• Korea Trade Review
• /
• v.46 no.6
• /
• pp.191-209
• /
• 2021

In this paper, various time series analysis models and machine learning models are presented for long-term prediction of export growth rate, and the prediction performance is compared and reviewed by RMSE and MAE. Export growth rate is one of the major economic indicators to evaluate the economic status. And It is also used to predict economic forecast. The export growth rate may have a negative (-) value as well as a positive (+) value. Therefore, Instead of using the ReLU function, which is often used for time series prediction of deep learning models, the PReLU function, which can have a negative (-) value as an output value, was used as the activation function of deep learning models. The time series prediction performance of each model for three types of data was compared and reviewed. The forecast data of long-term prediction of export growth rate was deduced by three forecast methods such as a fixed forecast method, a recursive forecast method and a rolling forecast method. As a result of the forecast, the traditional time series analysis model, ARDL, showed excellent performance, but as the time period of learning data increases, the performance of machine learning models including LSTM was relatively improved.

• Communications for Statistical Applications and Methods
• /
• v.29 no.1
• /
• pp.41-51
• /
• 2022

We forecast the US oil consumption level taking advantage of google trends. The google trends are the search volumes of the specific search terms that people search on google. We focus on whether proper selection of google trend terms leads to an improvement in forecast performance for oil consumption. As the forecast models, we consider the least absolute shrinkage and selection operator (LASSO) regression and the structured regularization method for large vector autoregressive (VAR-L) model of Nicholson et al. (2017), which select automatically the google trend terms and the lags of the predictors. An out-of-sample forecast comparison reveals that reducing the high dimensional google trend data set to a low-dimensional data set by the LASSO and the VAR-L models produces better forecast performance for oil consumption compared to the frequently-used forecast models such as the autoregressive model, the autoregressive distributed lag model and the vector error correction model.

• Atmosphere
• /
• v.27 no.3
• /
• pp.261-276
• /
• 2017

The main objectives of this study are to introduce Global Seasonal forecasting system version5 (GloSea5) of KMA and to evaluate the performance of ensemble prediction of system. KMA has performed an operational seasonal forecast system which is a joint system between KMA and UK Met office since 2014. GloSea5 is a fully coupled global climate model which consists of atmosphere (UM), ocean (NEMO), land surface (JULES) and sea ice (CICE) components through the coupler OASIS. The model resolution, used in GloSea5, is N216L85 (~60 km in mid-latitudes) in the atmosphere and ORCA0.25L75 ($0.25^{\circ}$ on a tri-polar grid) in the ocean. In this research, we evaluate the performance of this system using by RMSE, Correlation and MSSS for ensemble mean values. The forecast (FCST) and hindcast (HCST) are separately verified, and the operational data of GloSea5 are used from 2014 to 2015. The performance skills are similar to the past study. For example, the RMSE of h500 is increased from 22.30 gpm of 1 week forecast to 53.82 gpm of 7 week forecast but there is a similar error about 50~53 gpm after 3 week forecast. The Nino Index of SST shows a great correlation (higher than 0.9) up to 7 week forecast in Nino 3.4 area. It can be concluded that GloSea5 has a great performance for seasonal prediction.

• Atmosphere
• /
• v.29 no.1
• /
• pp.21-39
• /
• 2019

The conventional observations of the Korea Meteorological Administration (KMA) and National Centers for Environmental Prediction (NCEP) are compared in the numerical weather forecast system at the Korea Institute of Atmospheric Prediction Systems (KIAPS). The weather forecasting system used in this study is consists of Korea Integrated Model (KIM) as a global numerical weather prediction model, three-dimensional variational method as a data assimilation system, and KIAPS Package for Observation Processing (KPOP) as an observation pre-processing system. As a result, the forecast performance of NCEP observation was better while the number of observation is similar to the KMA observation. In addition, the sensitivity of forecast performance was investigated for each SONDE, SURFACE and AIRCRAFT observations. The differences in AIRCRAFT observation were not sensitive to forecast, but the use of NCEP SONDE and SURFACE observations have shown better forecast performance. It is found that the NCEP observations have more wind observations of the SONDE in the upper atmosphere and more surface pressure observations of the SURFACE in the ocean. The results suggest that evenly distributed observations can lead to improved forecast performance.

• Atmosphere
• /
• v.28 no.4
• /
• pp.509-520
• /
• 2018

The performance of the newly designed Pusan National University Coupled General Circulation Model (PNU CGCM) Ensemble Forecast System which produce 40 ensemble members for 12-month lead prediction is evaluated and analyzed in terms of boreal winter temperature over South Korea (S. Korea). The influence of ensemble size on prediction skill is examined with 40 ensemble members and the result shows that spreads of predictability are larger when the size of ensemble member is smaller. Moreover, it is suggested that more than 20 ensemble members are required for better prediction of statistically significant inter-annual variability of wintertime temperature over S. Korea. As for the ensemble average (ENS), it shows superior forecast skill compared to each ensemble member and has significant temporal correlation with Automated Surface Observing System (ASOS) temperature at 99% confidence level. In addition to forecast skill for inter-annual variability of wintertime temperature over S. Korea, winter climatology around East Asia and synoptic characteristics of warm (above normal) and cold (below normal) winters are reasonably captured by PNU CGCM. For the categorical forecast with $3{\times}3$ contingency table, the deterministic forecast generally shows better performance than probabilistic forecast except for warm winter (hit rate of probabilistic forecast: 71%). It is also found that, in case of concentrated distribution of 40 ensemble members to one category out of the three, the probabilistic forecast tends to have relatively high predictability. Meanwhile, in the case when the ensemble members distribute evenly throughout the categories, the predictability becomes lower in the probabilistic forecast.

• Journal of the Korean earth science society
• /
• v.45 no.4
• /
• pp.327-337
• /
• 2024

The ocean is linked to long-term climate variability, but there are very few methods to assess the short-term performance of forecast models. This study analyzes the short-term prediction performance regarding ocean temperature and salinity of the Global Seasonal prediction system version 5 (GloSea5). GloSea5 is a historical climate re-creation (2001-2010) performed on the 1st, 9th, 17th, and 25th of each month. It comprises three ensembles. High-resolution hindcasts from the three ensembles were compared with the Array for Real-Time Geostrophic Oceanography (ARGO) float data for the period 2001-2010. The horizontal position was preprocessed to match the ARGO float data and the vertical layer to the GloSea5 data. The root mean square error (RMSE), Brier Score (BS), and Brier Skill Score (BSS) were calculated for short-term forecast periods with a lead-time of 10 days. The results show that sea surface temperature (SST) has a large RMSE in the western boundary current region in Pacific and Atlantic Oceans and Antarctic Circumpolar Current region, and sea surface salinity (SSS) has significant errors in the tropics with high precipitation, with both variables having the largest errors in the Atlantic. SST and SSS had larger errors during the fall for the NINO3.4 region and during the summer for the East Sea. Computing the BS and BSS for ocean temperature and salinity in the NINO3.4 region revealed that forecast skill decreases with increasing lead-time for SST, but not for SSS. The preprocessing of GloSea5 forecasts to match the ARGO float data applied in this study, and the evaluation methods for forecast models using the BS and BSS, could be applied to evaluate other forecast models and/or variables.

• Journal of the Korean earth science society
• /
• v.40 no.4
• /
• pp.382-391
• /
• 2019

The impact of vertical grid-nesting on the tropical cyclone intensity and track forecast was investigated using the Weather Research and Forecast (WRF) version 3.8 and the initialization method of the Structure Adjustable Balanced Bogus Vortex (SABV). For a better resolution in the central part of the numerical domain, where the tropical cyclone of interest is located, a horizontal and vertical nesting technique was employed. Simulations of the tropical cyclone Sanba (16th in 2012) indicated that the vertical nesting had a weak impact on the cyclone intensity and little impact on the track forecast. Further experiments revealed that the performance of forecast was quite sensitive to the horizontal resolution, which is in agreement with previous studies. The improvement is due to the fact that horizontal resolution can improve forecasts not only on the tropical cyclone-scale but also for large-scale disturbances.

• Journal of Korea Water Resources Association
• /
• v.31 no.6
• /
• pp.855-862
• /
• 1998

This paper investigates the impact of the forecast error on performance of a reservoir system for hydropower production. Forecast error is measured as th Root Mean Square Error (RMSE) and parametrically varied within a Generalized Maintenance Of Variance Extension (GMOVE) procedure. A set of transition probabilities are calculated as a function of the RMSE of the GMOVE procedure and then incorporated into a Bayesian Stochastic Dynamic Programming model which derives monthly operating policies and assesses their performance. As a case study, the proposed methodology is applied to the Skagit Hydropower System (SHS) in Washington state. The results show that the system performance is a nonlinear function of RMSE and therefor suggested that continued improvements in the current forecast accuracy correspond to gradually greater increase in performance of the SHS.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.9
• /
• pp.1700-1705
• /
• 2009

In general, short term load forecasting is based on the periodical load pattern during a day or a week. Therefore, the conventional methods do not expose stable performance to every day during a year. Especially for anomalous weather conditions such as typhoons, the methods have a tendency to show the conspicuous accuracy deterioration. Furthermore, the tendency raises the reliability and stability problems of the conventional load forecast. In this study, a new load forecasting method is proposed in order to increase the accuracy of the forecast result in case of anomalous weather conditions such as typhoons. For irregular weather conditions, the sensitivity between temperature and daily load is used to improve the accuracy of the load forecast. The proposed method was tested with the actual load profiles during 14 years, which shows that the suggested scheme considerably improves the accuracy of the load forecast results.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.468-475
• /
• 2022

Currently, fine dust forecast models are operated by dividing the country into 19 regions. Therefore, it is important to reduce the learning time and the number of models as well as accurate forecast performance to operate lots of forecast models. In this paper, we develop a categorical wide area model that outputs forecast results categorically and integrates the regions with similar regional characteristics. The proposed model improved the convergence rate by 223 times compared to the existing model, which outputs at a single concentration value, and reduced the number of forecast models by a third.