The catalyst retained 91.3 % of its initial efficiency after five reuse cycles, with partial recovery after mild regeneration. Acute toxicity assays using <em>Artemia salina</em>, <em>Daphnia magna</em>, and <em>Raphidocelis subcapitata</em> revealed a 65–80 % reduction in post-treatment toxicity compared to the untreated effluent. These results demonstrate that Mg–Fe-LDH@HC is an efficient, recyclable, and eco-compatible photocatalyst for the degradation of antibiotic contaminants in water systems.</div></div>","PeriodicalId":11539,"journal":{"name":"Emerging Contaminants","volume":"12 1","pages":"Article 100623"},"PeriodicalIF":6.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145920688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Distribution, driving factors and prediction of antibiotics in Asia's largest River Basin: Comprehensive insights of Yangtze River Basin, China","authors":"Jiamei Zhang ,&nbsp;Yuyang Zhu ,&nbsp;Yu Wang ,&nbsp;Xing Chen ,&nbsp;Guolian Li ,&nbsp;Gege Cai ,&nbsp;Fazhi Xie ,&nbsp;Youqiang Sun","doi":"10.1016/j.emcon.2026.100624","DOIUrl":"10.1016/j.emcon.2026.100624","url":null,"abstract":"<div><div>Antibiotics have been a global concern because of their widespread occurrence and adverse effects on aquatic environments, particularly in large-scale river basins. However, their environmental fate in the Yangtze River Basin remains underexplored. In the present study, we investigated 31 antibiotics in surface water throughout the Yangtze River Basin, the largest river system in China and Asia. The total antibiotic concentrations ranged from 142.05 to 345.57 ng/L, with fluoroquinolones (FQs) predominating and accounting for 75.68 % of the total concentration. Higher antibiotic concentrations were observed in the midstream and downstream regions, particularly in the three major economic zones of the Yangtze River Basin, likely driven by rapid economic development and urbanization. Agricultural and livestock farming intensity, along with nitrogen and phosphorus levels, has significant positive effects on antibiotic concentrations. Antibiotic concentrations showed negative correlations with microbial diversity and community composition, suggesting potential links to shifts in microbial community structure. Analysis using the Positive Matrix Factorization (PMF) model identified four major sources of antibiotic pollution: livestock waste (31.30 %), aquaculture runoff (24.89 %), hospital discharges (21.95 %), and sewage treatment effluents (21.86 %). We also employed four machine learning (ML) models to relate antibiotic concentrations to explanatory variables, enabling prediction of their distribution across the Yangtze River Basin. The Random Forest model demonstrated superior performance in predicting the concentrations of FQs and tetracyclines (TCs), with R² values of 0.75 and 0.74, respectively. The results of this study provide new insights into the transport behavior and prediction of antibiotic concentrations in large river basins.</div></div>","PeriodicalId":11539,"journal":{"name":"Emerging Contaminants","volume":"12 1","pages":"Article 100624"},"PeriodicalIF":6.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145920704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Utilizing interpretable machine learning algorithms and multiple features from multi-temporal Sentinel-2 imagery for predicting wheat fusarium head blight","authors":"Hui Wang ,&nbsp;Chao Ruan ,&nbsp;Jinling Zhao ,&nbsp;Yunran Wang ,&nbsp;Ying Li ,&nbsp;Yingying Dong ,&nbsp;Linsheng Huang","doi":"10.1016/j.aiia.2025.10.012","DOIUrl":"10.1016/j.aiia.2025.10.012","url":null,"abstract":"<div><div>Wheat <em>Fusarium</em> head blight (FHB) severely affects wheat yields, and predicting its occurrence and spatial distribution is essential for safeguarding crop production. This study presents an interpretable machine learning method designed to predict FHB by leveraging multi-temporal and multi-feature information obtained from Sentinel-2 imagery. During the regreening and grain-filling stages, we extracted vegetation indices (VIs), texture features (TFs), and color indices (CIs). Single-temporal features were derived from the grain-filling stage, while multi-temporal features combined data from grain-filling and regreening stages. The synthetic minority over-sampling technique (SMOTE) was employed to adjust the class imbalance, while the most significant characteristics were found using the sequential forward selection (SFS) approach. The extreme gradient boosting (XGBoost) model, optimized using simulated annealing (SA) algorithm and explained via SHapley Additive exPlanation (SHAP) method, integrated VIs, TFs, and CIs as input features. The presented model demonstrated exceptional results, achieving a prediction accuracy of 89.9 % across multi-temporal and a Kappa coefficient of 0.797. It outperformed random forests (RF), backpropagation neural networks (BPNN), and support vector machines (SVM) model. This study indicates that an interpretable machine learning approach, which utilizes both multi-temporal and multi-feature data, is effective in forecasting FHB, thereby providing a valuable tool for agricultural management and disease prevention strategies.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 224-239"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145416196","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":"Nonlinear free vibrations of functionally graded graphene origami-enabled auxetic metamaterial skew-microplates with variable thickness using isogeometric analysis","authors":"Vu Ngoc Anh ,&nbsp;Tran Van Ke ,&nbsp;Nguyen Thi Thu Huong ,&nbsp;Nguyen Thi Hue ,&nbsp;Pham Hoang Tu","doi":"10.1016/j.dt.2025.09.024","DOIUrl":"10.1016/j.dt.2025.09.024","url":null,"abstract":"<div><div>The remarkable mechanical and physical characteristics of functionally graded (FG) graphene origami (GOri)-enabled auxetic metamaterial (GOEAM) structures, including their high strength-to-weight ratio, tunable stiffness and strength, and negative Poisson's ratio (NPR), have demonstrated significant promise for a range of engineering applications. This paper aims to investigate the nonlinear free vibrations behaviors of FG-GOEAM non-uniform thickness skew-microplate with rectangular and elliptical planform and resting on Kerr-elastic foundation in thermal environment. Within the framework of the higher-order shear deformation theory (HSDT), von Kármán assumption, modified couple stress theory (MCST) and by employing Hamilton's principle the nonlinear governing equations of motion are established. By combining an iterative technique with a displacement control strategy, an isogeometric analysis (IGA) approach used to determine the nonlinearity in free vibration, as measured by the nonlinear frequency ratio associated with the center deflection amplitude. The effects of GOri distribution patterns, weight fraction, length-scale parameter, temperature difference, skew-angle, and micro-plate dimensions on the nonlinear free vibrations behaviors of the FG-GOEAM non-uniform thickness skew-microplate are revealed through a thorough parametric study. This result can be applied in studies on the design of micro-electro-mechanical devices operating in various complex environments and conditions.</div></div>","PeriodicalId":58209,"journal":{"name":"Defence Technology(防务技术)","volume":"57 ","pages":"Pages 85-108"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453814","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":"Effects of end caps of cylindrical casing on fragment velocity distribution","authors":"Yueguang Gao ,&nbsp;Jianping Fu ,&nbsp;Siyu Wu ,&nbsp;Xuke Lan ,&nbsp;Kai Ren ,&nbsp;Rui Yang","doi":"10.1016/j.dt.2025.09.033","DOIUrl":"10.1016/j.dt.2025.09.033","url":null,"abstract":"<div><div>Fragment velocity distribution is an important parameter affecting the terminal effects of warheads. The rarefaction wave, end cap, and its confinement state can significantly affect the fragmentation of the cylindrical charge casing. Most of the existing studies have performed experiments and simulations considering the rarefaction wave and unfixed end caps; research on fixed end caps and sufficient theoretical explanations are limited. In this work, the effects of rarefaction waves, end caps, and their fixed states, on the fragment velocity distribution, were studied via experimentation and simulation, and reasonable theoretical explanations were provided. The results show that the rarefaction wave and end caps affect the fragment velocity by changing the pressure states of the detonation products. At the initiation end, the fragment velocities of casings with unfixed initiation ends are 33.3% (300 m/s) greater than that of casings without end caps, because of the weakening of the attenuation effect of the rarefaction wave. The fragment velocities of the casings with fixed initiation ends are 8.3% (100 m/s) greater than that of casings with unfixed initiation ends. At the non-initiation end, the fragment velocities are 24.8% (297 m/s) greater than that of a casing without end caps, and the reflecting shock wave generated by the fixed non-initiation end increases the fragment velocity by 7.3% (113 m/s), compared to the theoretical velocity. This work provides a basis for the structural design and analysis of the terminal effects of warheads.</div></div>","PeriodicalId":58209,"journal":{"name":"Defence Technology(防务技术)","volume":"57 ","pages":"Pages 377-394"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453891","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":"Dynamic behavior and damage evaluation of prototype caisson wharf against underwater explosion","authors":"Ziqi Chen ,&nbsp;Yudi Zhou ,&nbsp;Yuehua Cheng ,&nbsp;Hao Wu","doi":"10.1016/j.dt.2025.09.017","DOIUrl":"10.1016/j.dt.2025.09.017","url":null,"abstract":"<div><div>Gravity-caisson wharves have been widely constructed in coastal and island regions, which are threaten by potential underwater explosions. This work aims to study the dynamic behaviors and propose a damage evaluation approach of caisson wharf against underwater explosion. Firstly, based on both the underwater explosion loading test and underwater explosion test on the reduced-scale caisson specimen, a high-fidelity finite element analysis approach for numerically reproduce the dynamic behaviors of prototype caisson wharves against underwater explosions was proposed and verified. Secondly, the underwater explosion loadings and dynamic behaviors of prototype caisson wharf (14.9 m×8.1 m×10.95 m) against sequential blast wave and bubble pulsation of typical torpedo with a charge weight of 200 kg were studied. The influences of the seabed and cabin infill materials, as well as the explosion standoff distances of 3.4–10.2 m and depths of burst between 1/4 and 3/4 of water depth, on the blast resistance of caisson wharf were further examined through deflection distributions of exterior wall, damage evolution, and overall displacement of caisson wharf. Finally, a performance evaluation approach for prototype caisson wharves against underwater explosions was proposed by comprehensively considering the bearing, storage, and berthing capabilities. The corresponding protective measures and design recommendations were further provided. It indicates that: (i) under the explosion of a typical torpedo, the damage modes of prototype caisson wharf mainly involve the overall vibration, spalling and cracking of the exterior wall, collapse of the upper operating platform and cracking of the top plate; (ii) the blast wave and cavitation zone generated between the bubble and the exterior wall are the two primary causes of damage to caisson wharf; (iii) compared to the saturated calcareous sand seabed, the assumption of rigid seabed underestimates the spalling on the exterior wall, which is not recommended for scenarios where cavitation zones may generate; (iv) rock rubble is the most effective infill material in improving the blast resistance of caisson wharf among four types of infill configurations, i.e., fully filled and half-filled saturated calcareous sand, rock rubble and pure water; (v) the standoff distance of 10.2 m is regarded as a secure protective range in the scenarios discussed currently. As the standoff distance decreases and the depth of burst increases, the spalling of the exterior wall induced by the cavitation intensifies, posing a great threat to the functionality of caisson wharf.</div></div>","PeriodicalId":58209,"journal":{"name":"Defence Technology(防务技术)","volume":"57 ","pages":"Pages 246-266"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453906","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":"Machine learning for occupational accident analysis: Applications, challenges, and future directions","authors":"Izuchukwu Chukwuma Obasi,&nbsp;Pericles Cheng,&nbsp;Cleo Varianou-Mikellidou,&nbsp;Christos Dimopoulos,&nbsp;Georgios Boustras","doi":"10.1016/j.jnlssr.2025.100250","DOIUrl":"10.1016/j.jnlssr.2025.100250","url":null,"abstract":"<div><div>Machine learning (ML) drives progress in occupational accident prevention across diverse sectors. However, significant challenges persist in aligning these tools with practical safety needs, including accurate risk assessment, incident prediction, and targeted prevention strategies. While prior reviews focused narrowly on specific industries or data types, this study presents a comprehensive analysis of ML models in accident analysis, categorizing them by accident type, industry application, and modeling methodology. This study addresses critical challenges in ML model development—such as data quality, hyperparameter tuning, and managing class imbalances—and examines less-discussed topics, including explanatory variable selection and strategies for mitigating overfitting. This review thoroughly assesses the current state of ML-based accident prediction, highlighting critical gaps, methodological limitations, and potential research directions. By analyzing 504 studies across three perspectives—Accident Type, Industry Application, and Modeling Methodology—this review identifies pressing challenges, including (1) limitations in data quality and availability, especially for real-time sources; (2) inadequate model interpretability across applications; (3) difficulties in handling imbalanced accident datasets; and (4) the lack of an integrated framework for incorporating proactive data and industry-specific risk factors. The findings outline a roadmap for advancing ML in occupational safety by enhancing model robustness, improving interpretability, and expanding data sources. This review aims to better align ML applications with safety objectives, promoting data-driven approaches for effective accident analysis and prevention across industries.</div></div>","PeriodicalId":62710,"journal":{"name":"安全科学与韧性(英文)","volume":"7 1","pages":"Article 100250"},"PeriodicalIF":3.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048450","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}