• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.299-309
• /
• 2022

Recently, The sea water temperature around Korean Peninsula is steadily increasing. Water temperature changes not only affect the fishing ecosystem, but also are closely related to military operations in the sea. The purpose of this study is to suggest which model is more suitable for the field of water temperature prediction by attempting short-term water temperature prediction through various prediction models based on deep learning technology. The data used for prediction are water temperature data from the East Sea (Goseong, Yangyang, Gangneung, and Yeongdeok) from 2016 to 2020, which were observed through marine observation by the National Fisheries Research Institute. In addition, we use Long Short-Term Memory (LSTM), Bidirectional LSTM, and Gated Recurrent Unit (GRU) techniques that show excellent performance in predicting time series data as models for prediction. While the previous study used only LSTM, in this study, the prediction accuracy of each technique and the performance time were compared by applying various techniques in addition to LSTM. As a result of the study, it was confirmed that Bidirectional LSTM and GRU techniques had the least error between actual and predicted values at all observation points based on 1 hour prediction, and GRU was the fastest in learning time. Through this, it was confirmed that a method using Bidirectional LSTM was required for water temperature prediction to improve accuracy while reducing prediction errors. In areas that require real-time prediction in addition to accuracy, such as anti-submarine operations, it is judged that the method of using the GRU technique will be more appropriate.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.3
• /
• pp.47-57
• /
• 2022

We carried out studies on prediction in concentration of dissolved oxygen (DO) with LSTM model and prediction in occurrence of hypoxia water mass (HWM) with decision tree. As results of study on prediction in DO concentration, a large number of Hidden node caused high complexity of model and required enough Epoch. And it was high accuracy in long Sequence length as prediction time step increased. The results of prediction in occurrence of HWM showed that the accuracy of nonHWM case was 66.1% in 30 day prediction, it was higher than 37.5% of HWM case. The reason is that the decision tree might overestimate DO concentration.

• Korean Journal of Remote Sensing
• /
• v.32 no.2
• /
• pp.155-169
• /
• 2016

In this study, we developed a multi-sensor blending short-term rainfall forecasting technique using radar and satellite data during extreme rainfall occurrences in Busan and Gyeongnam region in August 2014. The Tropical Z-R relationship ($Z=32R^{1.65}$) has applied as a optimal radar Z-R relation, which is confirmed that the accuracy is improved during 20mm/h heavy rainfall. In addition, the multi-sensor blending technique has applied using radar and COMS (Communication, Ocean and Meteorological Satellite) data for quantitative precipitation estimation. The very-short-term rainfall forecasting performance was improved in 60 mm/h or more of the strong heavy rainfall events by multi-sensor blending. AWS (Automatic Weather System) and MAPLE data were used for verification of rainfall prediction accuracy. The results have ensured about 50% or more in accuracy of heavy rainfall prediction for 1-hour before rainfall prediction, which are correlations of 10-minute lead time have 0.80 to 0.53, and root mean square errors have 3.99 mm/h to 6.43 mm/h. Through this study, utilizing of multi-sensor blending techniques using radar and satellite data are possible to provide that would be more reliable very-short-term rainfall forecasting data. Further we need ongoing case studies and prediction and estimation of quantitative precipitation by multi-sensor blending is required as well as improving the satellite rainfall estimation algorithm.

• Journal of Navigation and Port Research
• /
• v.38 no.1
• /
• pp.65-71
• /
• 2014

Gyeongbu and Namhae expressways in the country, are the major arterial highways which are connected with the Busan port in the north-south and east-west directions, respectively, and required to study the traffic characteristics about the hourly volume factors(K-factor) by concentrated midium-size and large-size cargo trucks of 20% or higher in expressways. We therefore attempted to predict the K-factor in expressways through the correlation analysis between K-factor and K-factor estimates on the basis of the short-term VDS data collected at the basic segments of the above major expressways. As a result, power model appeared to be appropriate in predicting K-factor by the K-factor estimate based on VDS data for 7 days with a high explanatory power and validity.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.1142-1146
• /
• 2009

A rainfall simulation and forecasting technique that can generate daily rainfall sequences conditional on multi-model ensemble GCMs is developed and applied to data in Korea for the major rainy season. The GCM forecasts are provided by APEC climate center. A Weather State Based Downscaling Model (WSDM) is used to map teleconnections from ocean-atmosphere data or key state variables from numerical integrations of Ocean-Atmosphere General Circulation Models to simulate daily sequences at multiple rain gauges. The method presented is general and is applied to the wet season which is JJA(June-July-August) data in Korea. The sequences of weather states identified by the EM algorithm are shown to correspond to dominant synoptic-scale features of rainfall generating mechanisms. Application of the methodology to seasonal rainfall forecasts using empirical teleconnections and GCM derived climate forecast are discussed.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.603-614
• /
• 2021

Recently, the surface temperature in the seas around Korea has been continuously rising. This temperature rise causes changes in fishery resources and affects leisure activities such as fishing. In particular, high temperatures lead to the occurrence of red tides, causing severe damage to ocean industries such as aquaculture. Meanwhile, changes in sea temperature are closely related to military operation to detect submarines. This is because the degree of diffraction, refraction, or reflection of sound waves used to detect submarines varies depending on the ocean mixed layer. Currently, research on the prediction of changes in sea water temperature is being actively conducted. However, existing research is focused on predicting only the surface temperature of the ocean, so it is difficult to identify fishery resources according to depth and apply them to military operations such as submarine detection. Therefore, in this study, we predicted the temperature of the ocean mixed layer at a depth of 38m by using temperature data for each water depth in the upper mixed layer and meteorological data such as temperature, atmospheric pressure, and sunlight that are related to the surface temperature. The data used are meteorological data and sea temperature data by water depth observed from 2016 to 2020 at the IEODO Ocean Research Station. In order to increase the accuracy and efficiency of prediction, LSTM (Long Short-Term Memory), which is known to be suitable for time series data among deep learning techniques, was used. As a result of the experiment, in the daily prediction, the RMSE (Root Mean Square Error) of the model using temperature, atmospheric pressure, and sunlight data together was 0.473. On the other hand, the RMSE of the model using only the surface temperature was 0.631. These results confirm that the model using meteorological data together shows better performance in predicting the temperature of the upper ocean mixed layer.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2021

This is a basic study on the development of deep learning-based algorithms to detect smoke before the smoke detector operates in the event of a ship fire, analyze and utilize the detected data, and support fire suppression and evacuation activities by predicting the spread of smoke before it spreads to remote areas. Proposed algorithms were reviewed in accordance with the following procedures. As a first step, smoke images obtained through fire simulation were applied to the YOLO (You Only Look Once) model, which is a deep learning-based object detection algorithm. The mean average precision (mAP) of the trained YOLO model was measured to be 98.71%, and smoke was detected at a processing speed of 9 frames per second (FPS). The second step was to estimate the spread of smoke using the coordinates of the boundary box, from which was utilized to extract the smoke geometry from YOLO. This smoke geometry was then applied to the time series prediction algorithm, long short-term memory (LSTM). As a result, smoke spread data obtained from the coordinates of the boundary box between the estimated fire occurrence and 30 s were entered into the LSTM learning model to predict smoke spread data from 31 s to 90 s in the smoke image of a fast fire obtained from fire simulation. The average square root error between the estimated spread of smoke and its predicted value was 2.74.

• Ocean Systems Engineering
• /
• v.4 no.4
• /
• pp.293-308
• /
• 2014

Unlike the traditional displacement type vessels, the high speed planing crafts are supported by the lift forces which are highly non-linear. This non-linear phenomenon causes their motions in an irregular seaway to be non-Gaussian. In general, it may not be possible to express the probability distribution of such processes by an analytical formula. Also the process might not be stationary or ergodic in which case the statistical behavior of the motion to be constantly changing with time. Therefore the extreme values of such a process can no longer be calculated using the analytical formulae applicable to Gaussian processes. Since closed form analytical solutions do not exist, recourse is taken to fitting a distribution to the data and estimating the statistical properties of the process from this fitted probability distribution. The peaks over threshold analysis and fitting of the Generalized Pareto Distribution are explored in this paper as an alternative to Weibull, Generalized Gamma and Rayleigh distributions in predicting the short term extreme value of a random process.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.6 no.3
• /
• pp.700-714
• /
• 2014

This study aims to identify the relations between seakeeping characteristics and hull form parameters for YTU Gulet series with cruiser stern. Seakeeping analyses are carried out by means of a computer software which is based on the strip theory and statistical short term response prediction method. Multiple regression analysis is used for numerical assessment through a computer software. RMS heave-pitch motions and absolute vertical accelerations on passenger saloon for Sea State 3 at head waves are investigated for this purpose. It is well known that while ship weight and the ratios of main dimensions are the primary factors on ship motions, other hull form parameters ($C_P$, $C_{WP}$, $C_{VP}$, etc.) are the secondary factors. In this study, to have an idea of geometric properties on ship motions of gulets three different regression models are developed. The obtained outcomes provide practical predictions of seakeeping behavior of gulets with a high level of accuracy that would be useful during the concept design stage.

• Journal of Ocean Engineering and Technology
• /
• v.22 no.6
• /
• pp.52-57
• /
• 2008

The short-term high temperature creep rupture behavior of Ni-based Alloy718 steel was investigated at the elevated temperatures range of 550 to $700^{\circ}C$ under constant stress conditions. The creep rupture characteristics such as creep stress, rupture time, steady state creep rate, and initial strain were evaluated. Creep stress has a quantitative correlation between creep rupture tim and steady state creep rate. The stress exponents (n, m) of the experimental data at 550, 600, 650 and $700^{\circ}C$ were derived as 33.5, -24.9, 26.1, -21.2, 16.8, -12.8 and 10, -8.2, respectively. The stress exponent decreased with increasing creep temperature. The creep lift prediction was derived by the Larson-Miller parameter (LMP) method and the resultant equation was obtained as follows: T($logt_r$+20)=-0.00252 ${\sigma}^2$-1.377${\sigma}$+-22718.