• Journal of Korean Society of Disaster and Security
• /
• v.13 no.4
• /
• pp.75-92
• /
• 2020

In most cases of the water balance analysis, the return flow ratio for each water supply was uniformly determined and applied, so it has been contained a problem that the volume of available water would be incorrectly calculated. Therefore, sewage and wastewater among the return water were focused in this study and the data-driven model was developed to forecast the outflow from the sewage treatment plant. The forecasting results of LSTM (Long Short-Term Memory), GRU (Gated Recurrent Units), and SVR (Support Vector Regression) models, which are mainly used for forecasting the time series data in most fields, were compared with the observed data to determine the optimal model parameters for forecasting outflow. As a result of applying the model, the root mean square error (RMSE) of the GRU model was smaller than those of the LSTM and SVR models, and the Nash-Sutcliffe coefficient (NSE) was higher than those of others. Thus, it was judged that the GRU model could be the optimal model for forecasting the outflow in sewage treatment plants. However, the forecasting outflow tends to be underestimated and overestimated in extreme sections. Therefore, the additional data for extreme events and reducing the minimum time unit of input data were necessary to enhance the accuracy of forecasting. If the water use of the target site was reviewed and the additional parameters that could reflect seasonal effects were considered, more accurate outflow could be forecasted to be ready for climate variability in near future. And it is expected to use as fundamental resources for establishing a reasonable river water management system based on the forecasting results.

• Ocean and Polar Research
• /
• v.35 no.3
• /
• pp.259-272
• /
• 2013

One of the factors influencing the climate around Korea is the oceanic-atmospheric variability in the tropical region between the eastern Indian and the western Pacific Oceans. Lack of knowledge about the air-sea interaction in the tropical Indo-Pacific region continues to make it problematic forecasting the ocean climate in the East Asia. The 'Tropical Indo-Pacific water transport and ecosystem monitoring EXperiment (TIPEX)' is a program for monitoring the ocean circulation variability between Pacific and Indian Oceans and for improving the accuracy of future climate forecasting. The main goal of the TIPEX program is to quantify the climate and ocean circulation change between the Indian and the Pacific Oceans. The contents of the program are 1) to observe the mixing process of different water masses and water transport in the eastern Indian and the western Pacific, 2) to understand the large-scale oceanic-climatic variation including El Nino-Southern Oscillation (ENSO)/Warm Pool/Pacific Decadal Oscillation (PDO)/Indian Ocean Dipole (IOD), and 3) to monitor the biogeochemical processes, material flux, and biological changes due to the climate change. In order to effectively carry out the monitoring program, close international cooperation and the proper co-work sharing of tasks between China, Japan, Indonesia, and India as well as USA is required.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.2
• /
• pp.63-70
• /
• 2008

This paper resents the spatial electric load forecasting algorithm using the multiple regression analysis method which is enhanced from the algorithm of the DISPLAN(Distribution Information System PLAN). In order to improve the accuracy of the spatial electrical load forecasting, input variables are selected for GRDP(Gross Regional Domestic Product), the local population and the electrical load sales of the past year. Tests are performed to analyze the accuracy of the proposed method for Gyeong-San City, Gu-Mi City, Gim-Cheon City and Yeong-Ju City of North Gyeongsang Province. Test results show that the overall accuracy of the proposed method is improved the percentage error 11.2[%] over 12[%] of the DISPLAN. Specially, the accuracy is enhanced a lot in the case of high variability of input variables. The proposed method will be used to forecast local electric loads for the optimal investment of distribution systems.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.655-669
• /
• 2018

In this study, we developed a hybrid forecasting model based on a four-parameter distribution which allows a simultaneous season-ahead forecasting for both seasonal rainfall and sub-daily rainfall in Han-River and Geum-River basins. The proposed model is mainly utilized a set of time-varying predictors and the associated model parameters were estimated within a Bayesian nonstationary rainfall frequency framework. The hybrid forecasting model was validated through an cross-validatory experiment using the recent rainfall events during 2014~2017 in both basins. The seasonal precipitation results showed a good agreement with the observations, which is about 86.3% and 98.9% in Han-River basin and Geum-River basin, respectively. Similarly, for the extreme rainfalls at sub-daily scale, the results showed a good correspondence between the observed and simulated rainfalls with a range of 65.9~99.7%. Therefore, it can be concluded that the proposed model could be used to better consider climate variability at multiple time scales.

• Journal of the Korean earth science society
• /
• v.42 no.6
• /
• pp.605-622
• /
• 2021

Seasonal forecasting has numerous socioeconomic benefits because it can be used for disaster mitigation. Therefore, it is necessary to diagnose and improve the seasonal forecast model. Moreover, the model performance is partly related to the ocean model. This study evaluated the hindcast performance in the upper ocean of the Global Seasonal Forecasting System version 5-Global Couple Configuration 2 (GloSea5-GC2) using a multivariable integrated evaluation method. The normalized potential temperature, salinity, zonal and meridional currents, and sea surface height anomalies were evaluated. Model performance was affected by the target month and was found to be better in the Pacific than in the Atlantic. An increase in lead time led to a decrease in overall model performance, along with decreases in interannual variability, pattern similarity, and root mean square vector deviation. Improving the performance for ocean currents is a more critical than enhancing the performance for other evaluated variables. The tropical Pacific showed the best accuracy in the surface layer, but a spring predictability barrier was present. At the depth of 301 m, the north Pacific and tropical Atlantic exhibited the best and worst accuracies, respectively. These findings provide fundamental evidence for the ocean forecasting performance of GloSea5.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.22-25
• /
• 2005

The 10 Year Implementation Plan for a Global Earth Observation System of Systems (GEOSS), which was endorsed at the Third Earth Observation Summit in Brussels in February, 2005, emphasizes the importance of data management facilities for diverse and large-volume Earth Observation data from inhomogeneous information sources. A three year research plan for addressing this key target of GEOSS has just approved as the first step by the Japanese government. The goals of this research are, (1) to develop a data management core system consisting of data integration and information fusion functions and interoperability and information service functions; (2) to establish data and information flows between data providers and users; (3) to promote application studies of data integration and information fusion, especially in the fields of weather forecasting, flood forecasting, agricultural management, and climate variability and changes. The research group involves leading scientists on information science and technology, who have been developing giant data archive servers, storage area networks, metadata models, ontology for the earth observations. They are closely cooperating with scientists on earth sciences, water resources management, and agriculture, and establishing an effective collaborative research framework.

• Journal of Intelligence and Information Systems
• /
• v.14 no.3
• /
• pp.25-39
• /
• 2008

The objective of this study is to forecast the operational continuous ability using Artificial Neural Networks in battalion defensive operation for the commander decision making support. The forecasting of the combat result is one of the most complex issue in military science. However, it is difficult to formulate a mathematical model to evaluate the combat power of a battalion in defensive operation since there are so many parameters and high temporal and spatial variability among variables. So in this study, we used company combat power level data in Battalion Command in Battle Training as input data and used Feed-Forward Multilayer Perceptrons(MLP) and General Regression Neural Network (GRNN) to evaluate operational continuous ability. The results show 82.62%, 85.48% of forecasting ability in spite of non-linear interactions among variables. We think that GRNN is a suitable technique for real-time commander's decision making and evaluation of the commitment priority of troops in reserve.

• Atmosphere
• /
• v.32 no.4
• /
• pp.367-379
• /
• 2022

In this paper, the evaluation of the performance of Korea Meteorological Administratio (KMA) Global Seasonal forecasting system version 6 (GloSea6) is presented by assessing the effects of larger ensemble size and carrying out the test using different initial conditions for hindcast in sub-seasonal to seasonal scales. The number of ensemble members increases from 3 to 7. The Ratio of Predictable Components (RPC) approaches the appropriate signal magnitude with increase of ensemble size. The improvement of annual variability is shown for all basic variables mainly in mid-high latitude. Over the East Asia region, there are enhancements especially in 500 hPa geopotential height and 850 hPa wind fields. It reveals possibility to improve the performance of East Asian monsoon. Also, the reliability tends to become better as the ensemble size increases in summer than winter. To assess the effects of using different initial conditions, the area-mean values of normalized bias and correlation coefficients are compared for each basic variable for hindcast according to the four initial dates. The results have better performance when the initial date closest to the forecasting time is used in summer. On the seasonal scale, it is better to use four initial dates, where the maximum size of the ensemble increases to 672, mainly in winter. As the use of larger ensemble size, therefore, it is most efficient to use two initial dates for 60-days prediction and four initial dates for 6-months prediction, similar to the current Time-Lagged ensemble method.

• Korea Trade Review
• /
• v.47 no.4
• /
• pp.215-231
• /
• 2022

Analysis and forecasting of the Baltic Capsize Index (BCI) is important for managing an entity's losses and risks from the uncertainty and volatility of the fast-changing maritime transport market in the future. This study conducted volatility transition analysis through the GARCH model, using BCI which is highly related to steel raw materials. As for the data, 2,385 monthly data were used from March 1999 to March 2021. In this study, after basic statistical analysis, unit root and cointegration test, the GARCH, EGARCH, and DCC-GARCH models were used for volatility transition analysis. As the results of GARCH and EGARCH model, we confirmed that all variables had no autocorrelation between the standardized residuals for error terms and the square of residuals, that the variability of all variables at this time was likely to persist in the future, and that the variability of the time-series error term impact according to Iron ore trade (IoT). In addition, through the EGARCH model, the magnitude convenience of all variables except the Iron ore price (IOP) and Capesize bulk fleet (BCF) variables was greater than the positive value (+). As a result of analyzing the DCC-GARCH (1,1) model, partial linear combinations were confirmed over the entire period. Estimating the effect of variability transition on BCF and C5 with statistically significant linear combinations with BCI confirmed that the impact of BCF on BCI was greater than the impact of BCI itself.

• Atmosphere
• /
• v.34 no.2
• /
• pp.97-106
• /
• 2024

The seasonal forecast skill of tropical cyclones (TCs) in the Northern Hemisphere from the Korea Meteorological Administration (KMA) Global Seasonal Forecast System version 6 (GloSea6) hindcast has been verified for the period 1993 to 2016. The operational climate prediction system at KMA was upgraded from GloSea5 to GloSea6 in 2022, therefore further validation was warranted for the seasonal predictability and variability of this new system for TC forecasts. In this study, we examine the frequency, track density, duration, and strength of TCs in the North Indian Ocean, the western North Pacific, the eastern North Pacific, and the North Atlantic against the best track data. This methodology follows a previous study covering the period 1996 to 2009 published in 2020. GloSea6 indicates a higher frequency of TC generation compared to observations in the western North Pacific and the eastern North Pacific, suggesting the possibility of more TC generation than GloSea5. Additionally, GloSea6 exhibits better interannual variability of TC frequency, which shows relatively good correlation with observations in the North Atlantic and the western North Pacific. Regarding TC intensity, GloSea6 still underestimates the minimum surface pressures and maximum wind speeds from TCs, as is common among most climate models due to lower horizontal resolutions. However, GloSea6 is likely capable of simulating slightly stronger TCs than GloSea5, partly attributed to more frequent 6-hourly outputs compared to the previous daily outputs.