Search Results (126)

Coasts are critical ecological, economic and social interfaces between terrestrial and marine systems. The current upsurge in the acquisition and availability of remote sensing datasets, such as Landsat remote sensing data series, provides new opportunities for analyzing multi-decadal coastal changes and other components of coastal risk. The emergence of machine learning-based techniques represents a new trend that can support large-scale coastal monitoring and modeling using remote sensing big data. This study presents a comprehensive multi-decadal analysis of coastal changes for the period from 1990 to 2024 using Landsat remote sensing data series along the eastern and southern coasts of Peninsular Malaysia. These coastal regions include the states of Kelantan, Terengganu, Pahang, and Johor. An innovative approach combining deep learning-based shoreline extraction with the Digital Shoreline Analysis System (DSAS) was meticulously applied to the Landsat datasets. Two semantic segmentation models, U-Net and DeepLabV3+, were evaluated for automated shoreline delineation from the Landsat imagery, with U-Net demonstrating superior boundary precision and generalizability. The DSAS framework quantified shoreline change metrics—including Net Shoreline Movement (NSM), Shoreline Change Envelope (SCE), and Linear Regression Rate (LRR)—across the states of Kelantan, Terengganu, Pahang, and Johor. The results reveal distinct spatial–temporal patterns: Kelantan exhibited the highest rates of shoreline change with erosion of −64.9 m/year and accretion of up to +47.6 m/year; Terengganu showed a moderated change partly due to recent coastal protection structures; Pahang displayed both significant erosion, particularly south of the Pahang River with rates of over −50 m/year, and accretion near river mouths; Johor’s coastline predominantly exhibited accretion, with NSM values of over +1900 m, linked to extensive land reclamation activities and natural sediment deposition, although local erosion was observed along the west coast. This research highlights emerging erosion hotspots and, in some regions, the impact of engineered coastal interventions, providing critical insights for sustainable coastal zone management in Malaysia’s monsoon-influenced tropical coastal environment. The integrated deep learning and DSAS approach applied to Landsat remote sensing data series provides a scalable and reproducible framework for long-term coastal monitoring and climate adaptation planning around the world. Full article

High-resolution offshore digital elevation models (DEMs) are essential for coastal geomorphology, marine resource management, and disaster prevention. While deep learning-based super-resolution (SR) techniques have become a mainstream solution for enhancing DEMs, they often fail to maintain a balance between large-scale geomorphological structure and fine-scale topographic detail due to limitations in modeling spatial dependency. To overcome this challenge, we propose DEM-Asymmetric multi-scale super-resolution network (DEM-AMSSRN), a novel asymmetric multi-scale super-resolution network tailored for offshore DEM reconstruction. Our method incorporates region-level non-local (RL-NL) modules to capture long-range spatial dependencies and residual multi-scale blocks (RMSBs) to extract hierarchical terrain features. Additionally, a hybrid loss function combining pixel-wise, perceptual, and adversarial losses is introduced to ensure both geometric fidelity and visual realism. Experimental evaluations on U.S. offshore DEM datasets demonstrate that DEM-AMSSRN significantly outperforms existing GAN-based models, reducing RMSE by up to 72.47% (vs. SRGAN) and achieving 53.30 dB PSNR and 0.995056 SSIM. These results highlight its effectiveness in preserving both continental shelf-scale bathymetric patterns and detailed terrain textures. Using this model, we also constructed the USA_OD_2025, a 1/9 arc-second high-resolution offshore DEM for U.S. coastal zones, providing a valuable geospatial foundation for future marine research and engineering. Full article

Coastal waters are sensitive habitats that support high biodiversity and provide essential ecosystem goods. Changes in sedimentation regimes due to land-use and engineering activities in the coastal zone affect biodiversity and these habitats’ ecological value. This study aims to characterize the meiobenthic communities inhabiting the Zwin tidal lagoon, located on the border between Belgium and the Netherlands, and to evaluate to what extent the sedimentological characteristics and the quantity and composition of organic matter influence the composition and distribution of meiofauna. The meiobenthic community showed traits of a well-established population dominated by nematodes, followed by copepods + nauplii. Notably, meiofauna rapidly colonized the area after its opening to the sea in February 2019 (two years before sampling), showing that even very weak tidal currents were sufficient to suspend and transport these animals to the new environment. Our results suggest that the Zwin lagoon is a productive system with high food quality (i.e., PRT/CHO ≥ 1), predominantly of marine origin. Major structural differences in communities were related to the sedimentary environments at the investigated stations and estimations of the quantity of food. The present findings confirm that sedimentary dynamics and depositional processes, through their influence on sediment properties (e.g., grain size) and organic matter’s quantity and composition, shape meiofaunal communities and their vertical and horizontal distributions. Full article

This study addresses engineering challenges associated with sandy residual deposits in the coastal zone of Quanzhou, China, characterized by high void ratios (e > 0.8), low cohesion (c < 10 kPa), and strong liquefaction tendencies induced by marine dynamic forces. Focusing on the beach sands of Shenhu Bay and Qingshan Bay, 123 in situ dynamic penetration tests and 12 laboratory physical–mechanical tests (including water content, particle gradation, relative density, and triaxial shear strength) were conducted. The correlations between the physical and mechanical properties of these coastal sandy soils and their foundation bearing capacity were systematically analyzed. Results reveal that the sands, predominantly medium-to-fine grains with 8–15% biogenic debris, are generally in a loose-to-medium dense state (relative density ~34%), with negligible cohesion. Shear strength depends primarily on the internal friction angle (28.89–37.43°). Correlation analyses show that water content (17.8–31.92%) and particle gradation parameters (uniformity coefficient C_u and curvature coefficient C_c) significantly influence bearing capacity, with bearing capacity increasing by 12.15% per 14.12% rise in water content and 35% per 0.518 increase in C_c. An improved foundation bearing capacity model based on the Prandtl–Reissner theory is proposed by integrating particle gradation and water content, tailored for beach foundations in Quanzhou. Model validation demonstrates an average error of approximately 15%, outperforming traditional models. These findings provide valuable theoretical support for assessing foundation stability in building construction projects in Quanzhou and similar coastal regions. Full article

Shallow foundations are widely used in both terrestrial and marine environments, supporting critical structures such as buildings, offshore wind turbines, subsea platforms, and infrastructure in coastal zones, including piers, seawalls, and coastal defense systems. Accurately determining the soil bearing capacity for shallow foundations presents a significant challenge, as it necessitates considerable resources in terms of materials and testing equipment, as well as a substantial amount of time to perform the necessary evaluations. Consequently, our research was designed to approximate the forecasting of soil bearing capacity for shallow foundations using machine learning algorithms. In our research, four ensemble machine learning algorithms were employed for the prediction process, benefiting from previous experimental tests. Those four models were AdaBoost, Extreme Gradient Boosting (XGBoost), Gradient Boosting Regression Trees (GBRTs), and Light Gradient Boosting Machine (LightGBM). To enhance the model’s efficacy and identify the optimal hyperparameters, grid search was conducted in conjunction with k-fold cross-validation for each model. The models were evaluated using the R² value, MAE, and RMSE. After evaluation, the R² values were between 0.817 and 0.849, where the GBRT model predicted more accurately than other models in training, testing, and combined datasets. Moreover, variable importance was analyzed to check which parameter is more important. Foundation width was the most important parameter affecting the shallow foundation bearing capacity. The findings obtained from the refined machine learning approach were compared with the well-known empirical and modern machine learning equations. In the end, the study designed a web application that helps geotechnical engineers from all over the world determine the ultimate bearing capacity of shallow foundations. Full article

Drag embedment anchors (DEAs) play a vital role in maintaining the stability and safety of offshore structures, including floating wind turbines, oil rigs, and marine renewable energy systems. Accurate prediction of anchor performance is essential for optimizing mooring system designs, reducing costs, and minimizing risks in challenging marine environments. By leveraging advanced machine learning techniques, this research provides innovative solutions to longstanding challenges in geotechnical engineering, paving the way for more efficient and reliable offshore operations. The findings contribute significantly to developing sustainable marine infrastructure while addressing the growing global demand for renewable energy solutions in coastal and deep-water environments. This current study evaluated tree-based machine learning algorithms, e.g., decision tree regression (DTR) and random forest regression (RFR), to predict the holding capacity and efficiency of DEAs in sand seabed. To train and validate the results of machine learning models, the K-fold cross-validation method, with K = 5, was utilized. Eleven geotechnical and geometric parameters, including sand friction angle (φ), fluke-shank angle (α), and anchor dimensions, were analyzed using 23 model configurations. Results demonstrated that RFR outperformed DTR, achieving the highest accuracy for capacity prediction (R = 0.985, RMSE = 344.577 KN) and for efficiency (R = 0.977, RMSE = 0.821 KN). Key findings revealed that soil strength dominated capacity, while fluke-shank angle critically influenced efficiency. Single-parameter models failed to capture complex soil-anchor interactions, underscoring the necessity of multivariate analysis. The ensemble approach of RFR provided superior generalization across diverse seabed conditions, maintaining errors within ±10% for capacity and ±5% for efficiency. Full article

Growing concern over anthropogenic underwater noise, highlighted by initiatives like the Marine Strategy Framework Directive (MSFD) and its Technical Group on Underwater Noise (TG Noise), emphasizes regions like the Western Black Sea, where increasing activities threaten marine habitats. This region is experiencing rapid growth in maritime traffic and resource exploitation, which is intensifying concerns over the noise impacts on its unique marine habitats. While machine learning offers promising solutions, a research gap persists in comprehensively evaluating diverse ML models within an integrated framework for complex underwater acoustic data, particularly concerning real-world data limitations like class imbalance. This paper addresses this by presenting a multi-faceted framework using passive acoustic monitoring (PAM) data from fixed locations (50–100 m depth). Acoustic data are processed using advanced signal processing (broadband Sound Pressure Level (SPL), Power Spectral Density (PSD)) for feature extraction (Mel-spectrograms for deep learning; PSD statistical moments for classical/unsupervised ML). The framework evaluates Convolutional Neural Networks (CNNs), Random Forest, and Support Vector Machines (SVMs) for noise event classification, alongside Gaussian Mixture Models (GMMs) for anomaly detection. Our results demonstrate that the CNN achieved the highest classification accuracy of 0.9359, significantly outperforming Random Forest (0.8494) and SVM (0.8397) on the test dataset. These findings emphasize the capability of deep learning in automatically extracting discriminative features, highlighting its potential for enhanced automated underwater acoustic monitoring. Full article

Excess-sulfate phosphogypsum slag cement (EPSC), offering the potential for large-scale phosphogypsum (PG) utilization, has drawn significant attention. However, its susceptibility to salt erosion in marine/saline environments remains unquantified, hindering engineering applications. This study, therefore, systematically investigates the effect of various salts (NaCl, MgCl₂, KCl, and Na₂SO₄) at different concentrations (0.5–1.5%) on the hydration mechanism and performance of EPSC using rheometry, strength tests, and microstructural characterization (XRD/SEM-EDS). The findings reveal that EPSC exhibits low initial yield stress and plastic viscosity, both of which increase over time. The addition of Na⁺, Cl⁻, and SO₄²⁻ ions promotes hydration and flocculent structure formation in the EPSC paste, thereby enhancing the yield stress and plastic viscosity. In contrast, Mg²⁺ and K⁺ ions inhibit the hydration reaction, although Mg²⁺ temporarily increases the plastic viscosity by forming Mg(OH)₂ during the initial stage of the reaction. Both Na₂SO₄ and NaCl improve mechanical properties when their concentrations are within the 0.5–1.0% range; however, excessive amounts (>1%) negatively impact these properties. Significantly, adding 0.5% NaCl significantly improves the mechanical properties of EPSC, achieving a 28-day compressive strength of 51.06 MPa—a 9.5% increase compared to the control group. XRD and SEM-EDX analyses reveal that NaCl enhances pore structure via Friedel’s salt formation, while Na₂SO₄ promotes the early nucleation of ettringite. However, excessive ettringite formation in the later stages of the hydration reaction due to Na₂SO₄ may negatively affect compressive strength due to the inherent abundance of SO₄²⁻ in the EPSC system. Therefore, attention should be paid to the effect of excessive SO₄²⁻ on the system. These results establish salt-type/dosage thresholds for EPSC design, enabling its rational use in coastal infrastructure where salt resistance is critical. Full article

The natural and biological processes of organisms offer significant potential for the removal and remediation of environmental contaminants including organic pollutants such as persistent organic pollutants (POPs) like polychlorinated biphenyls (PCBs), pesticides, herbicides, industrial chemicals, and pharmaceuticals. Biotechnology provides various approaches to detoxify or remove these pollutants from ecosystems through the use of microorganisms and plants. This review explores the application of biotechnology for the remediation of organic pollutants in coastal marine ecosystems. A thorough analysis of the existing literature highlights bioremediation methods, such as biostimulation, bioaugmentation, and bioattenuation, and phytoremediation methods, like phytoextraction, phytostabilization, phytovolatilization, phytodegradaton, and phytofiltration. as the most widely used techniques in biotechnology. While bioremediation has advanced substantially in fields such as electrochemistry, genetic engineering, and nanotechnology, there is still limited research on the compatibility and application of these technologies in phytoremediation. This paper therefore aims to examine biotechnological methods for tackling organic pollutants in coastal marine environments with an emphasis on the need for further research on enhancing phytoremediation through microbial inoculation and nanomaterial-assisted uptake. Full article

Reliable coastal and offshore sediment transport data is a requirement for many engineering and environmental projects including port and harbour design, dredging and beach nourishment, sea shoreline protection, inland navigation, marine pollution monitoring, benthic habitat mapping, and offshore renewable energy (ORE). Novel sediment transport numerical modelling approaches allow engineers and scientists to investigate the physical interactions involved in these projects both in the near and far field. However, a lack of confidence in simulated sediment transport results is evident in many coastal and offshore studies, mainly due to limited access to validation datasets. This study addresses the need for cost-effective sediment validation datasets by investigating the applicability of four new suspended load validation techniques to a 2D model of the south-western Irish Sea. This involves integrating an estimated spatial time series of suspended solids concentration (${SSC}_{solids}$) derived from acoustic Doppler current profiler (ADCP) acoustic backscatter with several in situ water sample-based ${SSC}_{solids}$ datasets. Ultimately, a robust spatial time series of ADCP-based ${SSC}_{solids}$ was successfully calculated in this offshore, tidally dominated setting, where the correlation coefficient between estimated ${SSC}_{solids}$ and directly measured ${SSC}_{solids}$ is 0.87. Three out of the four assessed validation techniques are deemed advantageous in developing an accurate 2D suspended sediment transport model given the assumptions of the depth-integrated approach. These recommended techniques include (i) the validation of 2D modelled suspended sediment concentration (${SSC}_{sediment}$) using water sample-based ${SSC}_{solids}$, (ii) the validation of the flood–ebb characteristics of 2D modelled suspended load transport and ${SSC}_{sediment}$ using ADCP-based datasets, and (iii) the validation of the 2D modelled peak ${SSC}_{sediment}$ over a spring–neap cycle using the ADCP-based ${SSC}_{solids}$. Overall, the multi-disciplinary method of collecting in situ metocean and sediment dynamic data via acoustic instruments (ADCPs) is a cost-effective in situ data collection method for future ORE developments and other engineering and scientific projects. Full article

Marine soft clay is characterized by a high water content and low strength, exhibiting pronounced creep deformation under long-term loading that threatens the serviceability and durability of coastal infrastructure. Accordingly, this study develops a creep constitutive model that combines elastic, plastic, and viscous effects and quantitatively evaluates time-dependent deformation under varying water contents and stress levels to provide reliable prediction tools for tunnel, excavation, and pile-foundation design. Cyclic creep tests were carried out on reconstituted marine soft clay with water contents of 40–60% and stress ratios of 0.4–1.2 using a pneumatic, fully digital, closed-loop triaxial apparatus. A “nonlinear spring–Bingham slider–dual viscous dashpot in parallel with a standard Kelvin dashpot” element assembly was proposed, and the complete stress–strain relationship was derived. Experimental data were fitted with Python to generate a creep-strain polynomial and verify the model accuracy. The predicted–measured creep difference remained within 10%, and the surface-fit coefficient of determination reached R² = 0.97, enabling rapid estimation of deformation for the given stress and time conditions. The findings offer an effective method for the precise long-term settlement prediction of marine soft clay and significantly enhance the reliability of the deformation assessments in coastal civil-engineering projects. Full article

Seawater Coral Aggregate Concrete (SCAC), made using coral aggregates from marine environments, is gaining attention as a promising material for marine and coastal engineering applications. This study investigates the dynamic tensile behavior of SCAC under both dry and saturated conditions, with an emphasis on the effects of free water on its mechanical properties. The dynamic Brazilian splitting (DBS) tests were conducted to evaluate the dynamic tensile strength, strain rate sensitivity, failure modes, and fracture morphology of SCAC specimens. The results show that saturated SCAC specimens exhibit a reduction in dynamic tensile strength compared to dry specimens, with this difference becoming more pronounced at higher strain rates. The maximum reduction can be observed to be 17.87%. Additionally, saturated SCAC specimens demonstrate greater strain rate sensitivity than dry specimens, which highlights the significant influence of moisture on the material’s mechanical behavior. The failure modes of SCAC were found to be less severe under saturated conditions, suggesting that moisture suppresses crack propagation to some extent, thereby reducing brittleness. Numerical simulations based on the finite element analysis were conducted to simulate the dynamic tensile response; the comparison of numerical and experimental data indicates that adjusting material model parameters effectively simulates the behavior of saturated SCAC. Full article

The resource utilization of marine-dredged sediment is considered a sustainable approach to its disposal. This paper investigates the preparation of non-sintered ceramsites from marine-dredged sediments and CSA cement via cold-bonded pelletization. The study examines the effects of various preparation conditions on the engineering properties, phase compositions and microstructures of non-sintered ceramsites. The results indicate that preparation conditions significantly influence the particle size distribution of non-sintered ceramsites. The early-strength development of non-sintered ceramsites prepared from CSA cement is remarkable, with the PCS achieving approximately 60% and 80% of the 28-day strength within 3 days and 7 days, respectively—a marked contrast to OPC. Response surface methodology analysis reveals significant interaction effects between the disc rotation angle, rotational speed, and duration of rotation on the PCS of non-sintered ceramsites. The open-ended porosity of non-sintered ceramsites exhibits greater sensitivity to changes in preparation parameters compared to closed-ended porosity and total porosity. The preparation conditions have negligible impact on the hydration process of CSA cement in non-sintered ceramsites. For both ellipsoidal and plate-like marine-dredged soil particles, ettringite and the AH₃ phase provide effective pore-filling and binding effects in the microstructures of non-sintered ceramsites. These findings imply that low-carbon utilization of marine-dredged sediments through the preparation of non-sintered ceramsites offers a nature-based solution for sustainable management in coastal systems. Full article

Quaternary climate has been characterized by pronounced glacial–interglacial cycles, with eustatic sea-level fluctuations directly controlling coastal sedimentary environments. The Yellow River Delta, situated on the southwestern coast of Bohai Bay, bears a distinct stratigraphic imprint of marine–terrestrial environmental transitions. However, critical knowledge gaps persist in reconstructing an integrated continental–marine stratigraphic framework. This study focuses on the nearshore core CB2302, integrating sediment lithology, grain size, foraminiferal assemblages, and geochemical proxies to establish a regional stratigraphic chronology since MIS5. Three depositional units (DU1–DU3) and 12 sedimentary subunits (C1–C12) were identified based on grain-size distributions, geochemical signatures, hydrodynamic, and microfossil assemblages. Integration of AMS ¹⁴C dating and sequence stratigraphic analysis establishes a post-MIS 5 stratigraphic framework for the northern Yellow River Delta, revealing sedimentary responses to three transgressive–regressive cycles (MIS 5e, 5c, and 5a) and confirming widespread terrestrial deposition during MIS 4–2, with no detectable marine influence in MIS 3 strata. Furthermore, correlation with representative cores across the Yellow–Bohai Sea coastal system elucidates a unified model of shoreline migration patterns driven by post-MIS5 sea-level oscillations. These findings advance the understanding of Quaternary sediment–landscape interactions in deltaic systems and provide critical stratigraphic benchmarks for petroleum exploration and coastal engineering in active depositional basins. Full article

High-resolution multispectral remote sensing imagery is widely used in critical fields such as coastal zone management and marine engineering. However, obtaining such images at a low cost remains a significant challenge. To address this issue, we propose the MRSRGAN method (multi-scale residual super-resolution generative adversarial network). The method leverages Sentinel-2 and GF-2 imagery, selecting nine typical land cover types in coastal zones, and constructs a small sample dataset containing 5210 images. MRSRGAN extracts the differential features between high-resolution (HR) and low-resolution (LR) images to generate super-resolution images. In our MRSRGAN approach, we design three key modules: the fusion attention-enhanced residual module (FAERM), multi-scale attention fusion (MSAF), and multi-scale feature extraction (MSFE). These modules mitigate gradient vanishing and extract image features at different scales to enhance super-resolution reconstruction. We conducted experiments to verify their effectiveness. The results demonstrate that our approach reduces the Learned Perceptual Image Patch Similarity (LPIPS) by 14.34% and improves the Structural Similarity Index (SSIM) by 11.85%. It effectively improves the issue where the large-scale span of ground objects in remote sensing images makes single-scale convolution insufficient for capturing multi-scale detailed features, thereby improving the restoration effect of image details and significantly enhancing the sharpness of ground object edges. Full article