Diverse Network Research Articles

Tree species-dependent effects of afforestation on soil fungal diversity, functional guilds and co-occurrence networks in northern China

Afforestation exerts a profound impact on soil fungal communities, with the nature and extent of these changes significantly influenced by the specific tree species selected. While extensive research has addressed the aboveground ecological outcomes of afforestation, the nuanced interactions between tree species and soil fungal dynamics remain underexplored. This study investigated the effects of afforestation with Caragana microphylla (CMI), Populus simonii (PSI), and Pinus sylvestris var. mongolica (PSY) on soil fungal diversity, functional guilds, and co-occurrence networks, drawing comparisons with neighboring grasslands. Our findings reveal a significant increase in soil fungal Chao1 richness following afforestation, though the degree of enhancement varied across tree species. Specifically, CMI and PSI forests showed notable increases in fungal richness, whereas the response in PSY forests was comparatively modest. Saprotrophic fungal groups, integral to organic matter decomposition, showed a substantial increase across all afforested sites, with CMI forests exhibiting an impressive 205.58% rise. Conversely, pathogenic fungi, which can negatively impact plant health, demonstrated a marked decrease within plantation forests. Symbiotic groups, particularly ectomycorrhizal fungi, were notably enriched solely in PSI forests. Co-occurrence network analysis further indicated that afforestation alters fungal network complexity: CMI forests displayed increased network interactions, while PSI and PSY forests exhibited a reduction in network connectivity. Soil bulk density and organic carbon content emerged as key factors influencing network complexity, whereas tree species identity played a crucial role in shaping soil fungal community composition. Collectively, these results emphasize the importance of adopting a species-specific strategy for afforestation to optimize soil fungal diversity and network structure, ultimately enhancing the ecological resilience and sustainability of forest plantation ecosystems.

Remote sensing ecological index (RSEI) affects microbial community diversity in ecosystems of different qualities

Soil microorganisms are key to ecological environment stability, but climate change and human activities exacerbate ecological environment changes. Therefore, assessment of ecological environment quality impacts on microbial diversity is needed. The Tarim River is the largest inland river in China and plays a crucial role in supporting regional biodiversity, maintaining ecological balance, and preventing desertification. In this study, we used the Remote Sensing-based Ecological Index (RSEI) to assess the ecological quality of habitats in the Tarim River Basin and explore the effects of habitat quality (extreme, semi-extreme, and general) on the structural diversity of microbial (bacterial and fungal) communities, biogeographic patterns, co-occurrence networks, and community assembly processes. Study results show that soil physicochemical characteristics varied significantly with habitat quality; highly resilient microorganisms are more abundant in habitats with low ecological quality. RSEI affects changes in microbial communities, and the positive correlation ratio of the network is inversely proportional to RSEI. The interspecific relationships of microbial communities in the Tarim River Basin are dominated by positive correlations, and community assembly is strongly influenced by stochastic processes. RSEI directly affects soil microbial diversity, with its contribution to both bacterial and fungal diversity being 0.27. Total nitrogen (TN) also directly affects microbial diversity, with effects of 0.11 on bacteria and 0.07 on fungi, respectively. This study provides scientific evidence and technical support for understanding microbial diversity in environments and for the development of regional sustainable development policies.

Generative adversarial imitation learning assisted virtual network embedding algorithm for space-air-ground integrated network

The space-air-ground integrated network (SAGIN) comprises a multitude of interconnected and integrated heterogeneous networks. Its network is large in scale, complex in structure, and highly dynamic. Virtual network embedding (VNE) is designed to efficiently allocate resources within the physical host to diverse virtual network requests (VNRs) with different constraints while improving the acceptance ratio of VNRs. However, in a heterogeneous SAGIN environment, improving the utilization of network resources while ensuring the performance of the VNE algorithm is a very challenging topic. To address the aforementioned issues, we first introduce a services diversion strategy (SDS) to select embedded nodes based on different service types and network state, thereby alleviating the uneven use of resources in different network domains. Subsequently, we propose a VNE algorithm (GAIL-VNE) based on generative adversarial imitation learning (GAIL). We construct a generator network based on the actor-critic architecture, which can generate the probability of physical nodes being embedded based on the observed network state. Secondly, we construct a discriminator network to distinguish between generator samples and expert samples, which aids in updating the generator network. After offline training, the generator and discriminator reach a Nash equilibrium through game confrontation. During the embedding process of VNRs, the output of the generator provides an effective basis for generating VNE solutions. Finally, we verify the effectiveness of this method through experiments involving offline training and online embedding.

Effects of experimental nutrient enrichment and eutrophication on microbial community structure and function in “marine lakes”

Biogeochemical cycling of nitrogen (N) and carbon (C) are regulated by microbial communities that can respond to altered N and C availability, yet the form, consistency, and magnitude of these responses remain poorly constrained. We enriched and eutrophied distinct microbial communities in “marine lakes” through experimental additions of N (5 μM NH4Cl), C (100 μM sucrose), and combined N+C (same forms and concentrations), examining microbial community responses via 16S rRNA sequencing in conjunction with functional responses represented by net community production (NCP) and community respiration (CR) measurements. Individual N or C additions drove significant shifts in microbial community structure only sporadically, and rarely with a corresponding difference in NCP or CR rates. In contrast, the combined addition of N+C elicited strong coincident responses in microbial community structure and function: NCP and CR rates shifted sharply toward heterotrophy and were correlated with multiple microbial networks (r2 = 0.309–0.599, P < 0.001) that included globally distributed marine bacteria. Across multiple experiments, the consistent response of one network, comprised primarily of gammaproteobacterial heterotrophs (particularly Vibrio and Alteromonas), led initially dissimilar communities to converge toward similar composition. However, the distinct response patterns of other more diverse networks were superimposed on top of this network, indicating that inorganic N and organic C enrichment have multilayered effects on microbial communities. Collectively our results demonstrate that elevated N and C alter microbial community structure and function, selecting for multiple microbial networks that compete for, and rapidly cycle, N and C.

Gene horizontal transfers and functional diversity negatively correlated with bacterial taxonomic diversity along a nitrogen gradient.

Horizontal gene transfer (HGT) mediated diversification is a critical force driving evolutionary and ecological processes. However, how HGT might relate to anthropogenic activity such as nitrogen addition, and its subsequent effect on functional diversity and cooccurrence networks remain unknown. Here we approach this knowledge gap by blending bacterial 16S rRNA gene amplicon and shotgun metagenomes from a platform of cessation of nitrogen additions and continuous nitrogen additions. We found that bacterial HGT events, functional genes, and virus diversities increased whereas bacterial taxonomic diversity decreased by nitrogen additions, resulting in a counterintuitive strong negative association between bacterial taxonomic and functional diversities. Nitrogen additions, especially the ceased one, complexified the cooccurrence network by increasing the contribution of vitamin B12 auxotrophic Acidobacteria, indicating cross-feeding. These findings advance our perceptions of the causes and consequences of the diversification process in community ecology.

Karst Ecosystem: Moso Bamboo Intercropping Enhances Soil Fertility and Microbial Diversity in the Rhizosphere of Giant Lily (Cardiocrinum giganteum)

Intercropping affects soil microbial community structure significantly; however, the effects on understory medicinal plants in karst areas remain unclear. We investigated the effects of four intercropping systems (Moso bamboo, Chinese fir, bamboo-fir mixed forest, and forest gap) on the rhizosphere microbial communities of giant lily (Cardiocrinum giganteum), an economically important medicinal plant in China. We assessed the intercropping impact on rhizosphere microbial diversity, composition, and co-occurrence networks and identified key soil properties driving the changes. Bacterial and fungal diversity were assessed by 16S rRNA and ITS gene sequencing, respectively; soil physicochemical properties and enzyme activities were measured. Moso bamboo system had the highest fungal diversity, with relatively high bacterial diversity. It promoted a distinct microbial community structure with significant Actinobacteria and saprotrophic fungi enrichment. Soil organic carbon, total nitrogen, and available potassium were the most influential drivers of microbial community structure. Co-occurrence network analysis revealed that the microbial network in the Moso bamboo system was the most complex and highly interconnected, with a higher proportion of positive interactions and a greater number of keystone taxa. Thus, integrating Moso bamboo into intercropping systems can enhance soil fertility, microbial diversity, and ecological interactions in the giant lily rhizosphere in karst forests.

Preparing the Future Public Health Workforce: Fostering Global Citizenship Through the Relational Employability Framework—Insights from Two Case Studies

A well-prepared public health workforce is essential for reducing disease burdens and improving population health, necessitating an education that addresses global and complex challenges. This paper explores the integration of the Relational Employability Framework in public health education as a tool to foster critical reflection and cultivate global citizenship among students and graduates. Global citizenship encompasses the social, political, environmental and economic actions of globally conscious individuals and communities, recognising that individuals operate within diverse local and global networks. Relational employability expands traditional notions of graduate employability, incorporating not only foundational career development and human interactions but also connections with more-than-human elements, including ecologies, technologies and materials. Our research, conducted at Edith Cowan University in Perth, Western Australia, involved two case studies using qualitative interviews. Case Study 1, drawn from the Cook’s doctoral research, explored student experiences with the Relational Employability Framework within an undergraduate capstone unit. Case Study 2, a school-funded project, gathered graduate perspectives to inform ongoing curriculum development. The findings indicate that the Relational Employability Framework can help support the development of global citizenship through critical reflective practice, as students reported improved ability to engage with diverse perspectives and societal challenges, and graduates highlighted the framework’s role in supporting ethical, evidence-based practice in professional contexts. Additionally, the framework supported the development of a reflective mindset, which graduates said helped them make informed, value-based career decisions, thus advancing their professional growth. This study suggests that adopting a relational employability approach can prepare globally competent and reflective public health professionals and recommends its implementation across health and higher education.

Unveiling user identity across social media: a novel unsupervised gradient semantic model for accurate and efficient user alignment

AbstractThe field of social network analysis has identified User Alignment (UA) as a crucial area of investigation. The objective of UA is to identify and connect user accounts across diverse social networks, even when there are no explicit interconnections. UA plays a pivotal role in synthesising coherent user profiles and delving into the intricacies of user behaviour across platforms. However, traditional approaches have encountered limitations. Singular embedding techniques have been found to fall short in fully capturing the semantic essence of user profile attributes. Furthermore, classification-based embedding methods lack definitive criteria for categorisation, thereby constraining both the efficacy and applicability of these models. This paper presents a novel unsupervised Gradient Semantic Model for User Alignment (GSMUA) for the purpose of identifying common user identities across social networks. GSMUA categorises user profile information into weak, sub, and strong gradients based on the semantic intensity of attributes. Different gradient semantic levels direct attention to literal features, semantic features, or a combination of both during feature extraction, thereby achieving a full semantic representation of user attributes. In the case of strongly semantic long texts, GSMUA employs Named Entity Recognition (ENR) technology in order to enhance the inefficient handling of such texts. Furthermore, GSMUA compensates for missing user profile attributes by utilising profile information from user neighbours, thereby reducing the negative impact of missing user profile attributes on model performance. Extensive experiments conducted on four pairs of real datasets demonstrate the superiority of our approach. In comparison to the most effective previously developed unsupervised methods, GSMUA demonstrates improvements in hit-precision ranging from 5.32 to 12.17%. When compared to supervised methods, the improvements range from 0.71 to 11.79%.

Local and translocal social capital in flood adaptation: evidence from Indonesian coastal communities

ABSTRACT Environmental change and sea level rise challenge urban coastal communities, especially in the Global South. Existing hazard research emphasises the vital role of social capital in adaptation but often overlooks translocal social capital, which encompasses social support and resources that extend beyond local boundaries and connect people at different places. To reduce this research gap, this study investigates the impact of local and translocal social capital on flood-prone households in Padang and Denpasar, Indonesia, using survey data (N = 620) and social network data (N = 1169). The results show translocal contacts provide more emotional, moral, financial, and material support, while local contacts share flood-related knowledge, skills, advice, and practical support. Further, our findings show that the effectiveness of social support varies: local support is strengthened by community ties and diverse forms of support, whereas translocal support's significant role in mental health relies on intimacy and reliability in strong personal relationships. Well-connected support contacts help households to access broader social networks. These findings highlight the different roles of local and translocal social capital in long-term adaptation, which partly complement each other. Households benefit from maintaining diverse support networks, with each type of social capital playing distinct yet interdependent roles in enhancing resilience against environmental changes.

The master regulator OxyR orchestrates bacterial oxidative stress response genes in space and time.

Bacteria employ diverse gene regulatory networks to survive stress, but deciphering the underlying logic of these complex networks has proved challenging. Here, we use time-resolved single-cell imaging to explore the functioning of the E.coli regulatory response to oxidative stress. We observe diverse gene expression dynamics within the network. However, by controlling for stress-induced growth-rate changes, we show that these patterns involve just three classes of regulation: downregulated genes, upregulated pulsatile genes, and gradually upregulated genes. The two upregulated classes are distinguished by differences in the binding of the transcription factor, OxyR, and appear to play distinct roles during stress protection. Pulsatile genes activate transiently in a few cells for initial protection of a group of cells, whereas gradually upregulated genes induce evenly, generating a lasting protection involving many cells. Our study shows how bacterial populations use simple regulatory principles to coordinate stress responses in space and time. A record of this paper's transparent peer review process is included in the supplemental information.

Cost-of-living: the impact on emotional support for young Londoners

Purpose The purpose of this study is to explore the ways in which the cost-of-living crisis affected emotional support access and availability among multiply-marginalised UK-based youth. Design/methodology/approach This study reports findings from early stages of a multiphase youth participatory action research (YPAR) project. In all, 12 young residents of Tower Hamlets London (ages 16–22 years) employed as peer researchers conducted 14 focus groups with 44 residents of Tower Hamlets over a six-month period. Data were analysed using principles of reflective thematic analysis. Findings Analyses produced salient themes that identified barriers to obtaining emotional support from parents and carers, described the utility of diverse support networks and elucidated the impact of the cost-of-living crisis on emotional support and youth well-being. Research limitations/implications This study has several limitations pertaining primarily to study design, sample size and sample composition that limit generalizability of findings. The findings indicate that the cost-of-living crisis markedly constrained the participants’ access to and availability of formal and informal support from others. Practical implications The findings from this research will influence the design and delivery of policy and services to better meet the needs and experiences of UK-based young people and their families. Social implications This project has the potential to increase understanding of how families can provide effective emotional support to young people and so improve the lives of Londoners now and in the future. Originality/value To the best of the authors’ study, this study is the first to use a YPAR approach to exploring the impact of the cost-of-living crisis on UK-based youth.

Two-dimensional network scene design for traffic simulation: An approach using computational Delaunay triangulation

Traffic network design is a pivotal aspect of urban planning, necessitating a harmonious blend of theoretical and practical approaches. In this paper, we propose a novel network design methodology utilizing Delaunay triangulation. We address the limitations of raw Delaunay networks, particularly their triangular configurations, by introducing edge-reduction techniques guided by a newly developed metric, detour redundancy. This metric is instrumental in assessing edge importance, facilitating the transformation of the network to better mirror real-world traffic scenarios. The efficacy and practical application of the designed networks are then evaluated through traffic simulations using the principles of cellular automata. Our findings underscore the potential of this approach in enriching traffic network design and pave the way for future investigations into diverse network characteristics and their implications in urban environments.

Multi-source partial discharge pattern recognition in GIS based on Grabcut-MCNN

Partial discharge (PD) surveillance constitutes a pivotal methodology for diagnosing insulation failures in electrical equipment. Enhancing comprehensively the precision of identifying PD anomalies in Gas Insulated Switchgear (GIS) is of paramount significance for ensuring the steady functioning of power grids. This study introduces a novel framework that integrates Phase-Resolved PD Graph Segmentation (PRPD-Grabcut) with a tailored MobileNets-based Convolutional Neural Network (MCNN) to classify GIS-related PD issues. Leveraging image segmentation via PRPD-Grabcut, crucial features are extracted from PRPD diagrams, which then facilitate the construction of the MCNN model. This model employs depth-wise separable convolutions alongside inverted residual architectures to tackle the vanishing gradient dilemma inherent in Deep Convolutional Neural Networks (DCNNs) during GIS PD pattern discernment. Upon the model's subsequent training and validation, empirical evidence illustrates that the PRPD-Grabcut-MCNN hybrid significantly alleviates the computational load and storage requisites of the model, concurrently enhancing the recognition precision and expediting the training process of the neural network. Relative to diverse established lightweight neural network architectures, MCNN manifests superior performance in terms of recognition accuracy, reduced cross-entropy loss, and expedited training duration.

Association between social networks and cognition among middle-aged and older adults in rural India.

Prior studies using global cognitive measures have shown that social connectedness is linked with cognitive performance. We investigate the role of different social network dimensions on performance across distinct cognitive domains among dementia-free middle-aged and older rural Indians. We utilized baseline assessment data of 2,525 participants (≥45 years) of an ongoing, prospective, aging cohort in rural India (Srinivaspura Aging, Neuro Senescence, and COGnition) for this study. We evaluated social networks using Cohen's Social Network Index on three dimensions: network diversity, network size, and network embeddedness. We measured cognitive performance on memory (narrative recall), visuospatial ability (geometric figure spatial recognition, visuospatial span), language (verbal fluency, semantic association, word comprehension, reading comprehension), and attention domains of a culturally adapted, computerized, neurocognitive test battery. Linear regression models, adjusted for age and sex, were used for statistical analysis. In the linear regression model adjusted for age and sex, we found that greater network diversity was significantly associated with better performance in narrative recall, geometric figure spatial recognition, reading comprehension, semantic association, and attention tests. Participants with a larger network size had significantly better performance in verbal fluency and semantic association tests. Further, participants with greater network embeddedness had better visuospatial span and verbal fluency. Individuals having a greater network diversity, larger network size, and greater network embeddedness had better cognitive performance in multiple distinct cognitive domains. Following up these participants with serial cognitive monitoring can help understand if social networks play a role in delaying cognitive decline and protecting against dementia. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Sequential decline in cyanobacterial, total prokaryotic, and eukaryotic responses to backward flow in a river connected to Lake Taihu

River ecosystems face escalating challenges due to altered flow regimes from human activities, such as urbanization with hydrological modifications. Understanding the role of microbial communities for ecosystems with changing flow regimes is still incomplete and remains at the frontier of aquatic microbial ecology. In particular, influences of riverine backward flow on the aquatic biota remain largely unknown. Therefore, we examined the impact of backward flow on the cyanobacterial, total prokaryotic, and eukaryotic communities in the Changdougang River, which naturally flows into Lake Taihu, through environmental DNA metabarcoding. We analyzed the differences in community diversity, assembly, and ecological network stability among groups under backward, weak, and forward flow direction conditions. Non-metric multidimensional scaling showed higher variations in communities of groups across flow direction conditions than seasonal groups. Variations in alpha and beta diversity showed that cyanobacterial and total prokaryotic communities experienced strong homogenization under backward flow conditions, whereas the ecological uniqueness of the eukaryotic community decreased. Assembly of the three flow-related communities was primarily governed by drift and dispersal limitation in stochastic processes. However, in the cyanobacterial community, homogeneous selection in deterministic processes increased from 22.79% to 42.86% under backward flow, aligning with trends observed in the checkerboard score (C-score). More importantly, the topological properties of ecological networks and the degree of average variation revealed higher stability in the cyanobacterial community compared to total prokaryotic and eukaryotic communities. Considering the variations in cohesion, the network stability in the cyanobacterial community decreased under backward flow. Our findings emphasize the distinct and sequentially diminishing responses of cyanobacterial, total prokaryotic, and eukaryotic communities to backward flowing rivers. This knowledge is crucial for maintaining ecological health of rivers, assessing the complex ecological impacts on hydrological engineering, and formulating sustainable water management strategies.

Weighted Asymmetry Index: A New Graph-Theoretic Measure for Network Analysis and Optimization

Graph theory is a crucial branch of mathematics in fields like network analysis, molecular chemistry, and computer science, where it models complex relationships and structures. Many indices are used to capture the specific nuances in these structures. In this paper, we propose a new index, the weighted asymmetry index, a graph-theoretic metric quantifying the asymmetry in a network using the distances of the vertices connected by an edge. This index measures how uneven the distances from each vertex to the rest of the graph are when considering the contribution of each edge. We show how the index can capture the intrinsic asymmetries in diverse networks and is an important tool for applications in network analysis, optimization problems, social networks, chemical graph theory, and modeling complex systems. We first identify its extreme values and describe the corresponding extremal trees. We also give explicit formulas for the weighted asymmetry index for path, star, complete bipartite, complete tripartite, generalized star, and wheel graphs. At the end, we propose some open problems.

Deep learning approaches for protecting IoT devices in smart homes from MitM attacks

The primary objective of this paper is to enhance the security of IoT devices in Software-Defined Networking (SDN) environments against Man-in-the-Middle (MitM) attacks in smart homes using Artificial Intelligence (AI) methods as part of an Intrusion Detection and Prevention System (IDPS) framework. This framework aims to authenticate communication parties, ensure overall system and network security within SDN environments, and foster trust among users and stakeholders. The experimental analysis focuses on machine learning (ML) and deep learning (DL) algorithms, particularly those employed in Intrusion Detection Systems (IDS), such as Naive Bayes (NB), k-Nearest Neighbors (kNN), Random Forest (RF), and Convolutional Neural Networks (CNN). The CNN algorithm demonstrates exceptional performance on the training dataset, achieving 99.96% accuracy with minimal training time. It also shows favorable results in terms of detection speed, requiring only 1 s, and maintains a low False Alarm Rate (FAR) of 0.02%. Subsequently, the proposed framework was deployed in a testbed SDN environment to evaluate its detection capabilities across diverse network topologies, showcasing its efficiency compared to existing approaches.

Reducing Successive Interference Cancellation Iterations in Hybrid Beamforming Multiuser Massive Multiple Input Multiple Output Systems Through Grouping Users with Symmetry Channels

This paper presents a comprehensive exploration of advanced beamforming techniques tailored for millimeter-wave (mm-Wave) communication systems. In response to the burgeoning demand for higher data rates, coupled with the constraints of power consumption and hardware complexity, this study focuses on developing a hybrid beamforming framework optimized for downlink scenarios, specifically targeting groups of users based on the approximate symmetry of their channels. The primary innovation of this research lies in leveraging the symmetry of channels among near users to develop a group-based successive interference cancellation (SIC) algorithm. Unlike traditional approaches that address interference on a per-user basis, this algorithm utilizes channel symmetry within clusters of users to reduce computational complexity and improve the efficiency of SIC. By grouping users with symmetrical channel characteristics, the algorithm simplifies the interference management process while maintaining system performance. The proposed system demonstrates notable advantages over existing non-linear algorithms through extensive simulations and performance evaluations, particularly in terms of spectral efficiency and computational complexity. In this study, we further emphasize the importance of balancing spectral efficiency improvements with reduced computational demands, offering a nuanced trade-off that accommodates various operational requirements. The flexible optimization framework provided showcases the system’s adaptability to diverse deployment scenarios and network configurations.

Supraglacial and subglacial ecosystems contribute differently towards proglacial ecosystem communities in Kuoqionggangri Glacier, Tibetan Plateau

Glaciers are experiencing unprecedented global warming, resulting in significant changes to microbial communities and nutrient transport within glacial ecosystems. However, the influence of supraglacial and subglacial ecosystems on the proglacial ecosystem remains poorly understood. Here, we investigated microbial communities across seven habitats in three glacial ecosystems on the Tibetan Plateau using 16S rRNA sequencing. Our results revealed that the proglacial ecosystem exhibited higher alpha diversity but lower network stability than other ecosystems. Moreover, supraglacial and subglacial ecosystems contributed differently to the community diversity and stability of the proglacial ecosystem. Supraglacial ecosystems provided more high-abundance species and had a greater impact on the proglacial ecosystem’s stability, while subglacial ecosystems released a broader range of diverse taxa. These findings highlight the distinct influences of supraglacial and subglacial ecosystems on microbial community dynamics in proglacial environments, offering insights into their interactions and potential impacts on downstream environments as glaciers retreat.

Improved Early Detection of Tube Leaks Faults in Pulverised Coal-fired Boiler Using Deep Feed Forward Neural Network

Boiler tube leaks significantly reduce the operational availability of power units, yet their early detection and prediction have not been fully realised in the industry. This paper introduces a novel approach employing deep feedforward neural networks for early detection of boiler tube leaks in pulverised coal-fired boilers. Early detection enhances repair planning, minimising downtime and production losses. It also improves monitoring and control of boiler tube failures, thereby optimising power plant operations and revenue. Diverse deep neural network models were developed and rigorously tested by leveraging 9 years of operational data (2012–2020). Exhaustive hyper-parameter optimisation, involving seven parameters, substantially improved predictive accuracy. By achieving training and testing accuracies of 82.8% to 99.3%, the study assessed their ability to detect boiler tube leaks over the same 9-year span, providing insights into leak detection capabilities. The models notably predicted all 12 identified tube leak events, averaging a 14-day lead time before boiler shutdown. In addition to leak prediction, a leak detection matrix was devised to analyse residual behaviour and reduce the likelihood of false alarms. However, the models’ predictive performance was observed to be limited to the following year, with satisfactory results for 2021 only. Incorporating the 2021 data into retraining significantly improved the predictions for 2022. The study concludes that while the models demonstrate robust short-term prediction capabilities, they require continuous retraining to maintain accuracy and relevance. This ongoing refinement is essential for keeping the models up-to-date and reliable in predicting future boiler tube leaks.