Search Results (628)

Worker safety has been relatively overlooked in the rapidly growing aquaculture industry. To address this gap, industrial accident compensation insurance data—mainly from floating cage and seaweed farming—were analyzed to quantify accident types and frequencies, with a focus on human elements as root causes. Basic causes were selected based on IMO Resolution A/Res.884 and assessed through a worker awareness survey. Fault Tree Analysis (FTA), a Formal Safety Assessment technique, was applied to evaluate risks associated with these causes. The analysis identified organization at the farm site (23.3%), facility and equipment factors (22.8%), and people factors (21.4%) as the primary causes. Among secondary causes, personal negligence (13.2%), aging gear and poor maintenance (11.4%), and insufficient risk training (10.4%) were the most significant. Selective removal of these causes reduced the probability of human element-related accidents from 64.6% to 48.6%. While limited in scope to Korean data and self-reported surveys, the study demonstrates the value of combining quantitative data with worker perspectives. It provides foundational data for developing tailored safety strategies and institutional improvements—such as standardized procedures, multilingual education, and inclusive risk management—for sustainable safety in aquaculture. Full article

Accurate flood forecasts are imperative to supervise and prepare for extreme events to assess the risks and develop proactive prevention strategies. The flood time-series data exhibit both spatial and temporal structures and make it challenging for the models to fully capture the embedded features due to their complex stochastic nature. This paper proposed a new approach for the first time using variational mode decomposition (VMD) hybridized with Gaussian process regression (GPR) to design the VMD-GPR model for daily flood forecasting. First, the VMD model decomposed the (t − 1) lag into several signals called intrinsic mode functions (IMFs). The VMD has the ability to improve noise robustness, better mode separation, reduced mode aliasing, and end effects. Then, the partial auto-correlation function (PACF) was applied to determine the significant lag (t − 1). Finally, the PACF-based decomposed IMFs were sent into the GPR to forecast the daily flood index at (t − 1) for Jeddah and Jazan stations in Saudi Arabia. The long short-term memory (LSTM) boosted regression tree (BRT) and cascaded forward neural network (CFNN) models were combined with VMD to compare along with the standalone versions. The proposed VMD-GPR outperformed the comparing model to forecast daily floods for both stations using a set of performance metrics. The VMD-GPR outperformed comparing models by achieving R = 0.9825, RMSE = 0.0745, MAE = 0.0088, E_NS = 0.9651, KGE = 0.9802, IA = 0.9911, U_95% = 0.2065 for Jeddah station, and R = 0.9891, RMSE = 0.0945, MAE = 0.0189, E_NS = 0.9781, KGE = 0.9849, IA = 0.9945, U_95% = 0.2621 for Jazan station. The proposed VMD-GPR method efficiently analyzes flood events to forecast in these two stations to facilitate flood forecasting for disaster mitigation and enable the efficient use of water resources. The VMD-GPR model can help policymakers in strategic planning flood management to undertake mandatory risk mitigation measures. Full article

Accurate prediction of individual tree mortality in Pinus yunnanensis Franch. is essential for sustainable forest management and ecological monitoring in southwest China. The aim of this study is to develop a tree mortality prediction model for Pinus yunnanensis based on resurvey data from the Cangshan area in Dali, Yunnan Province, using a stacked ensemble learning algorithm. After an initial evaluation of model performance, the classification thresholds were optimized using the Minimum Classification Error method, the Maximum Sensitivity and Specificity method, the Kappa coefficient method, and the Precision-Recall (PR) curve method to enhance classification results. The findings show that, compared to traditional statistical methods and individual machine learning models, the stacked ensemble learning model (Stacked-RSX) outperforms others in tree mortality classification tasks, which achieved an accuracy of 0.8947, recall of 0.9431, true negative rate of 0.9490, misclassification rate of 0.2289, and an area under the curve of 0.953. Through an exhaustive search for the best classification thresholds, the PR curve method demonstrated good adaptability across all models. All optimal thresholds, relative to the default threshold, significantly improved overall classification performance. Furthermore, feature importance analysis revealed that tree height, diameter at breast height (DBH), Hegyi competition index, and the ratio of DBH to stand basal area are key variables influencing mortality risk. These results indicate that the stacking ensemble learning algorithm effectively analyzes the complex relationships among different factors, significantly improving the prediction accuracy of tree mortality, and providing scientific insights for the management and health monitoring of Pinus yunnanensis forests. Full article

Vehicle owners often use certified service centers throughout the warranty period, which usually extends for five years after buying. Nonetheless, after this timeframe concludes, a large number of owners turn to unapproved service providers, mainly motivated by financial factors. This change signifies a significant drop in income for automakers and their certified service networks. To tackle this issue, manufacturers utilize customer relationship management (CRM) strategies to enhance customer loyalty, usually depending on segmentation methods to pinpoint potential clients. However, conventional approaches frequently do not successfully forecast which clients are most likely to need or utilize maintenance services. This research introduces a machine learning-driven framework aimed at forecasting the probability of monthly maintenance attendance for customers by utilizing an extensive historical dataset that includes information about both customers and vehicles. Additionally, this predictive approach supports workforce planning and scheduling within after-sales service centers, aligning with AI-driven labor optimization frameworks such as those explored in the AI4LABOUR project. Four algorithms in machine learning—Decision Tree, Random Forest, LightGBM (LGBM), and Extreme Gradient Boosting (XGBoost)—were assessed for their forecasting capabilities. Of these, XGBoost showed greater accuracy and reliability in recognizing high-probability customers. In this study, we propose a machine learning framework to predict vehicle maintenance visits for after-sales services, leading to significant operational improvements. Furthermore, the integration of AI-driven workforce allocation strategies, as studied within the AI4LABOUR (reshaping labor force participation with artificial intelligence) project, has contributed to more efficient service personnel deployment, reducing idle time and improving customer experience. By implementing this approach, we achieved a 20% reduction in information delivery times during service operations. Additionally, survey completion times were reduced from 5 min to 4 min per survey, resulting in total time savings of approximately 5906 h by May 2024. The enhanced service appointment scheduling, combined with timely vehicle maintenance, also contributed to reducing potential accident risks. Moreover, the transition from a rule-based maintenance prediction system to a machine learning approach improved efficiency and accuracy. As a result of this transition, individual customer service visit rates increased by 30%, while corporate customer visits rose by 37%. This study contributes to ongoing research on AI-driven workforce planning and service optimization, particularly within the scope of the AI4LABOUR project. Full article

Huanglongbing (HLB), a globally devastating citrus disease, demands sophisticated mathematical modeling to decipher its complex transmission dynamics and inform optimized disease management protocols. This investigation develops an innovative compartmental framework that simultaneously incorporates two critical factors in HLB epidemiology: saturated removal rates of infected citrus trees and behavioral bias in vector movement patterns. Our study delves into the dynamics of non-spatial systems by analyzing the basic reproduction numbers, equilibria, bifurcation phenomena, and the stability of these equilibria. Additionally, we explore the impact of spatial factors on system stability. Results indicate that when the basic reproduction number $R_0<1$, the system may exhibit bistable behavior, while $R_0>1$ leads to a unique stable equilibrium. Notably, vector bias significantly enhances the likelihood of forward bifurcation, and the delay in the removal of diseased trees increases the risk of backward bifurcation. However, reaction–diffusion processes do not alter the stability of the system’s equilibria, and the spatial system lacks complex dynamic properties. This research offers valuable insights into the mechanisms driving HLB transmission and provides a foundation for developing effective control strategies. Full article

The expansion of Zigbee-enabled IoT networks has generated significant security issues, especially around threat detection and secure key management. Using RBF and blockchain technology, this study shows a smart hybrid framework to find threats early and distribute keys safely on IoT networks enabled by Zigbee. This methodology incorporates Radial Basis Function (RBF) networks for prompt threat detection and a blockchain-based trust framework for decentralized and tamper-proof key distribution. It guarantees safe network access, comprehensive authentication, and effective key updates, reducing risks associated with IoT-related DoS attacks and Man in the Middle Attacks. The Trust-Based Security Provider (TBSP) enhances security by administering critical credentials across diverse networks. Comprehensive simulations and performance assessments illustrate the effectiveness of the framework in increasing threat detection precision, minimizing key distribution delay, and bolstering overall network security. The findings confirm its efficacy in safeguarding IoT settings from new risks while ensuring scalability and resource efficiency. We proposed an RBF-based threat detection framework for network keys using the ZBDS2023 dataset and the J48 decision tree algorithm. In conclusion, we demonstrate the security and efficiency of our proposed work. Full article

We surveyed five urban parks in Wrocław, Lower Silesia (Poland) to document the diversity of wood-inhabiting fungi and assess their potential impact on trees and public safety. Field observations were conducted in 2021, yielding 53 fungal occurrences representing nine species of eight genera. The most frequently recorded taxa were Fomes fomentarius (accounting for 43.4% of all fungal observations), Fomitiporia robusta (15.0%), and Laetiporus sulphureus (13.2%). The highest number of fungal findings (35.8%) occurred in Zachodni Park, which is also the largest of the surveyed parks, while Grabiszyński Park—the second largest—had the lowest share (9.4%). Fungi were found on trees of six genera and eight species, most commonly on Quercus robur (35.5% of colonized trees) and Betula pendula (26.7%). In eight cases, host trees could not be identified due to severe damage or removal. Most fungal fruiting bodies appeared on upper trunks or branches of aging, weakened, or decaying trees. As the surveyed parks are highly frequented recreational areas, regular monitoring of wood-inhabiting fungi is recommended to manage tree health and minimize safety risks for park visitors. Full article

The maritime transport of liquefied gases poses significant safety and environmental hazards such as fire, explosion, toxic gas emissions, and air pollution. The main objective of this study was to systematically identify, analyze, and prioritise the potential risks associated with the operation of liquefied gas tankers using a hybrid methodological framework. This framework integrates Fuzzy Delphi, Fuzzy DEMATEL, and Fault Tree Analysis (FTA) techniques to provide a comprehensive risk assessment. Initially, 20 key risk factors were identified through expert consensus using the Fuzzy Delphi method. The causal relationships between these factors were then assessed using Fuzzy DEMATEL to understand their interdependencies. Based on these results, accident probabilities were further analyzed using FTA modelling. The results show that fires, explosions, and large gas leaks are the most serious threats. Equipment failures—often caused by corrosion and operational errors by crew members—are also significant contributors. In contrast, cyber-related risks were found to be of lower criticality. The study highlights the need for improved crew training, rigorous inspection mechanisms, and the implementation of robust preventive risk controls. It also suggests that the prioritisation of these risks may need to be reevaluated as autonomous ship technologies become more widespread. By mapping the interrelated structure of operational hazards, this research contributes to a more integrated and strategic approach to risk management in the LNG/LPG shipping industry. Full article

With the intensification of global climate change and human activities, coniferous species as the main components of natural forests in the Altay Mountains are facing the challenges of aging and regeneration. This study systematically analyzed structural heterogeneity and regeneration of three coniferous stand groups, Larix sibirica Ledeb. stand group, Abies sibirica Ledeb.-Picea obovata Ledeb.-Larix sibirica mixed stand group, and Picea obovata stand group, respectively, across western, central, and eastern forest areas of the Altay Mountains in Northwest China based on field surveys in 2023. Methodologically, we integrated Kruskal–Wallis/Dunn’s post hoc tests, nonlinear power-law modeling (diameter at breast height (DBH)–age relationships, validated via R², root mean square error (RMSE), and F-tests), static life tables (age class mortality and survival curves), and dynamic indices. Key findings revealed structural divergence: the L. sibirica stand group exhibited dominance of large-diameter trees (>30 cm DBH) with sparse seedlings/saplings and limited regeneration; the mixed stand group was dominated by small DBH individuals (<10 cm), showing young age structures and vigorous regeneration; while the P. obovata stand group displayed uniform DBH/height distributions and slow regeneration capacity. Radial growth rates differed significantly—highest in the mixed stand group (average of 0.315 cm/a), intermediate in the P. obovata stand group (0.216 cm/a), and lowest in the L. sibirica stand group (0.180 cm/a). Age–density trends varied among stand groups: unimodal in the L. sibirica and P. obovata stand groups while declining in the mixed stand group. All stand groups followed a Deevey-II survival curve (constant mortality across ages). The mixed stand group showed the highest growth potential but maximum disturbance risk, the L. sibirica stand group exhibited complex variation with lowest risk probability, while the P. obovata stand group had weaker adaptive capacity. These results underscore the need for differentiated management: promoting L. sibirica regeneration via gap-based interventions, enhancing disturbance resistance in the mixed stand group through structural diversification, and prioritizing P. obovata conservation to maintain ecosystem stability. This multi-method framework bridges stand-scale heterogeneity with demographic mechanisms, offering actionable insights for climate-resilient forestry. Full article

The prediction of agricultural commodity futures returns is crucial for understanding global economic trends, alleviating inflationary pressures, and optimizing investment portfolios. However, current research that uses full-sample decomposition to predict agricultural futures returns suffers from data leakage, and the resulting forecast bias leads to overly optimistic outcomes. Additionally, previous studies have lacked a comprehensive consideration of key economic variables that influence agricultural prices. To address these issues, this study proposes the “Rolling VMD-LASSO-Mixed Ensemble” forecasting framework and compares its performance with “Rolling VMD” against univariate models, “Rolling VMD-LASSO” against “Rolling VMD”, and “Rolling VMD-LASSO-Mixed Ensemble” against “Rolling VMD-LASSO”. Empirical results show that, on average, “Rolling VMD” improved MSE, MAE, Theil U, ARV, and DA by 3.05%, 1.09%, 1.52%, 2.96%, and 11.11%, respectively, compared to univariate models. “Rolling VMD-LASSO” improved these five indicators by 2.11%, 1.15%, 1.09%, 2.13%, and 1.00% over “Rolling VMD”. The decision tree-based “Rolling VMD-LASSO-Mixed Ensemble” outperformed “Rolling VMD-LASSO” by 1.98%, 0.96%, 1.28%, 2.55%, and 4.18% in the five metrics. Furthermore, the daily average return, maximum drawdown, Sharpe ratio, Sortino ratio, and Calmar ratio based on prediction results also show that “Rolling VMD” outperforms univariate forecasting, “Rolling VMD-LASSO” outperforms “Rolling VMD”, and “Rolling VMD-LASSO-Mixed Ensemble” outperforms “Rolling VMD-LASSO”. This study provides a more accurate and robust forecasting framework for the global agricultural futures market, offering significant practical value for investor risk management and policymakers in stabilizing prices. Full article

This manuscript proposes a methodology to leverage digitalisation to efficiently generate an overview of required condition-based railway track interventions, possession windows, and expected costs for railway networks at the beginning of the intervention planning process. The consistent and efficient generation of such an overview not only helps track managers in their decision-making but also facilitates the discussion among other decision-makers in later phases of the track intervention planning process, including line planners, capacity managers, and project managers. The methodology uses data of different levels of detail, discrete state modelling for uncertain deterioration of components, and component-level intervention strategies. It dynamically updates the condition estimates of components by capturing the interaction between deteriorating components using Bayesian filters. It also estimates the risks associated with different types of potential service losses that may occur due to sudden events using fault trees as a function of time and the condition of components. An implementation of the methodology is conducted for a 25 km regional railway network in Switzerland. The results suggest that the methodology has the potential to help track managers early in the intervention planning process. In addition, it is argued that the methodology will lead to improvements in the efficiency of the planning process, improvements in the scheduling of preventive interventions, and the reduction in corrective intervention costs upon the implementation in a digital environment. Full article

The cattle sector plays a critical role in Peru’s agricultural economy, yet it faces challenges related to low productivity and environmental degradation. Sustainable alternatives like silvo-pastoral systems (SPSs) offer promising solutions to enhance both economic returns and ecological outcomes in cattle farming. This study examines the economic viability of an intensive SPS (SPSi) compared to traditional monoculture grass systems in San Martín, Peru. The SPSi under study is in the evaluation phase, integrates grasses, legumes, shrubs, and trees, and has the potential to enhance cattle farming profitability while simultaneously offering environmental benefits such as improved soil health and reduced greenhouse gas emissions. Through a discounted cash flow model over an eight-year period, key profitability indicators—Net Present Value (NPV), Internal Rate of Return (IRR), Benefit–Cost Ratio (BC), and payback period—were estimated for four dual-purpose cattle production scenarios: a traditional system and three SPSi scenarios (pessimistic, moderate, and optimistic). Monte Carlo simulations were conducted to assess risk, ensuring robust results. The results show that the NPV for the traditional system was a modest USD 61, while SPSi scenarios ranged from USD 9564 to USD 20,465. The IRR improved from 8.17% in the traditional system to between 26.63% and 30.33% in SPSi scenarios, with a shorter payback period of 4.5 to 5.8 years, compared to 7.98 years in the traditional system. Additionally, the SPSi demonstrated a 30% increase in milk production and a 50% to 250% rise in stocking rates per hectare. The study recommends, subject to pending validations through field trials, promoting SPSi adoption through improved access to credit, technical assistance, and policy frameworks that compensate farmers for ecosystem services. Policymakers should also implement monitoring mechanisms to mitigate unintended consequences, such as deforestation, ensuring that SPSi expansion aligns with sustainable land management practices. Overall, the SPSi presents a viable solution for achieving economic resilience and environmental sustainability in Peru’s cattle sector. Full article

Debt levels are a crucial factor when assessing the financial stability of agricultural firms, and excessive indebtedness is usually the most important indicator of financial distress. As agriculture is a capital-intensive sector with a high reliance on borrowed funds, firms in this sector are more vulnerable to insolvency. This study examines the performance of artificial neural networks (ANNs) and decision trees (DTs) in predicting the bankruptcy of Slovak agricultural enterprises. In an attempt to compare the models’ performances, the most consequential indebtedness ratios are investigated through machine learning approaches. ANN and DT models are found to perform significantly better than traditional forecast methods. ANN achieved an AUC of 0.9500, accuracy of 96.37%, precision of 96.60%, recall of 99.68%, and an F1-score of 98.12%, determining its robust predictive ability. DT performed a little better on AUC (0.9550) and achieved an accuracy of 97.78%, precision of 98.69%, recall of 99.01%, and an F1-score of 98.85%, determining its predictive ability and interpretability. These findings confirm the potential for applying AI-based models to enhance financial risk assessment. This study provides informative results for financial analysts, policymakers, and corporate managers in support of early intervention strategies. Additional research would be required to explore state-of-the-art AI techniques to further refine bankruptcy forecasting and financial decision-making in vulnerable sectors like agriculture. Full article

Acute oak decline (AOD) is a multifactorial disease that affects European oaks and represents a growing threat to forests. The disease results from a complex interaction between biotic and abiotic factors: the various environmental stresses, which vary depending on the area in question, and generally increased by climate change, predispose trees to attack by opportunistic pathogens. Among them, we focused on a bacterial consortium associated with AOD, consisting mainly of Brenneria goodwinii, Gibbsiella quercinecans, Rahnella victoriana, and Lonsdalea britannica, which produce degrading enzymes that contribute to phloem necrosis and the development of stem bleeds and bark cracks. However, the role of other pathogens, such as fungi, cannot be ruled out, but instead could be contributory. The potential involvement of xylophagous insects is also being studied, particularly Agrilus biguttatus, which, although, frequently associated with the disease, has not been conclusively demonstrated to act as an active vector of the bacteria. Currently, disease management requires integrated approaches, including monitoring and other forestry strategies to increase forest resilience. Given the phenomenon’s complexity and the risk of the future expansion of that bacterial consortium, further research is necessary to understand the dynamics and to develop effective containment strategies of AOD-associated bacteria. Full article

Wildfires impact forest ecosystems, affecting tree survival and physiological responses. This study explored the effects of surface fires on Pinus densiflora and Quercus variabilis, assessing mortality, internal injuries, and canopy health. By 2024, P. densiflora had an 18.0% mortality rate, whereas Q. variabilis exhibited no crown dieback. Morphological traits, including tree height, the bark scorch index (BSI), and bark thickness, influenced fire resistance. Despite superior stand characteristics, P. densiflora showed higher mortality due to thin bark, whereas Q. variabilis maintained xylem integrity. While sonic tomography (SoT) showed no significant differences, electrical resistance tomography (ERT) detected physiological stress, with higher ERT_R and ERT_Y area ratios correlating with mortality risk. Notably, F-W-W classified trees showed elevated resistance a year before mortality, suggesting ERT as a predictive tool. ERT_R values exceeding 15.0% were associated with a 37.5% mortality rate, whereas ERT_B values below 55.0% corresponded to 42.9% mortality. Despite fire exposure, canopy responses, including chlorophyll fluorescence and photosynthetic efficiency, remained stable, indicating that the surviving trees maintained functional integrity. This study underscores ERT’s efficacy in diagnosing fire-induced stress and predicting mortality risk. The findings highlight species-specific diagnostic criteria and inform post-fire management, supporting forest resilience through the early detection of high-risk trees and improved restoration strategies. Full article