Hasil untuk "Ocean engineering"

Diego Firmenich, Leandro Antonelli, Bruno Pazos et al.

User stories are one of the most widely used artifacts in the software industry to define functional requirements. In parallel, the use of high-fidelity mockups facilitates end-user participation in defining their needs. In this work, we explore how combining these techniques with large language models (LLMs) enables agile and automated generation of user stories from mockups. To this end, we present a case study that analyzes the ability of LLMs to extract user stories from high-fidelity mockups, both with and without the inclusion of a glossary of the Language Extended Lexicon (LEL) in the prompts. Our results demonstrate that incorporating the LEL significantly enhances the accuracy and suitability of the generated user stories. This approach represents a step forward in the integration of AI into requirements engineering, with the potential to improve communication between users and developers.

Yuta Hirabayashi, Daisuke Matusoka, Konobu Kimura

Research on data-driven ocean models has progressed rapidly in recent years; however, the application of these models to global eddy-resolving ocean forecasting remains limited. The accurate representation of ocean dynamics across a wide range of spatial scales remains a major challenge in such applications. This study proposes a multi-scale graph neural network-based ocean model for 10-day global forecasting that improves short-term prediction skill and enhances the representation of multi-scale ocean variability. The model employs an encoder-processor-decoder architecture and uses two spherical meshes with different resolutions to better capture the multi-scale nature of ocean dynamics. In addition, the model incorporates surface atmospheric variables along with ocean state variables as node inputs to improve short-term prediction accuracy by representing atmospheric forcing. Evaluation using surface kinetic energy spectra and case studies shows that the model accurately represents a broad range of spatial scales, while root mean square error comparisons demonstrate improved skill in short-term predictions. These results indicate that the proposed model delivers more accurate short-term forecasts and improved representation of multi-scale ocean dynamics, thereby highlighting its potential to advance data-driven, eddy-resolving global ocean forecasting.

Qiusheng Huang, Yuan Niu, Xiaohui Zhong et al.

Accurate, high-resolution ocean forecasting is crucial for maritime operations and environmental monitoring. While traditional numerical models are capable of producing sub-daily, eddy-resolving forecasts, they are computationally intensive and face challenges in maintaining accuracy at fine spatial and temporal scales. In contrast, recent data-driven approaches offer improved computational efficiency and emerging potential, yet typically operate at daily resolution and struggle with sub-daily predictions due to error accumulation over time. We introduce FuXi-Ocean, the first data-driven global ocean forecasting model achieving six-hourly predictions at eddy-resolving 1/12° spatial resolution, reaching depths of up to 1500 meters. The model architecture integrates a context-aware feature extraction module with a predictive network employing stacked attention blocks. The core innovation is the Mixture-of-Time (MoT) module, which adaptively integrates predictions from multiple temporal contexts by learning variable-specific reliability , mitigating cumulative errors in sequential forecasting. Through comprehensive experimental evaluation, FuXi-Ocean demonstrates superior skill in predicting key variables, including temperature, salinity, and currents, across multiple depths.

Yongfeng Yang

Tides represent the daily alternations of high and low waters along coastlines and in oceans, and the current theory (termed the gravitational forcing mechanism) explains them as a manifestation of the response of ocean water to the Moon's (Sun's) gravitational force. However, although the purely hydrodynamic models representing the current theory have been widely tested over global ocean,their tidal elevation accuracies are generally low. This implies an uncertainty as to whether the gravitational forcing mechanism is the best explanation for tides. In this study, we present a new theory (termed the oceanic basin oscillation-driving mechanism), in which tides are explained as a manifestation of oscillating ocean basin that is intricately linked to the elongated spinning solid Earth due to the Moon (Sun). Based on this new theory, we develop an algebraic tide model and test it using 11-year observations from 33 bottom pressure stations over the Pacific Ocean, the average Root Mean Square (RMS) deviation of tidal elevation predicted by this model against observation is 7.54 cm. Using a ratio of M2 elevation RMS of ocean tide model EOT11a and its total tidal elevation RMS as a reference, we estimate the total tidal elevation RMS of six purely hydrodynamic models (i.e.,Hallberg Isopycnal Model, OSU Tidal Inversion software-GN ,STORMTIDE model, OSU Tidal Inversion Software-ERB,STM-1B, and HYbrid Coordinate Ocean Model to be 59.93, 51.64, 57.05, 38.56, 86.92, and 53.56 cm, respectively.

Geoffrey Dawson, Remy Vandaele, Andrew Taylor et al.

Artificial Intelligence (AI) Foundation models (FMs), pre-trained on massive unlabelled datasets, have the potential to drastically change AI applications in ocean science, where labelled data are often sparse and expensive to collect. In this work, we describe a new foundation model using the Prithvi-EO Vision Transformer architecture which has been pre-trained to reconstruct data from the Sentinel-3 Ocean and Land Colour Instrument (OLCI). We evaluate the model by fine-tuning on two downstream marine earth observation tasks. We first assess model performance compared to current baseline models used to quantify chlorophyll concentration. We then evaluate the FMs ability to refine remote sensing-based estimates of ocean primary production. Our results demonstrate the utility of self-trained FMs for marine monitoring, in particular for making use of small amounts of high quality labelled data and in capturing detailed spatial patterns of ocean colour whilst matching point observations. We conclude that this new generation of geospatial AI models has the potential to provide more robust, data-driven insights into ocean ecosystems and their role in global climate processes.

Ruoying He, Tianning Wu, Shun Mao et al.

A 30-year high-resolution Northwestern Atlantic Ocean Reanalysis (NAOR) is presented. NAOR spans from January 1993 to December 2022 with a 4 km horizontal resolution and 50 vertical layers. It provides enhanced resolution and expands the spatial and temporal coverage of existing ocean reanalysis in the region. NAOR was conducted using the Regional Ocean Modeling System along with Ensemble Optimal Interpolation data assimilation. Open boundary and surface forcing conditions were obtained from GLORYS global ocean reanalysis and ECMWF ERA5 reanalysis. Multiple sources of satellite and in-situ observations were incorporated through the data assimilation. Additionally, major rivers were accounted for to include freshwater riverine discharge. NAOR was extensively evaluated against available independent observations. Spatio-temporal variations of mesoscale circulation, eddies, and boundary currents are well captured. Compared to GLORYS, NAOR offers a more accurate physical and dynamic baseline of the northwestern Atlantic Ocean, which can be utilized for a range of marine and environmental studies as well as climate impact research.

Lizhen Zhang, Chong Xu, Sai Jiang et al.

Deaths occur during the culture of sea bass, and if timely harvesting is not carried out, it will lead to water pollution and the continued spread of sea bass deaths. Therefore, it is necessary to promptly detect dead fish and take countermeasures. Existing object detection algorithms, when applied to the task of detecting dead sea bass, often suffer from excessive model complexity, high computational cost, and reduced accuracy in the presence of occlusion. To overcome these limitations, this study introduces YOLOv8n-Deadfish, a lightweight and high-precision detection model. First, the homemade sea bass death recognition dataset was expanded to enhance the generalization ability of the neural network. Second, the C2f-faster–EMA (efficient multi-scale attention) convolutional module was designed to replace the C2f module in the backbone network of YOLOv8n, reducing redundant calculations and memory access, thereby more effectively extracting spatial features. Then, a weighted bidirectional feature pyramid network (BiFPN) was introduced to achieve a more thorough integration of deep and shallow features. Finally, in order to compensate for the weak generalization and slow convergence of the CIoU loss function in detection tasks, the Inner-CIoU loss function was used to accelerate bounding box regression and further improve the detection performance of the model. The experimental results show that the YOLOv8n-Deadfish model has an accuracy, recall, and mean precision of 90.0%, 90.4%, and 93.6%, respectively, which is an improvement of 2.0, 1.4, and 1.3 percentage points, respectively, over the original base network YOLOv8n. The number of model parameters and GFLOPs were reduced by 23.3% and 18.5%, respectively, and the detection speed was improved from the original 304.5 FPS to 424.6 FPS. This method can provide a technical basis for the identification of dead sea bass in the process of intelligent aquaculture.

Lu Qiu, Zhiping Xu, Lixiong Lin et al.

With the rapid development of network technology, modern systems are facing increasingly complex security threats, which motivates researchers to continuously explore more advanced intrusion detection systems (IDSs). Even though they work effectively in some situations, the existing IDSs based on machine learning or deep learning still struggle with detection accuracy and generalization. To address these challenges, this study proposes an innovative network intrusion detection algorithm that combines convolutional neural networks (CNNs) and decision trees (DTs) together, named CNN-DT algorithm. In the CNN-DT algorithm, CNN extracts high-level features from data packets first, then the decision tree quickly determines the presence of intrusions based on these high-level features, while providing a clear decision path. Moreover, the study proposes a novel adaptive hybrid pooling mechanism that integrates maximal pooling, average pooling, and global maximal pooling. The hyperparameters of the CNN network are also optimized by actor–critic (AC) deep reinforcement learning algorithm (DRL). The experimental results show that the CNN–decision tree (DT) algorithm optimized by actor–critic (AC) achieves an accuracy of 0.9792 on the KDD dataset, which is 5.63% higher than the unoptimized CNN-DT model.

Feier Chen, Yi Sha, Huaxiao Ji et al.

This study investigates the multifractal characteristics of the tanker freight market from 1998 to 2024. Using multifractal detrended fluctuation analysis (MF-DFA) and multifractal detrending moving average (MF-DMA), we analyze temporal correlations and volatility, revealing subtle differences in multifractal features before and after 2010. We further examine the influence of key external factors—including economic disturbances (the 2008 financial crisis), technological innovations (the 2014 Shale Oil Revolution), supply chain disruptions (the COVID-19 pandemic), and geopolitical uncertainties (the Russia–Ukraine conflict)—on market complexity. Building on this, a predictive framework is introduced, leveraging the Baltic Dirty Tanker Index (BDTI) to forecast Brent oil prices. By integrating multifractal analysis with machine learning models (e.g., XGBoost, LightGBM, and CatBoost), our framework fully exploits the predictability from the freight index to oil prices across the above four major global events. The results demonstrate the potential of combining multifractal analysis with advanced machine learning models to improve forecasting accuracy and provide actionable insights during periods of heightened market volatility. On average, the coefficient of determination (<i>R</i>²) increases by approximately 62.65% to 182.54% for training and 55.20% to 167.62% for testing, while the mean squared error (MSE) reduces by 60.83% to 92.71%. This highlights the effectiveness of multifractal analysis in enhancing model performance, especially in more complex market conditions post-2010.

Jin-Ho Lee, Kyung-Ae Park, Kwang-Seok Moon et al.

Small-scale oil spills can exert substantial ecological impacts on pristine coastal environments, even when the discharged volume is relatively limited. This study investigates a diesel oil spill that occurred on 4 July 2022 along the coast of Jeju Island, Korea, following a fire on moored fishing vessels. Using high-resolution Sentinel-2 optical imagery, we developed a remote sensing-based framework to detect, quantify, and analyze the dispersion of the oil spill. Nonocean pixels, including land, ships, and clouds, were first removed through spectral thresholding. A spectral unmixing algorithm was then applied to extract endmembers representing oil and seawater. The spectral angle mapper method was used to delineate the spatial extent of the spill and a two-beam interference model was employed to estimate oil thickness and total volume. The resulting oil-covered area and volume estimates showed reasonable consistency with reported values. A particularly notable observation was the bifurcation of the oil slick into two distinct branches after exiting the harbor. Hydrodynamic simulations, combined with near-surface wind data, revealed a strong temporal correlation between surface current direction and oil advection, with statistical significance. In addition, bathymetric analysis derived from Sentinel-2 imagery identified two small seamounts near the harbor outlet, which contributed to the divergence of the oil&#x2019;s trajectory. This study demonstrates the utility of high-resolution optical satellite data for detecting thin oil sheens and highlights the combined influence of wind, surface currents, and local bathymetry on oil dispersion dynamics in shallow, environmentally sensitive coastal waters.

Chung-Ru Ho

Our Oceans cover more than 70% of the Earth’s surface, and thus various ocean engineering projects have been undertaken to utilize these vast resources effectively [...]

Dawen Yu, Shunping Ji

Instance segmentation performance in remote sensing images (RSIs) is significantly affected by two issues: how to extract accurate boundaries of objects from remote imaging through the dynamic atmosphere, and how to integrate the mutual information of related object instances scattered over a vast spatial region. In this study, we propose a novel shape guided transformer network (SGTN) to accurately extract objects at the instance level. Inspired by the global contextual modeling capacity of the self-attention mechanism, we propose an effective transformer encoder termed LSwin, which incorporates vertical and horizontal 1-D global self-attention mechanisms to obtain better global-perception capacity for RSIs than the popular local-shifted-window based swin transformer. To achieve accurate instance mask segmentation, we introduce a shape guidance module (SGM) to emphasize the object boundary and shape information. The combination of SGM, which emphasizes the local detail information, and LSwin, which focuses on the global context relationships, achieve excellent RSI instance segmentation. Their effectiveness was validated through comprehensive ablation experiments. Especially, LSwin is proven better than the popular ResNet and swin transformer encoders at the same level of efficiency. Compared to other instance segmentation methods, our SGTN achieves the highest average precision scores on two single-class public datasets (WHU dataset and BITCC dataset) and a multiclass public dataset (NWPU VHR-10 dataset).

Seraj Al Mahmud Mostafa, Jinbo Wang, Benjamin Holt et al.

Ocean eddies play a significant role both on the sea surface and beneath it, contributing to the sustainability of marine life dependent on oceanic behaviors. Therefore, it is crucial to investigate ocean eddies to monitor changes in the Earth, particularly in the oceans, and their impact on climate. This study aims to pinpoint ocean eddies using AWS cloud services, specifically SageMaker. The primary objective is to detect small-scale (<20km) ocean eddies from satellite remote images and assess the feasibility of utilizing SageMaker, which offers tools for deploying AI applications. Moreover, this research not only explores the deployment of cloud-based services for remote sensing of Earth data but also evaluates several YOLO (You Only Look Once) models using single and multi-GPU-based services in the cloud. Furthermore, this study underscores the potential of these services, their limitations, challenges related to deployment and resource management, and their user-riendliness for Earth science projects.

Xiang Wang, Renzhi Wang, Ningzi Hu et al.

The leading operational Global Ocean Forecasting Systems (GOFSs) use physics-driven numerical forecasting models that solve the partial differential equations with expensive computation. Recently, specifically in atmosphere weather forecasting, data-driven models have demonstrated significant potential for speeding up environmental forecasting by orders of magnitude, but there is still no data-driven GOFS that matches the forecasting accuracy of the numerical GOFSs. In this paper, we propose the first data-driven 1/12° resolution global ocean eddy-resolving forecasting model named XiHe, which is established from the 25-year France Mercator Ocean International's daily GLORYS12 reanalysis data. XiHe is a hierarchical transformer-based framework coupled with two special designs. One is the land-ocean mask mechanism for focusing exclusively on the global ocean circulation. The other is the ocean-specific block for effectively capturing both local ocean information and global teleconnection. Extensive experiments are conducted under satellite observations, in situ observations, and the IV-TT Class 4 evaluation framework of the world's leading operational GOFSs from January 2019 to December 2020. The results demonstrate that XiHe achieves stronger forecast performance in all testing variables than existing leading operational numerical GOFSs including Mercator Ocean Physical SYstem (PSY4), Global Ice Ocean Prediction System (GIOPS), BLUElinK OceanMAPS (BLK), and Forecast Ocean Assimilation Model (FOAM). Particularly, the accuracy of ocean current forecasting of XiHe out to 60 days is even better than that of PSY4 in just 10 days. Additionally, XiHe is able to forecast the large-scale circulation and the mesoscale eddies. Furthermore, it can make a 10-day forecast in only 0.35 seconds, which accelerates the forecast speed by thousands of times compared to the traditional numerical GOFSs.

Yixuan Sun, Elizabeth Cucuzzella, Steven Brus et al.

Numerical models of the ocean and ice sheets are crucial for understanding and simulating the impact of greenhouse gases on the global climate. Oceanic processes affect phenomena such as hurricanes, extreme precipitation, and droughts. Ocean models rely on subgrid-scale parameterizations that require calibration and often significantly affect model skill. When model sensitivities to parameters can be computed by using approaches such as automatic differentiation, they can be used for such calibration toward reducing the misfit between model output and data. Because the SOMA model code is challenging to differentiate, we have created neural network-based surrogates for estimating the sensitivity of the ocean model to model parameters. We first generated perturbed parameter ensemble data for an idealized ocean model and trained three surrogate neural network models. The neural surrogates accurately predicted the one-step forward ocean dynamics, of which we then computed the parametric sensitivity.

B.Y. Chinmayi, H. Ramesh

Freshwater resources remain unequally distributed in time and space around the world. Water resource frameworks should be designed, planned, and overseen in order to fully meet current and future social and economic objectives. The difficulties grow as the system gets bigger and more complex, with varying spatial distribution of water and insufficient resources, making water re-distribution more difficult. The current study fills such gaps by evaluating several factors influencing conjunctive management. In the current study, an effort has been made to compile the best data on water use, agricultural practises, socioeconomic status, and so on through field surveys in order to comprehend the reality on the ground. Additionally, investigations are being conducted into the causes and barriers that are most likely to have slowed the implementation of conjunctive use of available water resources. Two comprehensive socioeconomic surveys were conducted using the quantitative research methodology in a river basin in Southern India, and the results clearly show that stakeholders are unaware of the most effective agricultural water management techniques and the rationale behind modern irrigation systems. Over ninety-five percent of the total respondents were farmers, with only five percent having basic knowledge of watershed development and conjunctive use water management. The identified gaps and the inference made in the study are in the context of conjunctive water management of agricultural water. The current work may provide useful information on the baseline scenarios for upcoming agricultural water management plans, as well as a useful tool for achieving significant milestones in the agricultural sector. Furthermore, the prepared questionnaire and the data gathered for the study may also be helpful to decision-makers.

Shi Hua, Moses Oyaro Okello, Jian Zhang

Abstract With the development of green buildings, people pay more attention to the quality of the indoor sound environment. The air sound insulation performance of floors and exterior walls plays a key role in today's green buildings. The thermal performance of the enclosure structure's floor and exterior wall heat transfer resistance is an important factor in reducing building carbon emissions in green buildings. The aim of this paper is to study the efficiency of the acoustic and thermal insulation of a foaming system with porous carbon balls and the combination of different structural ways of construction boards and external walls. The acoustic and thermal parameters of different sound insulation and thermal insulation systems designed with porous carbon sphere foam and inserted into the floors and exterior walls are compared to highlight the optimal structure. The theoretical and experimental tests showed that to improve the sound insulation performance of the floor, a sound insulation system needs to be placed on the surface of the floor in contact with the impact object and inlaid in the vertical gap in contact with the floor and the wall. Furthermore, it has been determined that the surface of the foam particle acoustic ball with micropores has good sound absorption performance. Finally, the high-quality building thermal insulation material with low thermal conductivity in any combination with the floor slabs and the external wall structure improves the thermal insulation performance.

Yuxin Zhu, Peihong Jia, Zhouyao Zhang et al.

Mangrove restoration is recognized as an effective strategy for enhancing the carbon storage capacity of natural ecosystems, advancing toward the “carbon neutrality” goal. The carbon storage effects of ecological restoration efforts remain insufficiently understood as previous studies have focused on carbon storage dynamics in ecosystems, yet the specific impacts of targeted mangrove restoration are less explored. This study utilizes multi-temporal remote sensing data and actual restoration data from Dongzhai Harbor Hainan Island to identify the mangrove wetland coverage and quantify the spatiotemporal evolution of carbon storage under various restoration efforts using the InVEST model. Additionally, we employed the PLUS model to simulate and compare carbon storage potential under multiple development goals. The findings reveal the following: (a) Mangrove restoration significantly increased the area of land with high carbon sink capability, resulting in a regional carbon storage increase of 210,001.68 tons from 2015 to 2021, with 97% of this increase attributable to ecological restoration. (b) Mangrove coverage is crucial for regional carbon storage, with an average of 443 tons of carbon stored per hectare. Decreases in carbon storage occurred mainly during the conversion of mangroves to aquaculture, and forests/agriculture to residential areas. Increases in carbon storage were seen in the reverse transitions. (c) Comparing the scenarios focused solely on mangrove protection with cultivated land protection, the carbon storage in Dongzhai Harbor is projected to reach its maximum by 2045 under the carbon storage priority scenario. Our findings build a scientific foundation for formulating effective mangrove conservation and restoration strategies.

Sanghwan Heo, Weoncheol Koo, MooHyun Kim

Submerged breakwaters can be installed underneath floating structures to reduce the external wave loads acting on the structure. The objective of this study was to establish an optimization analysis framework to determine the corresponding shape and position of the submerged breakwater that can minimize or maximize the external forces acting on the floating structure. A two-dimensional frequency-domain boundary element method (FD-BEM) based on the linear potential theory was developed to perform the hydrodynamic analysis. A metaheuristic algorithm, the advanced particle swarm optimization, was newly coupled to the FD-BEM to perform the optimization analysis. The optimization analysis process was performed by calling FD-BEM for each generation, performing a numerical analysis of the design variables of each particle, and updating the design variables using the collected results. The results of the optimization analysis showed that the height of the submerged breakwater has a significant effect on the surface piercing body and that there is a specific area and position with an optimal value. In this study, the optimal values of the shape and position of a single submerged breakwater were determined and analyzed so that the external force acting on a surface piercing body was minimum or maximum.

Bozhezi Peng, Tao Wang, Yi Zhang et al.

Understanding the spatially varying effect mechanism of intermodal connection on metro ridership helps policymakers develop differentiated interventions to promote metro usage, especially for megacities with multiple city sub-centers and ring roads. Using multiple datasets in Shanghai, this study combines Light Gradient Boosting Machine (LightGBM) with Shapley additive explanations (SHAP) to explore these effects with the consideration of the built environment and metro network topology. Results show that the collective impacts of intermodal connection are positive, not only within the main city but also alongside the main commuting corridors, while negative effects occur in the peripheral area. Specifically, bike sharing trips increase metro ridership within the inner ring of the city, while bus services lower metro usage at stations alongside the elevated ring roads. Parking facilities enable metro usage at city sub-centers, and the small pedestrian catchment area increases metro riders alongside the main commuting corridors. Empirical findings help policymakers understand the effect mechanism of intermodal connection for stations in different regions and prioritize customized planning strategies.