• Journal of Electrical Engineering and Technology
• /
• v.8 no.3
• /
• pp.559-564
• /
• 2013

In this paper a new hybrid forecast method composed of wavelet transform and neural network is proposed to forecast the wind speed more accurately. In the field of wind energy research, accurate forecast of wind speed is a challenging task. This will influence the power system scheduling and the dynamic control of wind turbine. The wind data used here is measured at 15 minute time intervals. The performance is evaluated based on the metrics, namely, mean square error, mean absolute error, sum squared error of the proposed model and compared with the back propagation model. Simulation studies are carried out and it is reported that the proposed model outperforms the compared model based on the metrics used and conclusions were drawn appropriately.

• Journal of Wetlands Research
• /
• v.13 no.1
• /
• pp.13-23
• /
• 2011

In this study, Mike11 will be used as the numerical model where a data assimilation method will be applied to it. This paper aims to gain an insight and understanding of data assimilation in flood forecasting models. It will start with a general discussion of data assimilation, followed by a description of the methodology and discussion of the statistical error forecast model used, which in this case is the linear regression. This error forecast model is applied to the water level forecast simulated by MIKE11 to produced improved forecast and validated against real measurements. It is found that there exists a phase error in the improved forecasts. Hence, 2 general formula are used to account for this phase error and they have shown improvement to the accuracy of the forecasts, where one improved the immediate forecast of up to 5 hours while the other improved the estimation of the peak discharge.

• Journal of Korea Water Resources Association
• /
• v.44 no.11
• /
• pp.853-861
• /
• 2011

The objective of this study is to assess Sejong University River Forecast (SURF) model which consists of a continuous rainfall-runoff model and measured streamflow assimilation using ensemble Kalman filter technique for streamflow forecast on Nakdong river basin. The study area is divided into 43 subbasins. The forecasted streamflows are evaluated at 12 measurement sites during flood season from 2006 to 2007. The forecasted ones are improved due to the impact of the measured streamflows assimilation. In effectiveness indices corresponding to 1~5 h forecast lead times, the accuracy of the forecasted streamflows with the assimilation approach is improved by 46.2~30.1% compared with that using only the rainfall-runoff model. The mean normalized absolute error of forecasted peak flow without and with data assimilation approach in entering 50% of the measured rainfall, respectively, the accuracy of the latter is improved about 40% than that of the former. From these results, SURF model is able to be used as a real-time river forecast model.

• The Plant Pathology Journal
• /
• v.26 no.1
• /
• pp.37-48
• /
• 2010

This paper describes a web-based information system for plant disease forecast that was developed for crop growers in Gyeonggi-do, Korea. The system generates hourly or daily warnings at the spatial resolution of $240\;m{\times}240\;m$ based on weather data. The system consists of four components including weather data acquisition system, job process system, data storage system, and web service system. The spatial resolution of disease forecast is high enough to estimate daily or hourly infection risks of individual farms, so that farmers can use the forecast information practically in determining if and when fungicides are to be sprayed to control diseases. Currently, forecasting models for blast, sheath blight, and grain rot of rice, and scab and rust of pear are available for the system. As for the spatial interpolation of weather data, the interpolated temperature and relative humidity showed high accuracy as compared with the observed data at the same locations. However, the spatial interpolation of rainfall and leaf wetness events needs to be improved. For rice blast forecasting, 44.5% of infection warnings based on the observed weather data were correctly estimated when the disease forecast was made based on the interpolated weather data. The low accuracy in disease forecast based on the interpolated weather data was mainly due to the failure in estimating leaf wetness events.

• Korean Management Science Review
• /
• v.26 no.1
• /
• pp.77-91
• /
• 2009

It is the most important sucess factor for the electricity generation industry to minimize operations cost of surplus electricity generation through accurate demand forecasts. Temperature forecast is a significant input variable, because power demand is mainly linked to the air temperature. This study estimates the information value of the temperature forecast by analyzing the relationship between electricity load and daily air temperature in Korea. Firstly, several characteristics was analyzed by using a population-weighted temperature index, which was transformed from the daily data of the maximum, minimum and mean temperature for the year of 2005 to 2007. A neural network-based load forecaster was derived on the basis of the temperature index. The neural network then was used to evaluate the performance of load forecasts for various types of temperature forecasts (i.e., persistence forecast and perfect forecast) as well as the actual forecast provided by KMA(Korea Meteorological Administration). Finally, the result of the sensitivity analysis indicates that a $0.1^{\circ}C$ improvement in forecast accuracy is worth about $11 million per year.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.14 no.4
• /
• pp.265-268
• /
• 2012

There are increasing number of allergic patients due to the increasing outdoor activities and allergenic pollens by local climate changes. Korea Meteorological Administration provides daily forecasts for pollen allergy warnings on the Internet. The forecast models are composed of pollen concentration models and risk grade levels. The accuracy of the models was determined in terms of risk grade. Pollen concentration models were developed using the observed data during from 2001 to 2006 and accuracy was validated against the data during from 2010 to 2011. The accuracy was different from location to location. The accuracy for most tree species was higher in April than that in May. The accuracy for weed species was higher in October than in September. Our result suggest that the models presented in this study can be used to estimate daily number and risk grade of pollens.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.8-14
• /
• 2020

The human impact of particulate matter are revealed and demand for improved forecast accuracy is increasing. Recently, efforts is made to improve the accuracy of PM10 predictions by using machine learning, but prediction performance is decreasing due to the particulate matter data with a large rate of low concentration occurrence. In this paper, separation prediction model by concentration is proposed to improve the accuracy of PM10 particulate matter forecast. The low and high concentration prediction model was designed using the weather and air pollution factors in Cheonan, and the performance comparison with the prediction models was performed. As a result of experiments with RMSE, MAPE, correlation coefficient, and AQI accuracy, it was confirmed that the predictive performance was improved, and that 20.62% of the AQI high-concentration prediction performance was improved.

• Journal of Digital Convergence
• /
• v.17 no.4
• /
• pp.107-114
• /
• 2019

This study analyzes the effect of the accuracy of future management performance, which managers voluntarily announce in the previous year's disclosure, on managers compensation. In the case of a company that disclosed the bad news in the previous year, the ability to predict uncertain future will be more important, and expects executives with better predictability to receive more compensation. The results of this study show that there is a significant negative(-) relationship between the accuracy of the manager's earnings forecast and the performance - compensation of the firms that disclosed the bad news in the previous year. The accuracy of the manager's disclosure is important, and it is confirmed that the manager's compensation increases as the incentive of the manager's effort to reduce future uncertainty. The results of this study are as follows: there is a positive relationship between the managerial performance and the managerial competence of managers. It is important to note that there is a difference and that we have identified additional determinants of the manager compensation contract.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.10
• /
• pp.159-168
• /
• 2022

The time series of foreign trade turnover is complex and variable and contains linear and nonlinear information. This paper proposes preprocessing the dataset by the EMD algorithm and combining the linear prediction advantage of the SARIMA model with the nonlinear prediction advantage of the EMD-LSTM model to construct the SARIMA-EMD-LSTM hybrid model by the weight assignment method. The forecast performance of the single models is compared with that of the hybrid models by using MAPE and RMSE metrics. Furthermore, it is confirmed that the weight assignment approach can benefit from the hybrid models. The results show that the SARIMA model can capture the fluctuation pattern of the time series, but it cannot effectively predict the sudden drop in foreign trade turnover caused by special reasons and has the lowest accuracy in long-term forecasting. The EMD-LSTM model successfully resolves the hysteresis phenomenon and has the highest forecast accuracy of all models, with a MAPE of 7.4304%. Therefore, it can be effectively used to forecast the Sino-Russia foreign trade turnover time series post-epidemic. Hybrid models cannot take advantage of SARIMA linear and LSTM nonlinear forecasting, so weight assignment is not the best method to construct hybrid models.

• Atmosphere
• /
• v.33 no.5
• /
• pp.441-456
• /
• 2023

The mobile observation method, in which a meteorological drone observes while ascending, can observe the vertical profile of wind at 1 m-interval. In addition, since continuous flights are possible at time intervals of less than 30 minutes, high-resolution observation data can be obtained both spatially and temporally. In this study, we verify the accuracy of mobile observation data from meteorological drone (drone) and fill the spatio-temporal observation gaps in the lower atmosphere. To verify the accuracy of mobile observation data observed by drone, it was compared with rawinsonde observation data. The correlation coefficients between two equipment for a wind speed and direction were 0.89 and 0.91, and the root mean square errors were 0.7 m s^-1 and 20.93°. Therefore, it was judged that the drone was suitable for observing vertical profile of the wind using mobile observation method. In addition, we attempted to resolve the observation gaps in the lower atmosphere. First, the vertical observation gaps of the wind profiler between the ground and the 150 m altitude could be resolved by wind observation data using the drone. Secondly, the temporal observation gaps between 3-hour interval in the rawinsonde was resolved through a drone observation case conducted in Taean-gun, Chungcheongnam-do on October 13, 2022. In this case, the drone mobile observation data every 30-minute intervals could observe the low-level jet more detail than the rawinsonde observation data. These results show that the mobile observation data of the drone can be used to fill the spatio-temporal observation gaps in the lower atmosphere.