• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1077-1093
• /
• 2020

Sea Surface Temperature (SST) is an important environmental indicator that affects climate coupling systems around the world. In particular, coastal regions suffer from abnormal SST resulting in huge socio-economic damage. This study used Long Short Term Memory (LSTM) and Convolutional Long Short Term Memory (ConvLSTM) to predict SST up to 7 days in the south sea region in South Korea. The results showed that the ConvLSTM model outperformed the LSTM model, resulting in a root mean square error (RMSE) of 0.33℃ and a mean difference of -0.0098℃. Seasonal comparison also showed the superiority of ConvLSTM to LSTM for all seasons. However, in summer, the prediction accuracy for both models with all lead times dramatically decreased, resulting in RMSEs of 0.48℃ and 0.27℃ for LSTM and ConvLSTM, respectively. This study also examined the prediction of abnormally high SST based on three ocean heatwave categories (i.e., warning, caution, and attention) with the lead time from one to seven days for an ocean heatwave case in summer 2017. ConvLSTM was able to successfully predict ocean heatwave five days in advance.

• Journal of Wetlands Research
• /
• v.13 no.2
• /
• pp.329-341
• /
• 2011

This study was conducted with the national river, Munsancheon, which is located in Paju-si, Gyeonggi-do. The sediment discharge of Munsancheon was directly measured to analyze the sediment characteristics, and the results were used in the numerical model to predict the long-term river bed variation. The flow-total sediment discharge relation was derived using the measured total sediment discharge, and the results were compared with the total sediment discharge that was calculated using the existing prediction formula to derive a proper sediment discharge prediction method. In the actual measurements, the total annual sediment discharge was 5,478 ton/year, and the specific sediment discharge was 29.23 ton/$km^2$/year. The Ackers & White formula resulted in the values very close to the actual measurements. With the actual sediment discharge, geographical and hydrologic data as the input variables, HEC-6 and GSTARS models were comparatively analyzed. The test results showed that the HEC-6 model is suitable for the reliable prediction of the long-term river bed variation. Accordingly, the model was used for the long-term river bed variation prediction in this study. In the case of Munsancheon, deposition was continued in the downstream area and erosion occurred in the upstream area on the whole. It was expected that the stream would be stabilized in the river bed condition of 20 years later. The river bed variation was within 1 m, which was at the significance level. In the downstream area that is influenced by tide, however, the accumulation was continuously increasing within the section 2,000-7,000 m from the outlet. It seems that this should be considered in establishing the river management plans.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.101-107
• /
• 2013

Is generated in real time in the real world, a large amount of time series data from a wide range of business areas. But it is not easy to determine the optimal model for the description and understanding of the time series data is represented as a dynamic feature. In this study, through the HMM suitable for estimating the short and long-term forecasting model of time-series data to estimate a model that can explain the characteristics of these time series data, it was estimated to predict future patterns of movement. The actual stock market through various materials, information criterion and optimal model estimation for the length of the most efficient data was found to accurately estimate the state of the model. Similar movement patterns predictive than the long-term prediction is more similar to the short-term prediction of the experimental result were found to be.

• 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 for Atmospheric Environment
• /
• v.32 no.1
• /
• pp.114-126
• /
• 2016

Many cohort studies have reported associations of individual-level long-term exposures to $PM_{10}$ and health outcomes. Individual exposures were often estimated by using exposure prediction models relying on $PM_{10}$ data measured at national regulatory monitoring sites. This study explored spatial and temporal characteristics of regulatory $PM_{10}$ measurement data in South Korea and suggested $PM_{10}$ concentration metrics as long-term exposures for assessing health effects in cohort studies. We obtained hourly $PM_{10}$ data from the National Institute of Environmental Research for 2001~2012 in South Korea. We investigated spatial distribution of monitoring sites using the density and proximity in each of the 16 metropolitan cities and provinces. The temporal characteristics of $PM_{10}$ measurement data were examined by annual/seasonal/diurnal patterns across urban background monitoring sites after excluding Asian dust days. For spatial characteristics of $PM_{10}$ measurement data, we computed coefficient of variation (CV) and coefficient of divergence (COD). Based on temporal and spatial investigation, we suggested preferred long-term metrics for cohort studies. In 2010, 294 urban background monitoring sites were located in South Korea with a site over an area of $415.0km^2$ and distant from another site by 31.0 km on average. Annual average $PM_{10}$ concentrations decreased by 19.8% from 2001 to 2012, and seasonal $PM_{10}$ patterns were consistent over study years with higher concentrations in spring and winter. Spatial variability was relatively small with 6~19% of CV and 21~46% of COD across 16 metropolitan cities and provinces in 2010. To maximize spatial coverage and reflect temporal and spatial distributions, our suggestion for $PM_{10}$ metrics representing long-term exposures was the average for one or multiple years after 2009. This study provides the knowledge of all available $PM_{10}$ data measured at national regulatory monitoring sites in South Korea and the insight of the plausible longterm exposure metric for cohort studies.

• KNOM Review
• /
• v.24 no.2
• /
• pp.13-23
• /
• 2021

Recently, as networks become more complex due to the activation of IoT devices, research on long-term traffic prediction beyond short-term traffic prediction is being activated to predict and prepare for network congestion in advance. The recursive strategy, which reuses short-term traffic prediction results as an input, has been extended to multi-step traffic prediction, but as the steps progress, errors accumulate and cause deterioration in prediction performance. In this paper, an LSTM-based multi-step traffic prediction method using a multi-output strategy is introduced and its performance is evaluated. As a result of experiments based on actual DNS request traffic, it was confirmed that the proposed LSTM-based multiple output strategy technique can reduce MAPE of traffic prediction performance for non-stationary traffic by 6% than the recursive strategy technique.

• Journal of Astronomy and Space Sciences
• /
• v.14 no.2
• /
• pp.381-385
• /
• 1997

A long-term prediction algorithm of geostationary orbit was developed using the analytical method. The perturbation force models include geopotential upto fifth order and degree and luni-solar gravitation, and solar radiation pressure. All of the perturbation effects were analyzed by secular variations, short-period variations, and long-period variations for equinoctial elements such as the semi-major axis, eccentricity vector, inclination vector, and mean longitude of the satellite. Result of the analytical orbit propagator was compared with that of the cowell orbit propagator for the KOREASAT. The comparison indicated that the analytical solution could predict the semi-major axis with an accuracy of better than $pm35$ meters over a period of 3 month.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.105-111
• /
• 2023

Recently, research on prediction algorithms using deep learning has been actively conducted. In addition, algorithmic trading (auto-trading) based on predictive power of artificial intelligence is also becoming one of the main investment methods in stock trading field, building its own history. Since the possibility of human error is blocked at source and traded mechanically according to the conditions, it is likely to be more profitable than humans in the long run. In particular, for the virtual currency market at least for now, unlike stocks, it is not possible to evaluate the intrinsic value of each cryptocurrencies. So it is far effective to approach them with technical analysis and cryptocurrency market might be the field that the performance of algorithmic trading can be maximized. Currently, the most commonly used artificial intelligence method for financial time series data analysis and forecasting is Long short-term memory(LSTM). However, even t4he LSTM also has deficiencies which constrain its widespread use. Therefore, many improvements are needed in the design of forecasting and investment algorithms in order to increase its utilization in actual investment situations. Meanwhile, Prophet, an artificial intelligence algorithm developed by Facebook (META) in 2017, is used to predict stock and cryptocurrency prices with high prediction accuracy. In particular, it is evaluated that Prophet predicts the price of virtual currencies better than that of stocks. In this study, we aim to show Prophet's virtual currency price prediction accuracy is higher than existing deep learning-based time series prediction method. In addition, we execute mock investment with Prophet predicted value. Evaluating the final value at the end of the investment, most of tested coins exceeded the initial investment recording a positive profit. In future research, we continue to test other coins to determine whether there is a significant difference in the predictive power by coin and therefore can establish investment strategies.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.199-207
• /
• 2024

Local reservoirs are crucial sources for agricultural water supply, necessitating stable water level management to prepare for extreme climate conditions such as droughts. Water level prediction is significantly influenced by local climate characteristics, such as localized rainfall, as well as seasonal factors including cropping times, making it essential to understand the correlation between input and output data as much as selecting an appropriate prediction model. In this study, extensive multivariate data from over 400 reservoirs in Jeollabuk-do from 1991 to 2022 was utilized to train and validate a water level prediction model that comprehensively reflects the complex hydrological and climatological environmental factors of each reservoir, and to analyze the impact of each input feature on the prediction performance of water levels. Instead of focusing on improvements in water level performance through neural network structures, the study adopts a basic Feedforward Neural Network composed of fully connected layers, batch normalization, dropout, and activation functions, focusing on the correlation between multivariate input data and prediction performance. Additionally, most existing studies only present short-term prediction performance on a daily basis, which is not suitable for practical environments that require medium to long-term predictions, such as 10 days or a month. Therefore, this study measured the water level prediction performance up to one month ahead through a recursive method that uses daily prediction values as the next input. The experiment identified performance changes according to the prediction period and analyzed the impact of each input feature on the overall performance based on an Ablation study.

• Journal of Korea Water Resources Association
• /
• v.31 no.1
• /
• pp.95-103
• /
• 1998

Dam sediment can be predicted from the two methods: the one is a physical analysis based on the hydrjulic mechanism and the other is an empirical approach using observed data as a design factor. The former can be used to estimate short-term phenomena by mathematical methods. the latter can be used for deriving long-term design parameters such as dead storage calculation. Monthly reservoir operation is possible with the sluicing efficiency curve based on empirical data. The optimal sediment management can be carried out using the information variable which traces deposit sediments corresponding to the reservoir storage. The idea can provide an optimal operation strategy to save effective storage varying with time. This study presents a methodology for the long-term sediment prediction using sluicing efficiency curve. An application is conducted for estimating accumulated sedment deposit and water supply capability ofr the Fenhe dam in the Yellow rever of China.