Efficient Resource Utilization Research Articles

Assessment of phylogenetic relationships and genetic diversity of Sagittaria trifolia using phenotypic traits and SNP markers.

The aquatic perennial herb Sagittaria trifolia L. commonly known as arrowhead, has been utilized in China both as a culinary vegetable and in traditional medicines. Characterizing the phylogenetic relationships and genetic diversity of arrowheads is crucial for improved management, conservation, and efficient utilization of the germplasm resources associated with this species. Herein, we presented the phenotypic traits and genome-wide DNA marker-based analyses of 111 arrowhead accessions, most of which were from China. Cluster analysis revealed that arrowhead could be categorized into two clusters based on 11 phenotypic traits, with Cluster 1 comprising two subclusters. All accessions were clustered into three sub-clusters based primarily on leaf shape and tuber weight. A set of 759,237 high-quality single-nucleotide polymorphisms was identified and used to assess the phylogenetic relationships. Population structure and phylogenetic tree analyses suggested that the accessions could be classified into two major groups, Group I was further subdivided into two subgroups, aligning with the clusters identified through morphological classification. By employing Sagittaria lichuanensis as an outgroup, the rooted tree revealed that the evolutionary relationships within the three groups followed a progression from Group I-1 to Group I-2 and finally to Group II. The landraces were clustered into one group along with the remaining wild accessions. The level of genetic diversity for Group I (π = 0.26) was slightly lower than that which was estimated for Group II (π = 0.29). The lowest pairwise differentiation levels (Fst, 0.008) were obtained from the comparison between groups I-2 and II, indicating that the two groups were the most closely related. This study provides novel insights into germplasm classification, evolutionary relationships, genomics and arrowhead breeding.

Enhancing the valorization efficiency of Camellia oil extraction wastes through sequential green acid pretreatment and solid-state fermentation-based enzymatic hydrolysis

This study focuses on the underutilized Camellia oleifera oil extraction wastes, namely C. oleifera shell (COS) and cake (COC), which are often overlooked due to their high recalcitrance and antimicrobial properties. COS was found to be an ideal substrate for producing on-site enzymes through solid-state fermentation (SSF) that can be used for lignocellulosic biomass degradation. Additionally, pretreating COS with 2 % (w/v) oxalic acid greatly enhanced sugar production, achieving 9.22 and 5.24 times more sugar compared to room temperature and thermal pretreatment methods, respectively. The highest sugar of 28 g/L was achieved by utilizing a mixture of COS and COC. Enzymatic hydrolysis performance was evaluated through three routes. In the first two routes, the whole pretreated slurry was employed, except the pH was adjusted in route 2. In route 3, the pretreated hydrolysate was recovered, while the solid residue underwent further enzymatic hydrolysis. Ultimately, route 3 resulted in the highest sugar of 20.58 g/L, using SSF enzymes and oxalic acid pretreated solid residues of COS and COC mixture. This value is twice the performance achieved using a single substrate of COS. The fine-tuning strategy employed in route 3 led to (1) achieving high sugar recovery from pretreatment and enzymatic hydrolysis, (2) minimizing water and alkaline regulator consumption, and (3) optimizing resource utilization efficiency. The effectiveness of this approach was also attributed to the synergistic effect of oxalic acid pretreatment and the use of mixed substrate. The possible mechanisms underlying these processes were discussed, offering potential directions for future studies aimed at developing even more efficient approaches.

Enhancing Resource Utilization Efficiency in Serverless Education: A Stateful Approach with Rofuse

Traditional container orchestration platforms often suffer from resource wastage in educational settings, and stateless serverless services face challenges in maintaining container state persistence during the teaching process. To address these issues, we propose a stateful serverless mechanism based on Containerd and Kubernetes, focusing on optimizing the startup process for container groups. We first implement a checkpoint/restore framework for container states, providing fundamental support for managing stateful containers. Building on this foundation, we propose the concept of “container groups” to address the challenges in educational practice scenarios characterized by a large number of similar containers on the same node. We then propose the Rofuse optimization mechanism, which employs delayed loading and block-level deduplication techniques. This enables containers within the same group to reuse locally cached file system data at the block level, thus reducing container restart latency. Experimental results demonstrate that our stateful serverless mechanism can run smoothly in typical educational practice scenarios, and Rofuse reduces the container restart time by approximately 50% compared to existing solutions. This research provides valuable exploration for serverless practices in the education domain, contributing new perspectives and methods to improve resource utilization efficiency and flexibility in teaching environments.

Improving IT Assets Management with ITIL 4 Framework

IT Asset Management (ITAM) is crucial for organizations as it enables efficient utilization of IT resources, cost reduction, and risk mitigation. Horangi, a startup company, recognizes the importance of asset optimization and aims to enhance its ITAM service. To achieve this, researcher conducts research to identify a suitable framework as a solid foundation. ITIL 4, a widely adopted IT service management framework, is chosen, along with the Continual Service Improvement and Service Value Chain models. These models provide guidelines and recommendations to identify weaknesses and improve current processes while enabling continuous improvement in response to the dynamic IT landscape. The research employs a qualitative approach, utilizing in-depth interviews, document research, and the ITIL 4 guidebook. The study aims to provide recommendations and a foundation for developing guidelines and workflows in ITAM within the company. However, a limitation of this research is not much research related to ITIL 4 in ITAM area and cannot proceed until the implementation of recommendations due to funding constraints and approval processes. To overcome this limitation, it is suggested that future research includes the implementation process to obtain more optimal evaluation results.

Toward efficient resource utilization at edge nodes in federated learning

Federated learning (FL) enables edge nodes to collaboratively contribute to constructing a global model without sharing their data. This is accomplished by devices computing local, private model updates that are then aggregated by a server. However, computational resource constraints and network communication can become a severe bottleneck for larger model sizes typical for deep learning (DL) applications. Edge nodes tend to have limited hardware resources (RAM, CPU), and the network bandwidth and reliability at the edge is a concern for scaling federated fleet applications. In this paper, we propose and evaluate a FL strategy inspired by transfer learning in order to reduce resource utilization on devices, as well as the load on the server and network in each global training round. For each local model update, we randomly select layers to train, freezing the remaining part of the model. In doing so, we can reduce both server load and communication costs per round by excluding all untrained layer weights from being transferred to the server. The goal of this study is to empirically explore the potential trade-off between resource utilization on devices and global model convergence under the proposed strategy. We implement the approach using the FL framework FEDn. A number of experiments were carried out over different datasets (CIFAR-10, CASA, and IMDB), performing different tasks using different DL model architectures. Our results show that training the model partially can accelerate the training process, efficiently utilizes resources on-device, and reduce the data transmission by around 75% and 53% when we train 25%, and 50% of the model layers, respectively, without harming the resulting global model accuracy. Furthermore, our results demonstrate a negative correlation between the number of participating clients in the training process and the number of layers that need to be trained on each client’s side. As the number of clients increases, there is a decrease in the required number of layers. This observation highlights the potential of the approach, particularly in cross-device use cases.

Particle swarm optimization-extreme learning machine model combined with the ADA boost algorithm for short-term wind power prediction

In our proposed approach, we integrate ADA boosting with particle swarm optimization-extreme learning machine (PSO-ELM) to enhance the accuracy of wind power estimation, addressing the inherent unpredictability and variability in wind energy. Initially, we refine the thresholds and input weights of the extreme learning machine (ELM) and then construct the PSO-ELM prediction model. ADA Boost is utilized to generate multiple weak predictors, each comprising a distinct hidden layer node. The PSO technique is then employed to optimize the input weights and thresholds for each weak predictor. The final forecast is attained by amalgamating and weighting the outcomes from each weak predictor using a robust wind power forecast model. Experimental validation utilizing data from Turkish wind turbines underscores the efficacy of our approach. Comparative analysis against contemporary techniques such as ensemble learning models and optimal neural networks reveals that our ADA-PSO-ELM model demonstrates superior accuracy and generalizability in predicting wind power output under real-world conditions. The proposed approach offers a promising framework for addressing the challenges associated with wind power estimation, thereby facilitating more reliable and efficient utilization of wind energy resources.

Synergistic photocatalysis of oxygen-enriched vacancy BiOBr based on rice husk biochar: Efficient seawater purification achieved by carrier directional migration

Addressing seawater pollution is crucial for the efficient utilization of seawater resources. Employing solar-driven seawater purification emerges as an ideal solution for the future renewable energy landscape. Herein, biomass carbon and oxygen-enriched defect materials were selected to design a high-performance photocatalyst for seawater purification. The strategic combination of defect energy levels and electron-conducting carbon enhances the directional migration and separation of photogenerated particles, thereby boosting the overall photocatalytic efficiency in seawater purification. In the simulated seawater experiment, ROV-BOB/RHC-3 exhibits significant resistant to conventional ions interference during purification. Transitioning to real seawater experiments, ROV-BOB/RHC-3 exhibits impressive removal performance for RhB and TC, achieving substantial purification in 10 L of seawater under natural sunlight. Combine free radical trapping experiments and electron spin resonance (ESR) analysis shows that reactive oxygen species (•O2- and 1O2) are responsible in purification. The project provides a practical and effective basis for further research on efficient biomass carbon-based photocatalysts to seawater purification.

Runoff Prediction in Different Forecast Periods via a Hybrid Machine Learning Model for Ganjiang River Basin, China

Accurate forecasting of monthly runoff is essential for efficient management, allocation, and utilization of water resources. To improve the prediction accuracy of monthly runoff, the long and short memory neural networks (LSTM) coupled with variational mode decomposition (VMD) and principal component analysis (PCA), namely VMD-PCA-LSTM, was developed and applied at the Waizhou station in the Ganjiang River Basin. The process begins with identifying the main forecasting factors from 130 atmospheric circulation indexes using the PCA method and extracting the stationary components from the original monthly runoff series using the VMD method. Then, the correlation coefficient method is used to determine the lag of the above factors. Lastly, the monthly runoff is simulated by combining the stationary components and key forecasting factors via the LSTM model. Results show that the VMD-PCA-LSTM model effectively addresses the issue of low prediction accuracy at high flows caused by a limited number of samples. Compared to the single LSTM and VMD-LSTM models, this comprehensive approach significantly enhances the model’s predictive accuracy, particularly during the flood season.

Enhancing yield, mineral composition, and energy fractions through intercropping and nutrient management in oats and berseem

Inadequate green fodder of subpar quality poses a significant risk to livestock productivity, underscoring the pivotal role of intercropping and integrated nutrient management to effectively address the dual challenge of meeting both quantity and quality requirements in fodder. In this study, employing factorial randomized block design the experiment incorporated intercropping treatments S1- sole oats, S2- sole berseem, S3- 2 rows of oats + 1 row of berseem, and S4 −1 row of oats + 2 rows of berseem) alongside four nutrient management treatments N1- Control (100 % Recommended dose of fertilizer (RDF)), N2 − 50 % RDF + Plant growth promoting rhizobacteria (PGPR) + 2 spray of seaweed extract, N3 − 75 % RDF + PGPR + 2 spray of seaweed extract, N4 − 100 % RDF + PGPR + 2 spray of seaweed extract with each treatment replicated thrice. Results revealed that the significantly highest green fodder yield of oats (24.73 and 12.81 t ha−1) and berseem (13.35 and 13.79 t ha−1) in S1 and S2 crops recorded at both the cuts, respectively followed by intercropping of oats: berseem in 2:1 (S3) and 1:2 (S4) row ratio. Application of 100 % RDF + PGPR + 2 spray of seaweed extract recorded the highest green fodder yield of oats (21.80 and 9.79 t ha−1) and berseem (8.09 and 11.46 t ha−1). Oats and berseem recorded varying trends in nutrient concentration (1.72–18.9 %), nutrient uptake (35.5 kg ha−1 to 251.4 kg ha−1), energy fractions (0.33 MJ kg−1 to 10.2 MJ kg−1) due to intercropping and nutrient management. Therefore, we recommend adopting a combination of oats: berseem intercropping in a 2:1 row ratio, coupled with the application of 100 % RDF + PGPR + 2 sprays of seaweed extract to optimize yield, improve nutritional quality, and increase energy content. This approach ensures efficient utilization of available resources and can be beneficial for the farming community.

Biochemical properties of sludge derived hydrothermal liquid products and microbial response of wastewater treatment

Sludge hydrothermal treatment can achieve efficient reduction and resource utilization, and the hydrothermal liquid products (HLPs) generated in the hydrothermal process may be returned to beginning of the wastewater plant for resource utilization. In this study, dehydrated sludge was treated by a hydrothermal treatment process, and hydrothermal products were separated by centrifugation. Then the HLPs were returned to the front end of the anaerobic-oxic (A/O) reactor to explore their potential role as a source of denitrified carbon. Study focuses on the HLPs’ changes of Carbon (C), Nitrogen (N), and Phosphorus (P) speciation and distribution, and clarifying the organic matter forms and their impacts on the microbial community composition and functional expression in biological process after recirculation. The results show C and N components are dissolved to HLPs, existing in forms of easily biodegraded components, such as acetic acid (28.04 %), tryptophan, and humic substances, while P mainly precipitates in the solid residue, avoiding accumulation in the wastewater treatment system. The dominant bacteria Proteobacteria accounts for 30 %–40 % of the total sequence, and the abundance of metabolism-related genes maintain the highest level. The wastewater treatment process can withstand the shock of the recirculation of HLPs, and the microbial community composition remains stable.

Comprehensive review of load balancing in cloud computing system

Load balancing plays a critical role in optimizing resource utilization and enhancing performance in cloud computing systems. As cloud environments grow in scale and complexity, efficient load balancing mechanisms become increasingly vital. This paper presents a comprehensive review of load balancing techniques in cloud computing systems, with a focus on their applicability, advantages, and limitations. The review encompasses both static and dynamic load balancing approaches, evaluating their effectiveness in addressing the challenges posed by cloud infrastructure, such as heterogeneity, scalability, and variability in workload demands. Furthermore, the review examines load balancing algorithms considering factors such as resource utilization, response time, fault tolerance, and energy efficiency. Additionally, the impact of load balancing on cloud performance metrics, including throughput, latency, and scalability, is analyzed. This review aims to provide insights into the state-of-the-art load balancing strategies and serve as a valuable resource for researchers, practitioners, and system designers involved in the development and optimization of cloud computing systems.

The culture of Chlorella with livestock wastewater and the application of its oligosaccharides in promoting rice seed germination under high salinity conditions

Algal oligosaccharides, derived from polysaccharides in algal biomass, exhibit bioactive properties that enhance plant antioxidant enzyme activity and free radical scavenging. Currently, algal oligosaccharides are mainly produced from large algae, while studies on preparing algal oligosaccharides from microalgae are relatively insufficient. This study focuses on utilizing Chlorella cultivated under controlled conditions using diluted livestock wastewater to produce algal oligosaccharides and investigates their impact on rice seed germination under salt stress. Results show that culturing Chlorella with diluted livestock wastewater not only stimulated algal growth but also efficiently removed nitrogen, phosphorus, and other nutrients. Algal oligosaccharides demonstrated significant improvements in rice seed germination, vigor indices, biomass accumulation, and nitrogen absorption under salt stress. Physiological indicators revealed elevated osmotic adjustment substances, increased chlorophyll content, and alleviated oxidative damage in rice seedlings treated with algal oligosaccharides. The study introduces an innovative method of using livestock wastewater for algal oligosaccharides production, emphasizing its dual benefits including efficient resource utilization and significant cost reduction. The findings also support the theoretical application of Chlorella-derived algal oligosaccharides in enhancing rice cultivation under salt stress.

Catalytic supercritical water gasification of oily sludge with the FeOOH/AC for hydrogen production

Along with the continuous increase of crude oil consumption in China, the production of oily sludge is increasing. The traditional oily sludge treatment technology cannot realize the purpose of green and efficient resource utilization of oily sludge. Supercritical water gasification hydrogen technology can efficiently convert oily sludge into hydrogen and realize the resource utilization of oily sludge. However, the traditional supercritical water gasification process requires high energy consumption. It is necessary to study the catalysts in the gasification process. Loaded catalysts have a large specific surface area and can effectively reduce the reaction activation energy. This paper investigated the effects of different catalyst types and concentrations on gasification. The results showed that adding FeOOH/AC effectively increased hydrogen production, and the best catalytic effect was achieved when the FeOOH loading was 10 wt%. The catalyst concentration was 5%, with a hydrogen production rate of 4.638 mol/kg. It was found that the activation energy of the reaction with the addition of the catalyst was reduced by 8.61 kJ/mol compared to that without the catalyst through kinetic analysis. 8.61 kJ/mol.

Emergency Department closed reduction of dislocated THR: the REDDTHR Prospective Multi-centre Study.

Dislocation is a potentially devastating complication severely affecting outcomes post total hip arthroplasty (THR). We aimed to assess the efficacy and safety of closed reduction of a dislocated THR within the Emergency Department (ED). A prospective multi-centre study was conducted over a 1-year period from November 2020 to December 2021 within 10 hospitals based in the East of England. Collected data included patient demographics, agent used for sedation, hospital length of stay, implant type and discharge destination. Patients were analysed according to whether successful reduction was performed in the ED or not. The primary outcome was length of stay, with secondary outcomes including discharge destination and pain post-procedure. We studied 99 patients with an average age of 77.02 years, with 39 (39%) patients being male. 11 patients had revision hip replacements and 88 patients had primary THRs. 57 (57.6%) underwent closed reduction in the Emergency department, of which 44 (77.2%) were successful. Successful closed reduction was significantly associated with lower patient age (p = 0.02), lower American society of Anesthesiologists (ASA) score (p < 0.01) and use of propofol (p < 0.01). Patients who underwent successful ED closed reduction had a lower hospital stay than those that did not (1 vs. 3 days, p < 0.01), however there was no significant difference in discharge destination. When adopted, success following closed reduction is increased in younger patients with less comorbidities following use of propofol sedation. Following sedation, patients have a significantly shorter hospital stay. Increasing uptake of closed reduction of THR dislocation within the ED in suitable patients with evidence-based best practice protocols will maximise patient outcomes whilst allowing efficient resource utilisation.

Performance and protein conformation of thermally treated silver carp (Hypophthalmichthys molitrix) and scallop (Argopecten irradians) blended gels.

The quality of surimi-based products can be improved by combining the flesh of different aquatic organisms. The present study investigated the effects of incorporating diverse ratios of unwashed silver carp (H) and scallop (A) and using various thermal treatments on the moisture, texture, microstructure, and conformation of the blended gels and myofibrillar protein of surimi. A mixture ratio of A:H = 1:3 yielded the highest gel strength, which was 60.4% higher than that of scallop gel. The cooking losses of high-pressure heating and water-bath microwaving were significantly higher than those of other methods (P < 0.05). Moreover, the two-step water bath and water-bath microwaving samples exhibited a more regular spatial network structure compared to other samples. The mixed samples exhibited a microstructure with a uniform and ordered spatial network, allowing more free water to be trapped by the internal structure, resulting in more favorable gel properties. The thermal treatments comprehensively modified the tertiary and quaternary structures of proteins in unwashed mixed gel promoted protein unfurling, provided more hydrophobic interactions, enhanced protein aggregation and improved the gel performance. The findings of the present study improve our understanding of the interactions between proteins from different sources. We propose a new method for modifying surimi's gel properties, facilitating the development of mixed surimi products, as well as enhancing the efficient utilization of aquatic resources. © 2024 Society of Chemical Industry.

Potential of artificial soil preparation for vegetation restoration using red mud and phosphogypsum

Red mud and phosphogypsum have long been a focus and challenge in global industrial waste management, and their low-cost and large-scale utilization technology has always been an urgent need. This study is based on the strong acid-base neutralization reaction between red mud and phosphogypsum, which contain an elemental composition similar to that of natural soil, red mud itself has characteristic of clay minerals, and other auxiliary materials (i.e. rice husk powder, bentonite, fly ash, polyacrylamide flocculant and microbial suspension) were added, so as to explore the potential of synergistically prepared artificial soil for vegetation restoration. The results showed that the artificial soils exhibited physicochemical characteristics (e.g., pH, moisture content, cation exchange capacity) similar to those of natural soil, along with abundant organic matter, nitrogen, phosphorus, and potassium contents, meeting the growth requirements of plants. The artificial soils were able to support favorable growth of suitable plants (e.g., sunflower, wheat, rye grass), accumulating high levels of diverse enzymatic activities, comparable to those in natural soils (e.g., catalase, urease, phosphatase), or even surpassing natural soils (e.g., sucrase), and rich microorganism communities, such as Cyanobacteria, Proteobacteria, Actinobacteria in the bacteria domain, and Ascomycota in the fungi domain, were initially developed. It's suggested that preparing 1 ton of artificial soil entails synergistic consumption of 613.7 kg of red mud and 244.6 kg of phosphogypsum, accounting for mass proportions of 61.4 % and 24.5 %, respectively. In future, more evaluations on the leaching loss of nutrients and alkalinity and the environmental risks of heavy metals should be conducted to more references for the artificial soil application. In summary, the preparation of artificial soil is a very simple, efficient, scalable and low-cost collaborative resource utilization scheme of red mud and phosphogypsum, which has great potential for vegetation restoration in some places such as tailings field and soil-deficient depression.

Unraveling the Structure-Activity-Stability Relationship over Gallium-Promoted HZSM-5 Nanocrystalline Aggregates for Propane Aromatization.

The aromatization of light alkane is an important process for increasing the aromatic production and utilization efficiency of light alkane resources simultaneously. Herein, Ga-modified HZSM-5 catalysts were prepared and investigated by a series of characterization techniques such as X-ray diffraction, nuclear magnetic resonance spectroscopy, transmission electron microscopy, N2 adsorption-desorption, and NH3 temperature-programmed desorption to study their physicochemical properties. The catalytic performance in propane aromatization was also tested. Importantly, the structure-activity relationship, reaction pathway, and coke formation mechanism in propane aromatization were systematically explored. It was found that different Ga introduction methods would affect the amounts of Brønsted and Lewis acid sites, and Ga-HZSM-5 prepared by the hydrothermal method exhibited higher amounts of Brønsted and Lewis acid sites but a lower B/L ratio. As a result, Ga-HZSM-5 showed higher propane conversion and benzene, toluene, and xylene yield compared with that of Ga2O3/HZSM-5. The propane aromatization reaction pathway indicated that propane dehydrogenation to propene was a crucial step for aromatic formation. The increase of the Lewis acid density in Ga-HZSM-5 can effectively improve the dehydrogenation rate and promote the aromatization reaction. Furthermore, the formation of coke species was studied by thermogravimetry-mass spectrometry and Raman approaches, the results of which indicated that the graphitization degree of coke formed over spent Ga-HZSM-5 is lower, resulting in enhanced anticoking stability.

Does digital technology advancement promote natural resource utilization efficiency?

While China has experienced an extended period of remarkable economic growth, certain industries have faced challenges such as high pollution, energy consumption, and emissions. To address these issues, China has set strategic goals for promoting harmonious coexistence between humans and nature in the new era. As a result, enhancing the efficiency of natural resource utilization has become crucial for achieving sustainable development. In line with this objective, this paper investigates the role of digital technology advancement as a pathway to improve the efficiency of e-government and natural resource utilization. This paper employs the Slacks-Based Measure (SBM) model to calculate the efficiency of natural resource utilization in 276 cities from 2010 to 2020. Utilizing Broadband China's pilot policy, the study employs differences-in-differences and propensity score matching to investigate the impact and mechanism of digital technology progress on natural resource utilization efficiency. The results indicate that the progress in digital technology significantly promotes the efficiency of natural resource utilization, a conclusion that holds even after a series of robustness tests. Mechanism analysis suggests that the progress in digital technology primarily influences resource efficiency by upgrading industrial structures and innovating green technologies. Heterogeneity analysis reveals that the positive impact of digital technology progress on natural resource utilization efficiency is more pronounced in cities with lower political hierarchies, larger population sizes, non-resource-based economies, and those not classified as old industrial bases. This paper expands the research scope of natural resource utilization efficiency and provides specific policy recommendations.

Advancing sustainability in mechanical engineering: Integration of green energy and intelligent manufacturing

Efficient energy utilization and waste reduction are imperative for sustainable mechanical engineering practices. This paper explores the integration of green energy sources and intelligent manufacturing techniques to enhance sustainability in the mechanical engineering sector. Through quantitative analysis and case studies, the efficacy of energy-efficient technologies, waste reduction strategies, and the adoption of green energy sources are examined. Additionally, the role of smart process automation and digital twin simulation in optimizing resource utilization and operational efficiency is discussed. The findings underscore the potential of integrating sustainable practices into mechanical engineering processes, contributing to environmental conservation, cost savings, and competitiveness.

Priority Setting and Resource Allocation in Coastal Local Government Marine Regulatory Reform: Application of Machine Learning in Resource Optimization

This study investigates the prioritization and resource allocation strategies adopted by the coastal local governments of Qingdao, Dalian, and Xiamen in the context of marine regulatory reform aimed at enhancing regulatory efficiency. Data on relevant opinions, departmental requirements, and existing resource allocations were collected through a questionnaire survey. A backpropagation (BP) neural network was then applied to analyze the survey data, prioritize regulatory tasks, and propose resource allocation schemes. The findings demonstrate that integrating machine learning into marine regulation can significantly improve resource utilization efficiency, optimize task execution sequences, and enhance the scientific and refined nature of regulatory work. The BP neural network model exhibited strong predictive capabilities on the training set and demonstrated good generalization abilities on the test set. The performance of the BP neural network model varied slightly across different management levels. For the management level, the accuracy, precision, and recall rates were 85%, 88%, and 82%, respectively. For the supervisory level, these metrics were 81%, 83%, and 78%, respectively. At the employee level, the accuracy, precision, and recall rates were 79%, 81%, and 76%, respectively. These results indicate that the BP neural network model can provide differentiated resource allocation recommendations based on the needs of different management levels. Additionally, the model’s performance was assessed based on the employees’ years of experience. For employees with 0–5 years of experience, the accuracy, precision, and recall rates were 82%, 84%, and 79%, respectively. For those with 5–10 years of experience, the metrics were 83%, 86%, and 80%, respectively. For employees with over 10 years of experience, the accuracy, precision, and recall rates were 85%, 88%, and 82%, respectively. These data further confirm the applicability and effectiveness of the BP neural network model across different experience groups. Thus, the adoption of machine learning technologies for optimizing marine regulatory resources holds significant practical value, aiding in the enhancement of regulatory capacity and effectiveness within coastal local governments.