Surf during typhoon events poses severe threats to coastal infrastructure and public safety. Traditional monitoring approaches, including in situ sensors and numerical simulations, face inherent limitations in capturing surf impacts—sensors are constrained by point-based measurements, while simulations require intensive computational resources for real-time monitoring. Video-based monitoring offers promising potential for continuous surf observation, yet the development of deep learning models for surf detection remains underexplored, primarily due to the lack of high-quality training datasets from typhoon events. To bridge this gap, we propose a lightweight YOLO (You Only Look Once) based framework for real-time surf detection. A novel dataset of 2855 labeled images with surf annotations, collected from five typhoon events at the Chongwu Tide Gauge Station, captures diverse scenarios such as daytime, nighttime, and extreme weather conditions. The proposed YOLOv6n model achieved 99.3% $mA{P}_{50}$ at 161.8 FPS, outperforming both other YOLO variants and traditional two-stage detectors in accuracy and computational efficiency. Scaling analysis further revealed that YOLO models with 2–5 M parameters provide an optimal trade-off between accuracy and computational efficiency. These findings demonstrate the effectiveness of YOLO-based video monitoring systems for real-time surf detection, offering a practical and reliable solution for coastal hazard monitoring under extreme weather conditions.

Detecting rip currents from satellite imagery offers valuable information for the characterization and assessment of this coastal hazard. While recent advances in deep learning have enabled automatic detection from close-view beach images, the broader geospatial context available in far-view satellite imagery has not yet been fully exploited. The main challenge lies in identifying rips as small objects within large and visually complex scenes that include both beach and non-beach areas. To address this, we proposed a detection pipeline which partitions high-resolution satellite images into small regions on which rip currents are detected using a deep learning object detection model that merges the results. The merged results are processed by applying a deep learning classification model to filter out non-beach scenes, followed by applying the detection model on augmented images to remove spurious detection. The proposed pipeline achieved an overall accuracy of 98.4%, a recall of 0.890, a precision of 0.633, and an F2 score of 0.823 on the testing dataset, demonstrating its effectiveness in locating rip currents within complex coastal scenes and its potential applicability to other regions. In addition, a new rip image dataset containing far-view satellite imagery was constructed. With the new dataset, we demonstrated a potential application of the proposed method in characterizing rip occurrences and found that rip currents tended to occur at open beaches under moderate-energy, onshore-directed waves conditions. Overall, the proposed pipeline, unlike existing near-real-time rip current monitoring systems, provides a high-accuracy offline analysis tool for rip current assessment using satellite imagery. Along with the new dataset introduced in this work, it can represent a valuable step towards expanding available resources for improving automated detection methods and rip current research.

The SCHISM model is widely used for ocean numerical simulations, but its computational efficiency is constrained by the substantial resources it requires. To enhance its performance, this study develops GPU–SCHISM, a GPU-accelerated parallel version of SCHISM using the CUDA Fortran framework, and this study evaluates its acceleration performance on a single GPU-enabled node. The research results demonstrate that the GPU–SCHISM model achieves computational acceleration while maintaining high simulation accuracy. For small-scale classical experiments, a single GPU improves the efficiency of the Jacobi solver—identified as a performance hotspot—by 3.06 times and accelerates the overall model by 1.18 times. However, increasing the number of GPUs reduces the computational workload per GPU, which hinders further acceleration improvements. The GPU is particularly effective for performing higher-resolution calculations, leveraging its computational power. For large-scale experiments with 2,560,000 grid points, the GPU speedup ratio is 35.13; however, CPU has more advantages in small-scale calculations. Moreover, a comparison between CUDA and OpenACC-based GPU acceleration shows that CUDA outperforms OpenACC under all experimental conditions. This study marks the first successful GPU acceleration of the SCHISM model within the CUDA Fortran framework, laying a preliminary foundation for lightweight GPU-accelerated parallel processing in ocean numerical simulations.

Rip currents at featureless beaches (i.e., beaches lacking sandbars or channels) are often hydrodynamically controlled, exhibiting intermittent and unpredictable behaviors that pose significant risks to recreational beach users. This study assessed occurrences of rip currents under a range of idealized morphology configurations and hydrodynamic wave forcing parameters using a wave-resolving Boussinesq-type model. Numerical experiments revealed that rip currents with durations on the time scale of 10 min are generated in the forms of vortex pairs, intensified eddies, mega-rips, and eddies shedding from longshore currents. In general, the key conditions that promote rip current formation at featureless beaches include shoreline curvature, headlands, moderately mild beach slopes (e.g., 0.02–0.03), normal or near-normal wave incidence, and large wave heights. Most importantly, this study highlights inherent uncertainties in rip current occurrences, particularly under conditions usually perceived as low risk: low wave heights, short wave periods, oblique wave incidence, and straight shorelines. These conditions can lead to transient rip currents and pose an unexpected hazard that coastal communities should be aware of.

Ocean winds and waves play a vital role in maritime navigation safety, offshore operations, and coastal zone dynamics. Although both factors have been widely studied individually, the joint characterization of wind and wave events remains limited in the North Indian Ocean. This study, utilizing ERA5 reanalysis data from 1980 to 2022, statistically analyzed the distribution and variation patterns of both wind speed and significant wave height, investigating the occurrence, affected area proportion, frequency, and intensity of SBLWEs. To understand the cause of Strong Breeze and Large Wave Events (SBLWEs), their connections with other phenomena, such as tropical cyclones, were also explored. The results show that regions with strong breezes and large waves are mainly concentrated in the central and western Arabian Sea near Africa and the central and western Bay of Bengal. Monthly averages indicate that wind and wave intensity are much higher during the summer monsoon than in other seasons, with high intensity, probability, and extensive affected areas of SBLWEs. The occurrence probability of SBLWEs is highest in the central and western Arabian Sea (up to ~40%), and the highest probability in the Bay of Bengal is about 20% near the eastern coast of Sri Lanka. The peak period of SBLWEs occurs from June to August, with the largest affected area in July, reaching almost 25%. Over the past 40 years, the number of SBLWEs has shown an increasing trend, with an average of 0.7 events annually. The intensity distribution of SBLWEs resembles that of wind speed and wave height, with the highest intensity areas concentrated in the Bay of Bengal, affected by tropical cyclones. This study can serve as a scientific reference for maritime route planning and offshore operations, helping to reduce the negative impacts of large wind and wave events and enhance navigation safety.