Optimal Resource Utilization Research Articles

Exploring library service preferences: A study of information source usage in engineering colleges

This study investigates the perception and preferences of library services and information sources among patrons at engineering colleges, specifically focusing on the Jaypee Institute of Information Technology (JIIT), Noida. Utilizing a quantitative approach, the research employs a survey method, collecting data from a sample of 382 respondents, including undergraduate students, postgraduate students, research scholars, and faculty members. The survey assesses satisfaction levels across various resources, including print books, e-books, print journals, e-journals/databases, and multimedia resources, with a particular emphasis on AI-based library services. Results indicate that faculty members exhibit the highest satisfaction with library services, particularly those enhanced by artificial intelligence, while undergraduate students show the least satisfaction. The findings highlight the importance of understanding user preferences to enhance library offerings, optimize resource utilization, and improve overall user experience. This research contributes valuable insights into the evolving needs of engineering college patrons in a digital age and offers recommendations for library management to better serve its diverse user base, particularly through the integration of AI-driven services.

Framework and Outlooks of Multi-Source–Grid–Load Coordinated Low-Carbon Operational Systems Considering Demand-Side Hierarchical Response

In the context of advancing new power systems, a multi-source–grid–load interactive operation framework considering low-carbon demand hierarchical response is developed to further explore the support value of the multi-source–grid–load interaction mechanism for the low-carbon economic operation of the power system. The framework analyzes the support mechanisms of carbon tracking and load-side demand response for the low-carbon economic dispatch of the system and derives the carbon flow calculation method based on the network node correlation matrix, laying the foundation for developing low-carbon demand response strategies. Meanwhile, considering the marginal contribution of each load-side node to the system carbon emissions, a combined Shapley–Topsis low-carbon demand hierarchical response mechanism is designed to guide load nodes in implementing accurate low-carbon hierarchical responses, thereby ensuring the optimal allocation and efficient utilization of system resources. Finally, based on the proposed framework, promising future research perspectives are proposed to provide critical insights for constructing a low-carbon and reliable new energy system.

Edge Computing and Microservices: Extending Scalability Beyond the Cloud

The convergence of edge computing and microservices architecture represents a transformative shift in how organizations process and manage distributed data systems. This article explores the limitations of traditional cloud-centric approaches and presents edge computing as a solution to address these challenges. Through a detailed analysis of real-world implementations across various sectors, including autonomous vehicles, smart cities, and industrial automation, the article examines how edge computing integrated with microservices architecture improves system performance, reduces latency, and optimizes resource utilization. The article investigates deployment challenges and security considerations and provides insights into effective monitoring strategies. Furthermore, the article explores emerging technologies and future research directions that will shape the evolution of edge computing and microservices integration.

Impact of Robotic Percutaneous Coronary Intervention (R-PCI) With and Without CCTA-Guidance on Clinical Outcomes and Hospital Economics: A Single Center Registry.

Several studies have confirmed the safety and efficacy of robotic assisted coronary interventions for simple and complex coronary lesions. However, in the real-world clinical setting the currently available evidence is still inconclusive with regard to clinical outcomes. In terms of financial sustainability, the emerging use of pre-PCI Coronary Computed Tomography Angiography (CCTA) may potentially impact the overall patient journey and related costs. However, the role of CCTA guidance in elective robotic-assisted revascularizations and its potential impact on hospital economics has never been investigated. Therefore, we aimed to assess the clinical impact of R-PCI according to procedural complexity and its potential financial sustainability when integrated with CCTA guidance. Major adverse cardiovascular events (MACE) at the latest clinical follow-up available have been prospectively evaluated in a single center cohort of 111 patients undergoing elective R-PCI (CorPath, Corindus GRX Robotic Drive, Boston, MA). The study population was subsequently divided into two groups according to either the median Syntax Score (SS = 14) as a surrogate of procedural complexity or the adoption of CCTA-guidance. Additionally, both periprocedural and in-hospital outcomes have been investigated in the overall cohort and in the subgroups. Overall, MACE occurred in 5.4% of the patients at a median follow-up of 309 days. Procedural complexity was associated with significantly longer procedural time and radiation exposure (SS ≥ 14: 94.5 ± 32.1 vs. 78.7 ± 25.5 min, p = 0.011, and 32.7 ± 30.9 vs. 22.5 ± 19.8 mSv, p = 0.010, respectively), but not with increased in-hospital and long-term clinical outcomes. Additionally, patients undergoing CCTA-guided R-PCI had a significantly higher rate of same-day-discharge (SDD-64.6% vs. 44.2% respectively, p = 0.034) than those without CCTA support. R-PCI appears safe and effective regardless the procedural complexity. Moreover, the integration of robotics and CCTA-guidance appears to have beneficial impact on hospital economics by optimizing resource utilization and improving patient selection for percutaneous revascularization.

Iron enrichment and alumina recovery from bauxite residue through hydrogen reduction followed by alkaline leaching and CaO circulation

ABSTRACT The alumina industry faces a significant challenge in effectively utilising bauxite residue due to its hazardous nature. A potential solution involves recovering iron and alumina from the bauxite residue, leading to a substantial reduction in residue volume and also drawing some material value. This study involved the production of self-hardened calcite pellets from the bauxite residue, which were then subjected to hydrogen reduction and subsequently leached with a sodium carbonate solution for alumina extraction. In an effort to establish a circular material flow, the leaching residue, which contains most of calcium and metallic iron, was reintegrated into the process to produce self-hardened pellets. Analytical techniques such as X-ray diffraction, electron probe microanalysis, X-ray fluorescence, and inductively coupled plasma-mass spectroscopy were employed for comprehensive microstructural, chemical, and elemental evaluations of the samples. The integrated process yielded a final alumina recovery rate exceeding 62%, a substantial improvement compared to the process lacking calcium looping. The incorporation of leaching residue recycling played a crucial role in significantly reducing calcium consumption throughout the integrated process, reaching approximately 70%. This research signifies a promising approach to efficiently recover valuable components from bauxite residue while mitigating environmental concerns and optimising resource utilisation.

Comparative Study of Water and Fertilizer Regimes on Water Potential, Phenolic Substances, and Photosynthetic Characteristics of Pistacia weinmannifolia

Effective water and fertilizer management is crucial for the forestry production of Pistacia weinmannifolia. This experiment employed an orthogonal design to measure the water potential, anthocyanins, chlorophyll, and photosynthetic parameters of Pistacia weinmannifolia under different water and fertilizer regimes. The effects of different water and fertilizer regimes on the water potential, phenolic compounds, and photosynthetic characteristics of Pistacia weinmannifolia were analyzed. A comprehensive analysis method was used to evaluate and establish the best water and fertilizer regimes system. The results showed that the water and fertilizer regimes increased the water potential, anthocyanins, chlorophyll content, flavonoids, and photosynthesis (p < 0.05). During the mid-growth stage and late mid-stage growth of Pistacia weinmannifolia, the fertilizers with the most significant effects on water potential, chlorophyll, and anthocyanins were nitrogen (N) and phosphorus (P). The supply of a certain amount of N and P had positive effect on water potential, chlorophyll, and anthocyanins. Increasing N content was more effective in improving carboxylation efficiency than increasing P content. The effect of N content on photosynthetic efficiency was greater than that of P content Analyses using the TOPSIS model demonstrate that Pistacia weinmannifolia exhibits superior comprehensive efficiency in water potential, chlorophyll, flavonoid, and anthocyanin content. When applying 0.54 g·plant−1 of pure P and 0.67 g·plant−1 of pure N, with the relative soil moisture content maintained at 85%, the optimal comprehensive benefit for photosynthetic indicators is achieved with 0.34 g·plant−1 of pure P and 0.77 g·plant−1 of pure N, while maintaining the relative soil moisture content at 46.66%. These findings indicate that the water–fertilizer coupling treatment group exhibited improved growth status and photosynthesis. Therefore, the cultivation of Pistacia weinmannifolia should prioritize maintaining a balanced water–fertilizer ratio to optimize resource utilization.

The role of dematerialization in promoting sustainable development

In light of the escalating global environmental issues, including climate change, biodiversity decline, and diverse pollutant types, researchers have introduced the notion of dematerialization. This idea primarily emphasizes minimizing material use and optimizing resource utilization to mitigate environmental impacts. This paper, through a literature review and case studies, will discuss the fundamental concept of dematerialization, its relationship with the Sustainable Development Goals (SDGs), and its role in different aspects of modern society. The paper will also examine how various innovations and policies reflect dematerialization and how this process contributes to achieving the SDGs. Research and studies indicate that dematerialization is an essential trajectory for humanity. Numerous rich nations and certain emerging ones are actively promoting this process. However, significant benefits may not be visible in the short term, and further technological and political supports are needed globally to ensure its development and effectiveness.

Intelligent Agriculture System using KNN Algorithm

The agricultural sector faces the challenge of maximizing crop yields while maintaining sustainability and resource efficiency. Nostalgic or Romantic Views, oftenreliant on manual monitoring and subjective decision-making, can result in inefficiencies and lower productivity. To address these issues, an intelligent agriculture system utilizing the K-Nearest Neighbors (KNN) algorithm has been proposed. This paper presents an intelligent agriculture system that leverages the K- Nearest Neighbors (KNN) algorithm to enhance crop management and yield prediction. By analyzing various environmental factors such as soil moisture, temperature, and humidity, the system accurately classifies the optimal planting and harvesting times for different crops. Additionally, it provides real-time recommendations for irrigation and fertilization based on predictive analysis. The integration of KNN allows for adaptive learning from historical data, thereby improving decision-making processes for farmers. This approach aims to optimize resource utilization, increase productivity, and promote sustainable agricultural practices. The proposed intelligent agriculture system leverages the K- Nearest Neighbors (KNN) algorithm to enhance crop management and sustainability. By analyzing real-time environmental data and historical agricultural records, the system provides precise recommendations for optimal planting and harvesting times, efficient irrigation schedules, and tailored fertilization strategies. This data-driven approach aims to increase crop yields, optimize resource utilization, and reduce the environmental impact of farming practices. The system's continuous learning capability allows it to adapt to changing conditions, ensuring that farmers receive up-to-date and accurate guidance. Overall, the integration of KNN in agriculture represents a significant advancement towards sustainable and efficient farming.

Integrating taxation, financial controls, and risk management: a comprehensive model for small and medium enterprises to foster economic resilience

Small and Medium Enterprises (SMEs) are vital contributors to economic growth, job creation, and innovation, yet they face persistent challenges in maintaining resilience amidst dynamic and uncertain environments. This paper proposes an integrated model that combines taxation, financial controls, and risk management as a comprehensive framework to enhance SME resilience. Theoretical insights are provided on the interdependencies of these elements, highlighting how their integration can optimize resource utilization, ensure regulatory compliance, and mitigate risks. Practical applications of the model are explored, emphasizing its scalability and adaptability to diverse economic contexts. The role of government policies, private sector initiatives, and technological advancements in supporting SMEs is discussed, with actionable recommendations for stakeholders to facilitate implementation. By adopting this holistic approach, SMEs can achieve operational efficiency, financial stability, and long-term sustainability, ultimately strengthening their contributions to global economic resilience. Keywords: SME Resilience, Tax Compliance, Financial Controls, Risk Management, Economic Sustainability, Integrated Model.

Optimizing Surgical Site Infection Prevention in Dermatologic Surgery.

We aim to review modifiable risk factors and practices for surgical site infections (SSIs) reduction in cutaneous surgeries. The existing norms are assessed with the latest evidence, with the aim of enhancing and optimizing intra and postoperative strategies. This review seeks to offer an updated summary of the results of evidence for SSI reduction strategies tailored for practicing general dermatologists. Searches were conducted for "cutaneous surgery surgical site infection complications" using PubMed Central® and DynaMed®. Articles with pragmatic guideline recommendations were selected. We found evidence for intraoperative factors such as non-sterile gloves, brushless hand scrubbing/simple hand washing, sterile materials, and chlorhexidine gluconate as a skin antiseptic. For postoperative factors, there is a lack of evidence to support the use of topical antibiotic ointments, dressings, or waiting 48 hours before wetting to prevent SSI. Several intra/postoperative factors not specific to dermatologic procedures are briefly discussed for additional context. Several SSI risk factors are inherent to patients or necessary procedures; however, dermatologists have identified modifiable risk factors and developed protocols to mitigate SSI risks intraoperatively and postoperatively. By questioning established practices in cutaneous surgery aimed at preventing SSIs, we can work towards the optimal utilization of resources. This dual-focused approach not only enhances the efficiency of the healthcare system but also diminishes the risks associated with SSIs. It is important to acknowledge that this review does not encompass all factors essential for consideration in these recommendations. Nonetheless, it will approach these factors with an evidence-based lens, placing SSI prevention at the forefront.

Integrating genomic evidence for an updated taxonomy of the bacterial genus Spiribacter

The genus Spiribacter encompasses halophilic bacteria widely distributed in hypersaline environments worldwide. Despite their ecological significance, initially isolating Spiribacter species under laboratory settings was challenging due to the lack of knowledge of their growth and cultivation requirements. However, with improved understanding of their ecological niche and metabolic pathways, additional species of Spiribacter have been successfully isolated and identified from diverse locations around the globe. Enriched media with sodium pyruvate as carbon source facilitated the isolation of twelve new strains closely related to the genus Spiribacter from hypersaline environments in Spain. Genome sequencing and analysis of these new strains and previously described Spiribacter species provided insights into their genomic features and phylogenomic relationships, supporting the delineation of three distinct new species within this genus, designated as Spiribacter insolitus sp. nov., Spiribacter onubensis sp. nov., and Spiribacter pallidus sp. nov. In Spiribacter species, streamlined genomes enhance survival in hypersaline environments by reducing non-essential genes and optimizing resource utilization. Key genes involved in osmoprotectant mechanisms, including those for the metabolism of myo-inositol, hydroxyproline, and L-proline, were identified and numerous transporters were noted, ensuring efficient nutrient acquisition and osmotic balance. Notably, these new species, along with other Spiribacter strains, exhibit metabolic diversity in utilizing inorganic sulfur compounds, including thiosulfate and tetrathionate, for energy production and adaptation to hypersaline environments. The presence of thiosulfate dehydrogenase (TsdA) genes suggests their capability to oxidize thiosulfate to tetrathionate, potentially influencing both aerobic and anaerobic respiration. Furthermore, the prevalence of the sqr gene indicates a role for sulfide oxidation in Spiribacter metabolism, underlining their metabolic versatility in saline habitats. These adaptations allow Spiribacter to thrive in nutrient-limited, high-salinity habitats. Moreover, genome mining analysis and physiological disparities observed in the already described species Spiribacter halobius raise significant challenges to its classification within the genus Spiribacter.

Policy Proposals for Mitigating Intensive Care Unit Strain: Insights from the COVID-19 Pandemic.

Intensive care unit (ICU) strain, characterized by a discrepancy between perceived or actual intensive care resources and demand, significantly impacts patient outcomes and healthcare worker well-being. The coronavirus disease (COVID-19) pandemic exacerbated ICU strain, leading to increased mortality and extended hospital stays, affecting both critically ill patients with and without COVID-19. A systematic review identified 16 leading and lagging indicators of ICU capacity strain, including queuing, premature and after-hours ICU discharge, use of temporary space, length of stay, burnout, staffing and nurse-to-patient ratio, ICU census, acuity and turnover, standardized mortality ratio, readmissions, availability of critical supplies, ventilator use, and surgery cancellation. However, variability in operational definitions and limited evidence regarding the reliability, validity, usability, and feasibility limit the value of single indicators for informed strategic planning and policy guidance. Regional and national policies and programs are essential to enhance real-time monitoring for effective management of critical care resources, and they mitigate the impact of ICU strain, facilitating complex interhospital transfers to reduce strain and ensuring comprehensive strategies for enhancing ICU resilience. Proactive regional cooperation is advocated for policy formulation, knowledge exchange, and resource allocation to anticipate and mitigate ICU strain, ensuring equitable healthcare access during global health crises. The policy implications for future preparedness emphasize the importance of evidence-based triage and adaptable patient management strategies alongside ethical considerations in resource allocation and the role of behavioral economic insights in optimizing resource utilization and collaborative healthcare practices. This multifaceted approach for addressing ICU strain comprehensively and effectively during a pandemic would promote health equity and enhance healthcare system resilience under both routine operations and crisis conditions.

Evaluating agriculture 4.0 decision support systems based on hyperbolic fuzzy-weighted zero-inconsistency combined with combinative distance-based assessment

Agriculture 4.0 plays a crucial role in shaping sustainable cities and societies by revolutionizing urban food systems. By incorporating advanced technologies like precision farming, vertical gardening, and data analytics, Agriculture 4.0 improves local food production, reduces food transportation, and optimizes resource utilization. This paper introduces an innovative approach using Multi-Criteria Decision-Making (MCDM) to assess Agriculture 4.0 Decision Support Systems (ADSS), contributing significantly to the selection of optimal systems that can drive sustainability in smart agriculture. The novelty of this research lies in developing a comprehensive evaluation framework that extends the hyperbolic fuzzy-weighted zero-inconsistency method for criteria weighting, combined with the combinative distance-based assessment method for benchmarking ADSS. The assessment matrix evaluates 13 ADSS across eight key criteria, including “accessibility,” “re-planning,” “expert knowledge,” “interoperability,” “scalability,” “uncertainty and dynamic factors,” “prediction and forecast,” and “historical data analysis”. Results from the hyperbolic fuzzy-weighted zero-inconsistency approach highlight “re-planning” (0.143) and “prediction and forecast” (0.140) as the most significant criteria, while “expert knowledge” ranked lowest (0.113). In the combinative distance-based assessment, the system labelled “OCCASION” achieved the highest score (3.843), positioning it as the most favourable ADSS, whereas the “MOLP-based beef supply chain” system scored lowest (−3.519). Sensitivity analysis, conducted using varying sets of weights, confirms the robustness and reliability of the proposed approach. This research provides a powerful decision-making tool that can guide stakeholders in selecting the best ADSS, ultimately promoting sustainability and resource optimization in Agriculture 4.0. The findings have important implications for farmers, agribusiness, and smart agriculture, demonstrating the potential of the methodology to enhance decision-making processes in a critical sector.

Integrated vertical mining and processing for Critical Mineral: A case study in Obi Island, North Maluku Province

Abstract Harita Nickel Group in Obi Island, Indonesia pioneered the utilization of limonite nickel ore (Ni <1.5%) for electric car batteries in the country. Nickel mining in Obi Island transitioned from nickel mining in 2010 to integrated mining by establishing downstream processing of raw materials for stainless steel in 2016 and electric car battery in 2018. Pyrometallurgical and hydrometallurgical technologies are employed in factories within Harita Nickel’s mining concession area, notably PT Trimegah Bangun Persada Tbk (PTTBP). This vertically integrated mining and downstream processing in Obi Island, South Halmahera Regency, North Maluku Province, marks a significant advancement in Indonesia’s mining industry. The close proximity (<3km) of mining and factory locations ensures efficiency and low costs. In vertically integrated mining, companies seek to maximize the use of all materials involved in production processes, minimizing waste and optimizing resource utilization. This research focusing on the waste generated during nickel processing of RKEF can be repurposing into new products, reducing environmental impact and increasing sustainability. Nickel, a critical mineral, has garnered global attention, particularly since Indonesia emerged as the world’s largest nickel ore reserve. The extractive industry, employing pyrometallurgy technology, has rapidly produced stainless steel raw materials from nickel mining since 2016. Indonesia’s nickel ore, known as saprolite nickel with high nickel content (>1.7%), has been exploited since the 1970s, while the low-grade limonite nickel layer gained traction only around mid-2018. In the future, Harita Nickel project in western Obi Island will be developed as an Eco Industrial Park for a greater integration, highlighting the comprehensive benefits of vertically integrated mining and providing a more thorough and insightful evaluation of its potential.

Dynamic Hardware Accelerator Selection Achieving Optimal Utilization of Resources

Dynamic Hardware Accelerator Selection Achieving Optimal Utilization of Resources

Assessing the Effectiveness of Satellite and UAV-Based Remote Sensing for Delineating Alfalfa Management Zones Under Heterogeneous Rootzone Soil Salinity

Site-specific application of agricultural inputs is crucial for optimizing resource utilization in alfalfa (Medicago sativa L.) production and addressing challenges such as soil salinity. The main objective of this study was to assess the effectiveness of PlanetScope and UAV-based NDVI imagery for delineating alfalfa management zones under heterogeneous rootzone soil salinity. The research was conducted in the alfalfa field located in Imperial Valley, CA. The extent of rootzone soil salinity was assessed using Electromagnetic induction (EMI) technology and deep soil sampling. Reference management zones were then defined using the soil salinity (ECe) map derived from apparent electrical conductivity (ECa) data. Additionally, a time series of NDVI images from PlanetScope imagery and an NDVI image captured using an unmanned aerial vehicle were used to delineate remote sensing-based management zones. Laboratory analysis of disturbed soil samples collected at various depths provided soil physicochemical property data. Soil salinity of the samples ranged from 2.2 to 13.4 dS m−1 with a moderate level of variability (CV = 37.7%). ECe-based management zones accounted for approximately 83% of the field's variability and exhibited substantial differentiation among delineated zones concerning diverse soil properties, including ECa, ECe, gravimetric water content, Mg2+, boron, Ca2+, Na+, and Cl−. Notably, NDVI images effectively captured field variability on par with ECe-based zoning. Moreover, NDVI images recommended the same optimal number of zones (i.e., three) to address the field's variability, aligning with the ECe-based zoning approach. Our findings highlight that heterogeneity of soil salinity in the root zone primarily impacts the variability of alfalfa NDVI early in the growing season. Consequently, this early stage emerges as the most opportune timeframe for NDVI-based zoning for rapid assessment of rootzone soil salinity concerns.

Latency-Aware Unified Dynamic Networks for Efficient Image Recognition.

Dynamic networks have become a pivotal area of study in deep learning due to their ability to selectively activate computing units (such as layers or channels) or dynamically allocate computation to information-rich regions. This capability significantly curtails unnecessary computations, adapting to varying inputs. Despite these advantages, the practical efficiency of dynamic models often falls short of theoretical computation. This discrepancy arises from three primary challenges: 1) a lack of a unified framework across different dynamic inference paradigms due to the fragmented research landscape; 2) an excessive focus on algorithm design at the expense of scheduling strategies, which are essential for optimizing resource utilization on hardware; and 3) the complexity of latency evaluation, since most current libraries cater to static operators. To tackle these issues, we introduce Latency-Aware Unified Dynamic Networks (LAUDNet), a general framework that integrates three fundamental dynamic paradigms-spatially-adaptive computation, layer skipping, and channel skipping-into a single unified formulation. LAUDNet not only refines algorithmic design but also enhances scheduling optimization with the aid of a latency predictor. This predictor efficiently and accurately predicts the inference latency of dynamic operators on specific hardware setups. Our empirical assessments across multiple vision tasks-image classification, object detection, and instance segmentation-confirm that LAUDNet significantly bridges the gap between theoretical and practical efficiency. For instance, LAUDNet cuts down the practical latency of its static counterpart, ResNet-101, by over 50% on hardware platforms like V100, RTX 3090, and TX2 GPUs. Additionally, LAUDNet excels in the accuracy-efficiency trade-off compared to other methods.

Dynamic workload balancing to part input sequencing for integrated scheduling decision-making of flexible manufacturing systems

Flexible manufacturing systems (FMSs) are crucial in contemporary manufacturing environments because they provide the required agility and adaptability to face volatile customer demands. Balancing workload among different work stations of an FMS is essential to ensure optimal resource utilization, minimize idle times, and improve overall system performance. This research is aimed to study the application of dynamic workload balancing to part input sequencing for integrated FMS scheduling decision-making. In this work, we propose an online algorithm that balances workload dynamically in FMSs. A mathematical model of FMS scheduling integration is presented. The proposed approach schedules tasks not only on machines but also on the robot responsible for part movement within a shop floor. The proposed approach is evaluated in two aspects of comparison and analysis. Data analysis is made by simulation experiment and statistical analysis. Conclusions with managerial implications for practical applications and future research suggestions are provided.

Parallel implementation and performance of super-resolution generative adversarial network turbulence models for large-eddy simulation

Super-resolution (SR) generative adversarial networks (GANs) are promising for turbulence closure in large-eddy simulation (LES) due to their ability to accurately reconstruct high-resolution data from low-resolution fields. Current model training and inference strategies are not sufficiently mature for large-scale, distributed calculations due to the computational demands and often unstable training of SR-GANs, which limits the exploration of improved model structures, training strategies, and loss-function definitions. Integrating SR-GANs into LES solvers for inference-coupled simulations is also necessary to assess their a posteriori accuracy, stability, and cost. We investigate parallelization strategies for SR-GAN training and inference-coupled LES, focusing on computational performance and reconstruction accuracy. We examine distributed data-parallel training strategies for hybrid CPU–GPU node architectures and the associated influence of low-/high-resolution subbox size, global batch size, and discriminator accuracy. Accurate predictions require training subboxes that are sufficiently large relative to the Kolmogorov length scale. Care should be placed on the coupled effect of training batch size, learning rate, number of training subboxes, and discriminator’s learning capabilities. We introduce a data-parallel SR-GAN training and inference library for heterogeneous architectures that enables exchange between the LES solver and SR-GAN inference at runtime. We investigate the predictive accuracy and computational performance of this arrangement with particular focus on the overlap (halo) size required for accurate SR reconstruction. Similarly, a posteriori parallel scaling for efficient inference-coupled LES is constrained by the SR subdomain size, GPU utilization, and reconstruction accuracy. Based on these findings, we establish guidelines and best practices to optimize resource utilization and parallel acceleration of SR-GAN turbulence model training and inference-coupled LES calculations while maintaining predictive accuracy.

AI-Based Monitoring for Enhanced Poultry Flock Management

The exponential growth of global poultry production highlights the critical need for efficient flock management, particularly in accurately counting chickens to optimize operations and minimize economic losses. This study advances the application of artificial intelligence (AI) in agriculture by developing and validating an AI-driven automated poultry flock management system using the YOLOv8 object detection model. The scientific objective was to address challenges such as occlusions, lighting variability, and high-density flock conditions, thereby contributing to the broader understanding of computer vision applications in agricultural environments. The practical objective was to create a scalable and reliable system for automated monitoring and decision-making, optimizing resource utilization and improving poultry management efficiency. The prototype achieved high precision (93.1%) and recall (93.0%), demonstrating its reliability across diverse conditions. Comparative analysis with prior models, including YOLOv5, highlights YOLOv8’s superior accuracy and robustness, underscoring its potential for real-world applications. This research successfully achieves its objectives by delivering a system that enhances poultry management practices and lays a strong foundation for future innovations in agricultural automation.