• Journal of the Korea Convergence Society
• /
• v.9 no.3
• /
• pp.15-21
• /
• 2018

The ocean drifter is a device for observing the ocean weather by floating off the sea surface. The data observed through the drifter is utilized in the ocean weather prediction and oil spill. Observed data may contain incorrect or missing data at the time of observation, and accuracy may be lowered when we use the data. In this paper, we propose a data correction model using recurrent neural networks. We corrected data collected from 7 drifters in 2015 and 8 drifters in 2016, and conducted experiments of drifter moving prediction to reflect the correction results. Experimental results showed that observed data are corrected by 13.9% and improved the performance of the prediction model by 1.4%.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.9 no.4
• /
• pp.204-211
• /
• 2004

Autonomous profiling CTD floats are a useful tool for observing the oceans. We, however, cannot perform post-deployment calibration of the CTD's attached to the floats, and the assessment of the accuracy and stability of the profile data from the floats is one of the important issues in the delayed mode quality control of the profiles. Variations in salinity in the intermediate level of East Sea is comparable to the accuracy of salinity data required by the international Argo Program, which is 0.01. Therefore, we can assess the credibility of salinity data from the floats deployed in the East Sea using three independent methods while considering the East Sea as a salinity calibration bath. The methods utilized here are 1) comparison of high quality CTD data and float data obtained at similar locations at similar time, 2) comparison of float data obtained at similar locations at similar time, and 3) investigation of long term stability and accuracy of salinity data from parking depths. All three methods show that without any calibration, the salinity data satisfy the accuracy criterion by the Argo Program. While assuming that the intermediate level temperature in the East Sea is as homogeneous as the salinity, we have applied the three methods to temperature data. We found that the accuracy of temperature reading is 0.01$^{\circ}C$, which is about twice larger than the requirement by the Argo Program, 0.005$^{\circ}C$. This does not mean that the temperature readings are inaccurate, because the intermediate level temperature does vary spacially and temporally more than the accuracy interval required by the Argo Program. If we take into account the variation in the intermediate level temperature, the accuracy of temperature data from the floats is not significantly different from that proposed by the Argo Program. Therefore, one could use both temperature and salinity profiles from the floats assessed in this study without calibration.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.57-67
• /
• 2018

The ensemble is a unified approach used for getting better performance by using multiple algorithms in machine learning. In this paper, we introduce boosting and bagging, which have been widely used in ensemble techniques, and design a method using support vector regression, radial basis function network, Gaussian process, and multilayer perceptron. In addition, our experiment was performed by adding a recurrent neural network and MOHID numerical model. The drifter data used for our experimental verification consist of 683 observations in seven regions. The performance of our ensemble technique is verified by comparison with four algorithms each. As verification, mean absolute error was adapted. The presented methods are based on ensemble models using bagging, boosting, and machine learning. The error rate was calculated by assigning the equal weight value and different weight value to each unit model in ensemble. The ensemble model using machine learning showed 61.7% improvement compared to the average of four machine learning technique.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.24 no.2
• /
• pp.208-225
• /
• 2019

To understand the mean surface circulation and surface currents in the East Sea, trajectories of surface drifters passed through the East Sea from 1991 to 2017 were analyzed. By analyzing the surface drifter trajectory data, the main paths of surface ocean currents were grouped and the variation in each main current path was investigated. The East Korea Warm Current (EKWC) heading northward separates from the coast at $36{\sim}38^{\circ}N$ and flows to the northeast until $131^{\circ}E$. In the middle (from $131^{\circ}E$ to $137^{\circ}E$) of the East Sea, the average latitude of the currents flowing eastward ranges from 36 to $40^{\circ}N$ and the currents meander with large amplitude. When the average latitude of the surface drifter paths was in the north (south) of $37.5^{\circ}N$, the meandering amplitude was about 50 (100) km. The most frequent route of surface drifters in the middle of the East Sea was the path along $37.5-38.5^{\circ}N$. The surface drifters, which were deployed off the coast of Vladivostok in the north of the East Sea, moved to the southwest along the coast and were separated from the coast to flow southeastward along the cyclonic circulation around the Japan Basin. And, then, the drifters moved to the east along $39-40^{\circ}N$. The mean surface current vector and mean speed were calculated in each lattice with $0.25^{\circ}$ grid spacing using the velocity data of surface drifters which passed through each lattice. The current variance ellipses were calculated with $0.5^{\circ}$ grid spacing. Because the path of the EKWC changes every year in the western part of the Ulleung Basin and the current paths in the Yamato Basin keep changing with many eddies, the current variance ellipses are relatively large in these region. We present a schematic map of the East Sea surface current based on the surface drifter data. The significance of this study is that the surface ocean circulation of the East Sea, which has been mainly studied by numerical model simulations and the sea surface height data obtained from satellite altimeters, was analyzed based on in-situ Lagrangian observational current data.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.45-52
• /
• 2017

Drifter is an equipment for observing the characteristics of seawater in the ocean, and it can be used to predict effluent oil diffusion and to observe ocean currents. In this paper, we design models or the prediction of drifter trajectory using machine learning. We propose methods for estimating the trajectory of drifter using support vector regression, radial basis function network, Gaussian process, multilayer perceptron, and recurrent neural network. When the propose mothods were compared with the existing MOHID numerical model, performance was improve on three of the four cases. In particular, LSTM, the best performed method, showed the imporvement by 47.59% Future work will improve the accuracy by weighting using bagging and boosting.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.1
• /
• pp.11-18
• /
• 2022

In order to improve the accuracy of particle tracking prediction techniques near the Korean Strait, this study compared and analyzed a particle tracking model based on a seawater flow numerical model and a machine learning based on a particle tracking model using field observation data. The data used in the study were the surface drifter buoy movement trajectory data observed in the Korea Strait, prediction data by machine learning (linear regression, decision tree) using the tide and wind data from three observation stations (Gageo Island, Geoje Island, Gyoboncho), and prediciton data by numerical models (ROMS, MOHID). The above three data were compared through three error evaluation methods (Correlation Coefficient (CC), Root Mean Square Errors (RMSE), and Normalized Cumulative Lagrangian Separation (NCLS)). As a final result, the decision tree model had the best prediction accuracy in CC and RMSE, and the MOHID model had the best prediction results in NCLS.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.3
• /
• pp.72-81
• /
• 2022

Positions of five drifting buoys deployed on August 2020 near southwestern area of Jeju Island and numerically predicted velocities were used to develop five Artificial Intelligence-based models (AI models) for the prediction of particle tracks. Five AI models consisted of three machine learning models (Extra Trees, LightGBM, and Support Vector Machine) and two deep learning models (DNN and RBFN). To evaluate the prediction accuracy for six models, the predicted positions from five AI models and one numerical model were compared with the observed positions from five drifting buoys. Three skills (MAE, RMSE, and NCLS) for the five buoys and their averaged values were calculated. DNN model showed the best prediction accuracy in MAE, RMSE, and NCLS.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.11 no.1
• /
• pp.21-30
• /
• 2006

This study investigated the temperature-salinity spatio-temporal variability around the Ulleung-do Island (UI) by using CTD profiles obtained by the ARGO floats far the period of Oct.,2003 to Aug.,2005. The waterbody in the upper 700 m around the UI could be classified into five water masses, which is consistent to traditional water characteristics in the East Sea. In the upper surface layer, the temperature and salinity in fall season became even lower than those properties in the summer time. The East Sea Intermediate Water (ESIW) characterized by the salinity minimum layer shows the range of potential temperature between 1 to $5^{\circ}C$ and salinity lower than 34.06 psu. The ESIW lies approximately at 265 m depth with average thickness of 175 m. This thickness of the ESIW continues to be relatively uniform regardless of spatio-temporal space. However, the depth of the ESIW shows vertical variation influenced by the Ulleung warm eddy (UWE). Since the UWE lies in the upper layer, the Upper Portion of the Japan Sea Proper. Water (UPJSPW) is also affected to show the vertical variation. The influence extorted by the UWE reached down to 700 m depth in terms of temperature. The CTD profiles obtained with the high sampling rate by ARCO floats over two-year period provided with very useful and detailed informations in investigating the spatio-temporal variability In the study area.

• Journal of the Korea Convergence Society
• /
• v.11 no.3
• /
• pp.53-59
• /
• 2020

Initial response is important in marine oil spills, such as the Hebei Spirit oil spill, but it is very difficult to predict the movement of oil out of the ocean, where there are many variables. In order to solve this problem, the forecasting of oil spill has been carried out by expanding the particle prediction, which is an existing study that studies the movement of floats on the sea using the data of the float. In the ocean data format HDF5, the current and wind velocity data at a specific location were extracted using bilinear interpolation, and then the movement of numerous points was predicted by particles and the results were visualized using polygons and heat maps. In addition, we propose a spill oil particle matching algorithm to compensate for the lack of data and the difference between the spilled oil and movement. The spilled oil particle matching algorithm is an algorithm that tracks the movement of particles by granulating the appearance of surface oil spilled oil. The problem was segmented using principal component analysis and matched using genetic algorithm to the point where the variance of travel distance of effluent oil is minimized. As a result of verifying the effluent oil visualization data, it was confirmed that the particle matching algorithm using principal component analysis and genetic algorithm showed the best performance, and the mean data error was 3.2%.

• Korean Journal of Remote Sensing
• /
• v.24 no.4
• /
• pp.273-287
• /
• 2008

Characteristics of skin-bulk sea surface temperature (SST) differences in the Northeast Asia seas were analyzed by utilizing 845 collocated matchup data between NOAA/AVHRR data and oceanic in-situ temperature measurements for selected months from 1994 to 2003. In order to understand diurnal variation of SST within a few meters of the upper ocean, the matchup database were classified into four categories according to day-night and drifter-shipboard measurements. Temperature measurements from daytime drifters showed a good agreement with satellite MCSST (Multi-Channel Sea Surface Temperature) with an RMS error of about $0.56^{\circ}C$. Poor accuracy of SST with an rrns error of $1.12^{\circ}C$ was found in the case of daytime shipboard CTD (Conductivity, Temperature, Depth) measurements. SST differences between MCSST and in-situ measurements are caused by various errors coming from atmospheric moist effect, coastal effect, and others. Most of the remarkable errors were resulted from the diurnal variation of vertical temperature structure within a few meters as well as in-situ oceanic temperatures at different depth, about 20 cm for a satellite-tracked drifting buoy and a few meters for shipboard CTD or moored buoy. This study suggests that satellite-derived SST shows significant errors of about ${\pm}3^{\circ}C$ in some cases and therefore it should be carefully used for one's purpose on the base of in-depth understanding of skin-bulk SST difference and vertical temperature structure in regional sea.