• 대기
• /
• 제31권1호
• /
• pp.73-83
• /
• 2021

Numerical weather prediction (NWP) models play an essential role in predicting weather factors, but using them is challenging due to various factors. To overcome the difficulties of NWP models, deep learning models have been deployed in weather forecasting by several recent studies. This study adapts long short-term memory (LSTM), which demonstrates remarkable performance in time-series prediction. The combination of LSTM model input of meteorological features and activation functions have a significant impact on the performance therefore, the results from 5 combinations of input features and 4 activation functions are analyzed in 9 Automated Surface Observing System (ASOS) stations corresponding to cities/islands/mountains. The optimized LSTM model produces better performance within eight forecast hours than Local Data Assimilation and Prediction System (LDAPS) operated by Korean meteorological administration. Therefore, this study illustrates that this LSTM model can be usefully applied to very short-term weather forecasting, and further studies about CNN-LSTM model with 2-D spatial convolution neural network (CNN) coupled in LSTM are required for improvement.

• 대기
• /
• 제21권1호
• /
• pp.85-93
• /
• 2011

UK Met Office Unified Model (UM) is a grid model applicable for both global and regional model configurations. The Met Office has developed a 4D-Var data assimilation system, which was implemented in the global forecast system on 5 October 2004. In an effort to improve its Numerical Weather Prediction (NWP) system, Korea Meteorological Administration (KMA) has adopted the UM system since 2008. The aim of this study is to provide the basic information on the effects of satellite data assimilation on UM performance by conducting global satellite data denial experiments. Advanced Tiros Operational Vertical Sounder (ATOVS), Infrared Atmospheric Sounding Interferometer (IASI), Special Sensor Microwave Imager Sounder (SSMIS) data, Global Positioning System Radio Occultation (GPSRO) data, Air Craft (CRAFT) data, Atmospheric Infrared Sounder (AIRS) data were assimilated in the UM global system. The contributions of assimilation of each kind of satellite data to improvements in UM performance were evaluated using analysis data of basic variables; geopotential height at 500 hPa, wind speed and temperature at 850 hPa and mean sea level pressure. The statistical verification using Root Mean Square Error (RMSE) showed that most of the satellite data have positive impacts on UM global analysis and forecasts.

• 디지털융복합연구
• /
• 제17권4호
• /
• pp.107-114
• /
• 2019

본 연구는 전년도 악재를 경험한 기업에서 경영자가 자발적으로 공시하는 미래 경영성과의 정확성이 경영자 보상에 미치는 영향에 대하여 분석하고자 한다. 전년도에 악재를 경험한 기업의 경우 불확실한 미래에 대한 예측 능력이 더욱 중요시 될 것이며 이에 따라 우수한 예측 능력을 가진 경영자에게 더 높은 보상을 지급할 것이라고 기대하였다. 본 연구의 분석결과 전년도에 악재를 경험한 기업의 경영자 이익 예측 정확성과 경영자 보상간의 관련성에 음(-)의 유의한 관계가 나타났으며, 이는 전년도에 악재를 경험한 기업일수록 당기 성과에 대한 경영자의 공시의 정확성이 중시되며, 시장에 경영자의 능력을 알리고자하는 신호 및 미래 불확실성을 줄이고자 하는 경영자의 노력 투입의 유인이 되어 경영 성과가 높아짐에 따라 경영자 보상이 높아지는 것으로 볼 수 있다. 본 연구는 우수한 예측능력을 가진 경영자가 많은 보상을 받을 것이라는 선행연구를 확장하여 전년도의 경영성과가 호재 혹은 악재인지에 따라 예측능력의 중요성이 차별적으로 경영자 보상에 영향을 미친다는 것을 검증하였다는 것에 차별성이 존재하며, 경영자 보상 계약에 영향을 미치는 결정요인을 추가적으로 파악했다는 것에 의의가 있다.

• 한국지구과학회지
• /
• 제36권2호
• /
• pp.158-170
• /
• 2015

큰 에디 모의과정을 포함한 WRF 모델 (WRF-LES)을 이용하여 수치모델의 수평공간 규모에 따른 대기경계층 모수화 실험과 LES 모의 결과를 지표층 근처의 풍속 예측에 대하여 비교하였다. 수치실험은 복잡한 산악지형과 해안지역을 포함하는 강원도 지역에서 수평해상도 1 km와 333 m 실험을 수행하였다. 수평해상도 1 km 실험은 대기경계층 모수화 방안을 채택하였으며, 333 m 실험에서는 LES를 이용하였다. 복잡한 산악지역에서의 풍속 예측의 정확성은 수평해상도 1 km 실험 보다 333 m 실험에서 향상되었으며 해안지역에서는 1 km 실험에서 관측과 더 일치하였다. 지표층 근처의 큰 난류를 직접 계산하는 LES 실험은 산악지역의 풍속예측 개선에 기여하였다.

• 디지털융복합연구
• /
• 제16권10호
• /
• pp.125-132
• /
• 2018

본 연구는 경영자 능력의 대용치로 경영자가 자발적으로 공시하는 미래 기업의 성과에 대한 정보인 이익 예측 정확성을 사용하여, 미래 이익을 정확하게 예측하는 경영자의 우수한 능력이 높을수록 경영자 성과-보상에 어떠한 영향을 미치는지에 대해 분석하고자 한다. 본 연구의 분석결과, 이익 예측 정확성과 경영자 보상 사이의 유의한 양(+)의 관계가 나타났으며, 이는 미래에 대한 예측이 우수한 경영자의 능력을 경영자 보상 계약에 반영한 결과로 볼 수 있다. 본 연구는 기존 선행연구에서 경영자의 능력의 대용치로 회계성과 변수를 주로 사용하여 경영자 보상 계약을 확인한 것을 확장하여 미래 기업이 직면할 상황을 정확하게 예측하는 경영자의 능력이 경영자 보상에 영향을 미치는 주요한 결정 요인임을 검증하였다는 것에 차별성이 존재한다. 따라서 기업의 미래에 대한 예측 역시 중요한 경영자의 역량으로 경영자 보상 계약에 영향을 미치는 추가적인 결정요인을 파악했다는 것에 의의가 있다.

• 대기
• /
• 제16권2호
• /
• pp.141-157
• /
• 2006

A revolution in weather and climate forecasting is in progress. This has been made possible as a result of theoretical advances in our understanding of the predictability of weather and climate, and by the extraordinary developments in supercomputer technology. New problem areas have been discovered and different solutions have been found by the recent high performance computers whose performance has been increased rapidly. Such advances in the computational performance may change the strategy of development of numerical models and prediction methods. This paper discusses a brief history and current status of the supercomputers in institutions for research and forecast of weather/climate. The main purpose of this study is to provide the preliminary information about supercomputers such as architecture of system and processor. Such information would be useful for meteorologists to understand the features and the preference of supercomputers in each institution.

• 대기
• /
• 제24권3호
• /
• pp.419-432
• /
• 2014

An assessment of typhoon intensity predictability of numerical models was conducted to develop the typhoon intensity forecast guidance comparing with the RSMC-Tokyo best track data. Root mean square error, box plot analysis and time series of wind speed comparison were performed to evaluate the each model error level. One of noticeable fact is that all models have a trend of error increase as typhoon becomes stronger and the Global Forecast System showed the best performance among the models. In the detailed analysis in two typhoon cases [Danas (1324) and Haiyan (1330)], GFS showed good performance in maximum wind speed and intensity trend in the best track, however it could not simulate well the rapid intensity increasing period. On the other hand, ECMWF and Hurricane-WRF overestimated the typhoon intensity but simulated track trend well.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1690-1707
• /
• 2021

Precipitation prediction during flood season has been a key task of climate prediction for a long time. This type of prediction is linked with the national economy and people's livelihood, and is also one of the difficult problems in climatology. At present, there are some precipitation forecast models for the flood season, but there are also some deviations from these models, which makes it difficult to forecast accurately. In this paper, based on the measured precipitation data from the flood season from 1993 to 2019 and the precipitation return data of CWRF, ANN cycle modeling and a weighted integration method is used to correct the CWRF used in today's operational systems. The MAE and TCC of the precipitation forecast in the flood season are used to check the prediction performance of the proposed algorithm model. The results demonstrate a good correction effect for the proposed algorithm. In particular, the MAE error of the new algorithm is reduced by about 50%, while the time correlation TCC is improved by about 40%. Therefore, both the generalization of the correction results and the prediction performance are improved.

• 대기
• /
• 제25권2호
• /
• pp.375-387
• /
• 2015

A Selected Multi-model CONsensus (SMCON) technique was developed and verified for the tropical cyclone track forecast in the western North Pacific. The SMCON forecasts were produced by averaging numerical model forecasts showing low 70% latest 6 h prediction errors among 21 models. In the homogeneous comparison for 54 tropical cyclones in 2013 and 2014, the SMCON improvement rate was higher than the other forecasts such as the Non-Selected Multi-model CONsensus (NSMCON) and other numerical models (i.e., GDAPS, GEPS, GFS, HWRF, ECMWF, ECMWF_H, ECMWF_EPS, JGSM, TEPS). However, the SMCON showed lower or similar improvement rate than a few forecasts including ECMWF_EPS forecasts at 96 h in 2013 and at 72 h in 2014 and the TEPS forecast at 120 h in 2013. Mean track errors of the SMCON for two year were smaller than the NSMCON and these differences were 0.4, 1.2, 5.9, 12.9, 8.2 km at 24-, 48-, 72-, 96-, 120-h respectively. The SMCON error distributions showed smaller central tendency than the NSMCON's except 72-, 96-h forecasts in 2013. Similarly, the density for smaller track errors of the SMCON was higher than the NSMCON's except at 72-, 96-h forecast in 2013 in the kernel density estimation analysis. In addition, the NSMCON has lager range of errors above the third quantile and larger standard deviation than the SMCON's at 72-, 96-h forecasts in 2013. Also, the SMCON showed smaller bias than ECMWF_H for the cross track bias. Thus, we concluded that the SMCON could provide more reliable information on the tropical cyclone track forecast by reflecting the real-time performance of the numerical models.