• Korean Journal of Remote Sensing
• /
• 제22권2호
• /
• pp.87-99
• /
• 2006

The Median Resolution Sensors (MRSs) for land observation such as Landsat-ETM+ and SPOT-HRV are more effective than Ocean Color Sensors (OCSs) for studying of detailed ecological and biogeochemical components of the coastal waters. In this study, we developed suspended sediment algorithm for Landsat TM/ETM+ by considering the spectral response curve of each band. To estimate suspended sediment concentration (SS) from satellite image data, there are two difference types of algorithms, that are derived for enhancing the accuracy of SS from Landsat imagery. Both empirical and remote sensing reflectance model (hereafter referred to as $R_{rs}$ model) are used here. This study tried to compare two algorithm, and verified using in situ SS data. It was found that the empirical SS algorithm using band 2 produced the best result. $R_{rs}$ model-based SS algorithm estimated higher values than empirical SS algorithm. In this study we used $R_{rs}$ model developed by Ahn (2000) focused on the Mediterranean coastal area. That's owing to the difference of oceanic characteristics between Mediterranean and Korean coastal area. In the future we will improve that $R_{rs}$ model for the Korean coastal area, then the result will be advanced.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• 제34권4호
• /
• pp.109-118
• /
• 2022

The data of the missing section among the vertex surface sea temperature observation data was imputed using the Bidirectional Recurrent Neural Network(BiRNN). Among artificial intelligence techniques, Recurrent Neural Networks (RNNs), which are commonly used for time series data, only estimate in the direction of time flow or in the reverse direction to the missing estimation position, so the estimation performance is poor in the long-term missing section. On the other hand, in this study, estimation performance can be improved even for long-term missing data by estimating in both directions before and after the missing section. Also, by using all available data around the observation point (sea surface temperature, temperature, wind field, atmospheric pressure, humidity), the imputation performance was further improved by estimating the imputation data from these correlations together. For performance verification, a statistical model, Multivariate Imputation by Chained Equations (MICE), a machine learning-based Random Forest model, and an RNN model using Long Short-Term Memory (LSTM) were compared. For imputation of long-term missing for 7 days, the average accuracy of the BiRNN/statistical models is 70.8%/61.2%, respectively, and the average error is 0.28 degrees/0.44 degrees, respectively, so the BiRNN model performs better than other models. By applying a temporal decay factor representing the missing pattern, it is judged that the BiRNN technique has better imputation performance than the existing method as the missing section becomes longer.

• Journal of the Korean Society of Marine Environment & Safety
• /
• 제29권1호
• /
• pp.60-66
• /
• 2023

Currently, the maritime industry is focusing on developing technologies that promote autonomy and intelligence, such as smart ships, autonomous ships, and eco-friendly technologies, to enhance ship operational efficiency. Many countries are conducting research on different methods to ensure ship safety while increasing operational efficiency. This study aims to develop a real-time ship operational efficiency analysis model using data analysis methods to address the current limitations of the present technologies in the real-time evaluation of operational efficiency. The model selected ship operational efficiency factors and ship operational condition factors to compare the operational efficiency of the ship with present and classified factors to determine whether the present ship operational efficiency is appropriate. The study involved selecting a target ship, collecting data, preprocessing data, and developing classification models. The results of the research were obtained by determining the improved ship operational efficiency based on the ship operational condition factors to support ship operators.

• Journal of the Korean earth science society
• /
• 제28권3호
• /
• pp.343-356
• /
• 2007

This paper explored the characteristics of the interannual sea surface temperature (SST) variability in the equatorial Pacific by analyzing the simulated data from a newly coupled general circulation model (CGCM). The CGCM simulates well the realistic ENSO variability as well as the mean climatologies including SST, seasonal cycle, precipitation, and subsurface structures. It is argued that the zonal gradient of SST in the equatorial Pacific is responsible for the over-energetic SST variability near the equatorial western boundary in the model. This variability could also be related to the strong westward propagation of SST anomalies which resulted from the enhanced the zonal advection feedback. The simple two-strip model supports this by sensitivity tests. Analysis of the relationship between zonal mean thermocline depth and NINO3 SST index suggested that the ENSO variability is controlled by the recharge-discharge oscillator of the model. The lead-lag regression result reveals that heat buildup process in the western equatorial Pacific associated with the increase of the barrier layer thickness (BLT) is a precedent condition for El $Ni\widetilde{n}o$ to develop.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• 제30권2호
• /
• pp.84-94
• /
• 2018

In order to overcome the limitation of deterministic forecast, an ensemble forecasting system for regional ocean wave is developed. This system predicts ocean wind waves based on the meteorological forcing from the Ensemble Prediction System for Global of the Korea Meteorological Administration, which is consisted of 24 ensemble members. The ensemble wave forecasting system is evaluated by using the moored buoy data around Korea. The root mean squared error (RMSE) of ensemble mean showed the better performance than the deterministic forecast system after 2 days, especially RMSE of ensemble mean is improved by 15% compared with the deterministic forecast for 3-day lead time. It means that the ensemble method could reduce the uncertainty of the deterministic prediction system. The Relative Operating Characteristic as an evaluation scheme of probability prediction was bigger than 0.9 showing high predictability, meaning that the ensemble wave forecast could be usefully applied.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제12권1호
• /
• pp.149-157
• /
• 2008

If we use the microwave of SAR, we can observe ocean in spite of severe weather or night time. The sea surface image of SAR has numerous information about atmospheric phenomena related to surface wind field. The extracted wind information from SAR can be used diversely. In order to extract sea wind speed from SAR image, a generated wind direction from SAR and sigma nought should be input into wind model. Therefore, wind speed can be obtained by input wind direction into CMOD5 Model. Azimuth angle using CMOD5 Model is generated by added $90^{\circ}$ to Look angle which is extracted from SAR data file. A gained wind direction spectrum from SAR image has $180^{\circ}$ ambiguity because of 2D-FFT. This ambiguity should decide to use the location of land, wind direction in field or the result of numerical model. Consequently, wind direction using 2D-FFT is $3^{\circ}{\sim}7^{\circ}$ differences with actual surveying data. Wind speed by CMOD5 model is similar to actual surveying data as below 2m/s.

• Journal of the Korean Society of Marine Environment & Safety
• /
• 제28권4호
• /
• pp.469-476
• /
• 2022

This study developed a Recurrent Neural Network model implemented through Long Short-Term Memory (LSTM) that generates long-term tidal level data at Busan Port using tide observation data. The tide levels in Busan Port were predicted by the Korea Hydrographic and Oceanographic Administration (KHOA) using the tide data observed at Busan New Port and Tongyeong as model input data. The model was trained for one month in January 2019, and subsequently, the accuracy was calculated for one year from February 2019 to January 2020. The constructed model showed the highest performance with a correlation coefficient of 0.997 and a root mean squared error of 2.69 cm when the tide time series of Busan New Port and Tongyeong were inputted together. The study's finding reveal that long-term tidal level data prediction of an arbitrary port is possible using the deep learning recurrent neural network model.

• Geophysics and Geophysical Exploration
• /
• 제26권3호
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• Journal of Navigation and Port Research
• /
• 제47권6호
• /
• pp.331-340
• /
• 2023

Predicting the survival time of a person in water (PIW) in maritime search and rescue (SAR) operations is an important concern. Although there have been many studies on survival models in marine-developed countries, it is difficult to apply them to Koreans in Korea's oceans because they were developed using marine distress data from the United Kingdom, United States, and Canada. Data on the survival time of a P IW were collected through interviews and surveys with a special rescue team from the Korea Coast Guard, SAR cases, press releases, and Korea Meteorological Administration data to address these issues. The maximum survival time (Korean) equation was developed by performing a regression analysis of this data, and the applicability to actual marine distress was reviewed and compared to the overseas survival model. By comprehensively using the maximum survival time (Korean), domestic SAR cases, and overseas survival models, guidelines for survival time and intensive and recommended search time were suggested. The study findings can contribute to decision-making, such as the input for search and rescue units. The findings can also help to determine the end of or reductions in SAR operations and explain policy decisions to the public and families of a PIW.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• 제5권1호
• /
• pp.11-18
• /
• 1993

A key element of a successful search and rescue is the correct prediction of the target location. In this paper, new computer models for drift prediction are suggested from the analysis of several methods currently used in other countries. Depending on the availability of the environmental data, users may select a model between the modified versions of U.S. Coast Guard CASP and FLENUMWEACEN SAR. Targets include boats, life rafts and person in water. Life rafts and boats are further classifed. New models are tested and compared with the limited number of field experimental results.