Search

This study summarises the scenario of maritime traffic anomalies, like the increased congestion and U-turn of ships caused by the ship grounding in the Suez Canal in March 2021. Here, satellite automatic identification system based ship trajectories, and Sentinel-1 and Sentinel-2 images based ship positions are analysed after subdividing the study area into seas, lakes and canals. The results show that the blockage affected the maritime traffic for more than three weeks, waiting ship numbers increased from 5 to 122, and daily one to three ships made a U-turn between 23 and 31 March in the Gulf of Suez. Ship density also increased to more than double in Bitter Lakes with a minimum waiting time of 7 days. Hence, to avoid such prolonged waiting of ships, we propose a warning method based on the sharp speed decrease rate, U-turn and congestion.

Illegal fishing has been a serious threat to the conservation of seafood resources and provoked the importance of marine surveillance. There are several types of fishing vessel monitoring systems operated by Republic of Korea, for example, Vessel Monitoring System(VMS), Automatic Identification System (AIS), V-Pass and VHF-DSC. However, those methods are not adaptable directly to fishing activity monitoring. The limitation requires more human resources to determine fishing status. Thus, this study proposes a method of estimating fishing activity from V-Pass, fishing vessel position reporting system, using Hidden Markov Model (HMM). HMM is a model to determine status through probability distribution for a sequence of time-series data. First of all, fishing activity status was labeled on V-Pass data. The distribution of speed on fishing activity was computed from the labeled data and HMM was constructed from the data obtained at Socheongcho Ocean Research Station (SORS). The model was first applied to the data of SORS for a test, and then Busan for validation. The model showed 99.4% and 89.6% as test and validation accuracy, respectively. It is concluded that the HMM can be applicable to predict a fishing activity from vessel tracks.

The global surface temperature has risen critically over the past century and according to the IPCC Fifth Assessment Report 2014, existing risks in natural and human systems will worsen. Coastal erosion is mostly caused by climate change and among all the coastal areas at risk, Benin, which is part of the Gulf of Guinea, has been ranked very highly as a vulnerable region. Therefore, in this review, we focus on the evolution of coastline change in Cotonou of Benin, summarizing its resultant impacts and applied measures around the coast area by reviewing previous studies. Signs of coastal erosion in Cotonou appeared in 1963. After 39 years, the east shoreline of Cotonou has retreated by 885 m, resulting in the disappearance of more than 800 houses. To solve this problem, Benin authorities built seven groynes in 2013, and have increased the number of the structure as a way to interrupt water flow and limit the movement of sediment. Over the region, shorelines appeared preserved accordingly. In contrast, areas located further east, where groynes were not installed, have suffered from intensive erosion at a rate of 49 m/yr. In the future, as a next step, the effectiveness of groynes should be studied with local and broader perspectives.

The amount of data in the maritime domain is rapidly increasing due to the increase in devices that can collect marine information, such as sensors, buoys, ships, and satellites. Maritime data is growing at an unprecedented rate, with terabytes of marine data being collected every month and petabytes of data already being made public. Heterogeneous marine data collected through various devices can be used in various fields such as environmental protection, defect prediction, transportation route optimization, and energy efficiency. However, it is difficult to manage vessel related data due to high heterogeneity of such marine big data. Additionally, due to the high heterogeneity of these data sources and some of the challenges associated with big data, such applications are still underdeveloped and fragmented. In this paper, we propose the Vessel Data Lakehouse architecture consisting of the Vessel Data Lake layer that can handle marine big data, the Vessel Data Warehouse layer that supports marine big data processing and AI, and the Vessel Application Services layer that supports marine application services. Our proposed a Vessel Data Lakehouse that can efficiently manage heterogeneous vessel related data. It can be integrated and managed at low cost by structuring various types of heterogeneous data using an open source-based big data framework. In addition, various types of vessel big data stored in the Data Lakehouse can be directly utilized in various types of vessel analysis services. In this paper, we present an actual use case of a vessel analysis service in a Vessel Data Lakehouse by using AIS data in Busan area.

In this letter, a novel theory is proposed to measure the velocity vector of moving targets such as ocean currents by multiaperture along-track interferometric synthetic aperture radar (MA-ATI SAR), utilizing the conventional dual-antenna ATI SAR data. In this system, the range component of the velocity vector is first computed with the conventional ATI SAR algorithm by correlating the two sets of complex images produced through the fore and aft antennas. For estimating the direction of the velocity vector, multilook/sublook processing is applied to two sets of range-compressed azimuth raw data. Now, there are four sets of complex subimages, two of which are forward-looking and the others are backward-looking. Then, from these subimage pairs, the two sublook interferograms of the corresponding directions are produced. The direction of the moving targets can be estimated either from the forward- and backward-looking azimuth velocity components, or directly from the interferometric phases. With this direction and the range velocity component, the velocity vectors of ocean currents and also moving hard targets on land and sea can be estimated.

Ship type classification of synthetic aperture radar imagery with convolution neural network (CNN) has been faced with insufficient labeled datasets, unoptimized and noised polarization images that can deteriorate a classification performance. Meanwhile, numerous labeled text information for ships, such as length and breadth, can be easily obtained from various sources and can be utilized in a classification with k-nearest neighbor (KNN). This study proposes a method to improve the efficiency of ship type classification from Sentinel-1 dual-polarization data with 10 m pixel spacing using both CNN and KNN models. In the first stage, Sentinel-1 intensity images centered on ship positions were used in a rectangular shape to apply an image processing procedure such as head-up, padding and image augmentation. The process increased the accuracy by 33.0% and 31.7% for VH (vertical transmit and horizontal receive) and VV (vertical transmit and vertical receive) polarization compared to the CNN-based classification with original ship images, respectively. In the second step, a combined method of CNN and KNN was compared with a CNN-alone case. The f1-score of CNN alone was up to 85.0%, whereas the combination method showed up to 94.3%, which was a 9.3% increase. In the future, more details on an optimization method will be investigated through field experiments of ship classification.

This paper presents a technique for tracking of oil slicks movement using synthetic aperture radar (SAR) and external force data with optimal coefficients. The detected oil from the SAR image is used as input data for tracking model, and wind and tidal current data are used as external forces to determine the displacement of oil slick. Forward and backward trackings were performed using a set of 4 SAR images observed at the time of the Hebei Spirit accident in 2007. The movement vectors are calculated using wind and tidal current with various coefficients. All tracking results show more than 56% accuracy. The new linear equations were calculated using coefficient values with the highest accuracy and velocity values of wind and tidal current. The modified equations were used to back-track from the satellite observation time to the accident occurrence time. The simulation results shows that most of the particles of the spread oil traced back around the point of the accident with little exceptions to some particles which shifted more than the oil spill. This is because the spill time of the particles are different from each other. Thus, the proposed method will contribute to the quick response activities and the estimation of location for the source of oil pollution.

This study proposes an approaching method of identifying sea fog by using Geostationary Ocean Color Imager (GOCI) data through applying a Convolution Neural Network Transfer Learning (CNN-TL) model. In this study, VGG19 and ResNet50, pre-trained CNN models, are used for their high identification performance. The training and testing datasets were extracted from GOCI images for the area of coastal regions of the Korean Peninsula for six days in March 2015. With varying band combinations and changing whether Transfer Learning (TL) is applied, identification experiments were executed. TL enhanced the performance of the two models. Training data of CNN-TL showed up to 96.3% accuracy in matching, both with VGG19 and ResNet50, identically. Thus, it is revealed that CNN-TL is effective for the detection of sea fog from GOCI imagery.

Hong, D.-B.; Bae, J.-J., and Yang, C.-S., 2018. Automatic mapping technique of sea ice in the coastal waters of the Arctic Ocean using Sentinel-1 data. In: Shim, J.-S.; Chun, I., and Lim, H.S. (eds.), Proceedings from the International Coastal Symposium (ICS) 2018 (Busan, Republic of Korea). Journal of Coastal Research, Special Issue No. 85, pp. 556–560. Coconut Creek (Florida), ISSN 0749-0208.The sea ice information such as ice extent, area, concentration, and thickness has been widely used for analyses of sea level, weather, and climate changes in the Polar Regions. Passive microwave sensing of sea ice traditionally has been applied to the Arctic Ocean for a shipping route support in spite of its low-spatial resolution. C-band Sentinel-1 (constellation of two satellites, Sentinel-1A and Sentinel-1B) synthetic aperture radar (SAR) is considered as one of the effective satellites because it provides an improvement in revisit time, and offers higher resolution and dual polarization (HH and HV). In this study, the Sentinel-1 sea ice mapping system was developed to acquire data automatically for the region of interest in the Arctic coastal region and to map sea ice areas extracted by using the sea ice discrimination algorithm. The system including a data acquisition process can make a sea ice product in 13 minutes. To intuitively understand the distribution of sea ice for safe navigation in coastal waters, the result can be visualized in a KML file that facilitates interfacing with other systems.

Yang, C.-S.; Kim, K.O.; Lim, H.S.; Kim C.-H.; Kim M.-W., and Hong, D.-B., 2018. Voyage environmental information system (VEIS) for safe navigation support in the coastal waters of the Arctic Ocean. In: Shim, J.-S.; Chun, I., and Lim, H.S. (eds.), Proceedings from the International Coastal Symposium (ICS) 2018 (Busan, Republic of Korea). Journal of Coastal Research, Special Issue No. 85, pp. 561–565. Coconut Creek (Florida), ISSN 0749-0208.The usage of the Northern Sea Route (NSR) in the Arctic Ocean has increased much over the years. For the navigation safety in the polar areas, the Polar Code entered into force on January 1, 2017 by International Maritime Organization (IMO). Korea Institute of Ocean Science & Technology (KIOST) has developed the Arctic Voyage Environmental Information System (VEIS) for sea ice, ocean, wave and weather parameters with a 2.5 km grid spacing on a polar stereographic north projection. Satellite-based sea ice concentration (SIC) includes three kinds of products (AL2, A25, and AM1). AL2 is produced over 5 times a day using the dynamic composite technique based on the SIC Level 2 data acquired from Advanced Microwave Scanning Radiometer 2 (AMSR2). The composite (A25) of AL2 and AMSR2 Level 3 data is also generated once a day to serve SIC less than 15%. AM1 is the product of A25 merged with sea ice extent data from Moderate Resolution Imaging Spectroradiometer (MODIS) of 1 km resolution. The short-term prediction data for wave and weather were processed from NCEP, and the data for ocean and sea ice were from Mercator, MetOffice and MetNo through E.U. Copernicus Marine Service Information. The model-based short-term SIC products were rescaled using the A25 data. The mid-term SIC and sea ice thickness (SIT) prediction (one-month) system was developed using a statistical method with 26-year re-analysis volume and a short-term predicted sea ice data.

In this study, hourly shift of green tide (GT) in the Yellow Sea (YS) during summer of 2015 and 2016 is investigated using Geostationary Ocean Color Imager-based normalized difference vegetation in...

This letter shows the phenomena of Brewster angle damping and its implication observed in the synthetic aperture radar (SAR) images of concrete constructions, such as a bridge and seawalls over the sea. The Fresnel reflection coefficient of concrete material is close to zero at the Brewster angle for X-band V-polarization microwave. The TerraSAR-X images of Tokyo Bay, Japan, at small incidence angles (20.1°–21.4°) showed strong double-bounce reflection between the sea surface and coastal structure with HH-polarization, whereas very little radar backscatter was observed with VV-polarization. The same little radar backscatter was seen in the images of concrete walls on ground and swamp areas covered with reeds. This effect is illustrated with HH/VV intensity and phase difference images, and ground survey data; its implication is also suggested for a better understanding of polarimetric SAR images.

Land masking of Synthetic Aperture Radar (SAR) images is generally accomplished by applying either archived shoreline databases or image segmentation. However, those methods cannot be solely applied to geographical areas complicated with many small islands and exposed rocks. Therefore, we have proposed a new procedure where Sobel edge extraction is applied to detect the edges of all objects from KOMPSAT-5 X-band SAR images, followed by a merging process with the edges from the land objects based on Electronic Navigational Chart (ENC) coastlines. Using the land mask data, geometrically corrected SAR images were masked before applying a ship detection algorithm. This land masking procedure was applied to several images covering different areas of the Korean Peninsula. The results show that land targets such as newly constructed and natural objects were also masked, and thus did not create false alarms during ship detection. Therefore, this method can be used to assist precise ship detection using SAR images in coastal waters.

Mapping of sea ice in the Arctic region is essential for environmental monitoring and ship navigation. Synthetic Aperture Radar can be used to observe sea ice at high spatial and temporal resolutio...

In this paper, we have proposed a method of sea fog prediction using model sea surface wind (SSW) data and hourly optical satellite data with 500 m spatial resolution. Three sea fog cases in the Ye...

This study represents a fundamental research for a passenger-ship escape guidance system that is a ship-borne agent, and it is for the support of escape decision-making by providing accurate maritime safety information in real time. We conducted a passenger escaping experiment on a training ship, SAEYUDAL, using the situation-aware escape guidance system, which has been developed for on-board application based on products for buildings. It is shown that the system contributes to the shortening of the escape duration and the dispersion of the escaping persons by generating and guiding the safe escape routes which dangerous areas are considered. From the experiment on ship's heeling condition, it is revealed that the heeling angle is linearly related to the escape duration. Therefore, this study shows that the shortening of the escape duration enables a safe and rapid mustering that is the most important process under emergency and appropriate incident responses to minimize loss of lives.