• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.327-333
• /
• 2019

Wind speed data constitute important weather information for aircrafts flying at low altitudes, such as drones. Currently, the accuracy of low altitude wind predictions is much lower than that of high-altitude wind predictions. Deep neural networks are proposed in this study as a method to improve wind speed forecast information. Deep neural networks mimic the learning process of the interactions among neurons in the brain, and it is used in various fields, such as recognition of image, sound, and texts, image and natural language processing, and pattern recognition in time-series. In this study, the deep neural network model is constructed using the wind prediction values generated by the numerical model as an input to improve the wind speed forecasts. Using the ground wind speed forecast data collected at the Boseong Meteorological Observation Tower, wind speed forecast values obtained by the numerical model are compared with those obtained by the model proposed in this study for the verification of the validity and compatibility of the proposed model.

• Atmosphere
• /
• v.24 no.2
• /
• pp.159-171
• /
• 2014

This study investigated the temporal and spatial characteristics of summertime (June-August) precipitation over Korean peninsula, using Korea Meteorological Administration (KMA)is Automated Synoptic Observing System (ASOS) data for the period of 1973-2010 and Automatic Weather System (AWS) data for the period of 1998-2010.The authors looked through climatological features of the summertime precipitation, then examined the degree of locality of the precipitation, and probable precipitation amount and its return period of 100 years (i.e., an extreme precipitation event). The amount of monthly total precipitation showed increasing trends for all the summer months during the investigated 38-year period. In particular, the increasing trends were more significant for the months of July and August. The increasing trend of July was seen to be more attributable to the increase of precipitation intensity than that of frequency, while the increasing trend of August was seen to be played more importantly by the increase of the precipitation frequency. The e-folding distance, which is calculated using the correlation of the precipitation at the reference station with those at all other stations, revealed that it is August that has the highest locality of hourly precipitation, indicating higher potential of localized heavy rainfall in August compared to other summer months. More localized precipitation was observed over the western parts of the Korean peninsula where terrain is relatively smooth. Using the 38-years long series of maximum daily and hourly precipitation as input for FARD2006 (Frequency Analysis of Rainfall Data Program 2006), it was revealed that precipitation events with either 360 mm $day^{-1}$ or 80 mm $h^{-1}$ can occur with the return period of 100 years over the Korean Peninsula.

• Journal of Wind Energy
• /
• v.14 no.3
• /
• pp.25-33
• /
• 2023

In order to secure the safety of increasing offshore activities such as offshore wind farm maintenance and fishing, IMPACT, a mid-term marine weather forecasting system, was established by predicting marine weather up to 7 days in advance. Forecast data from the Korea Hydrographic and Oceanographic Agency (KHOA), which provides the most reliable marine meteorological service in Korea, was used, but wind speed and wave height forecast errors increased as the leading forecast period increased, so improvement of the accuracy of the model results was needed. The Model Output Statistics (MOS) method, a post-correction method using statistical machine learning, was applied to improve the prediction accuracy of wave height, which is an important factor in forecasting the risk of marine activities. Compared with the observed data, the wave height prediction results by the model before correction for 6 to 7 days ahead showed an RMSE of 0.692 m and R of 0.591, and there was a tendency to underestimate high waves. After correction with the MOS technique, RMSE was 0.554 m and R was 0.732, confirming that accuracy was significantly improved.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.147-147
• /
• 2019

The Numerical Weather Prediction (NWP) models determine the future state of the weather by forcing current weather conditions into the atmospheric models. The NWP models approximate mathematically the physical dynamics by nonlinear differential equations; however these approximations include uncertainties. The errors of the NWP estimations can be related to the initial and boundary conditions and model parameterization. Development in the meteorological forecast models did not solve the issues related to the inevitable biases. In spite of the efforts to incorporate all sources of uncertainty into the forecast, and regardless of the methodologies applied to generate the forecast ensembles, they are still subject to errors and systematic biases. The statistical post-processing increases the accuracy of the forecast data by decreasing the errors. Error prediction of the NWP models which is updating the NWP model outputs or model output statistics is one of the ways to improve the model forecast. The regression methods (including linear, polynomial and scaling regression) are applied to the present study to improve the real time forecast skill. Such post-processing consists of two main steps. Firstly, regression is built between forecast and measurement, available during a certain training period, and secondly, the regression is applied to new forecasts. In this study, the WRF real-time forecast data, in comparison with the observed data, had systematic biases; the errors related to the NWP model forecasts were reflected in the underestimation of the meteorological data forecast by the WRF model. The promising results will indicate that the post-processing techniques applied in this study improved the meteorological forecast data provided by WRF model. A comparison between various bias correction methods will show the strength and weakness of the each methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.129-135
• /
• 2015

This study, in the operation of street lamp, suggests appropriate algorithm to extend the number of days of street lamp operation as much as possible if the number of sunless days continues and experimentally determines the value of Weather Factor necessary for this algorithm. This is conducted by reducing electricity consumption and securing battery remains through the use of standby power mode, in which maximum amount of light is maintained if there is a pedestrian, and constant brightness is maintained without utilizing maximum electric power if no pedestrians exist, with the application of WFactor value created by the algorithm considering weather forecast and amount of sunlight.

• Atmosphere
• /
• v.28 no.2
• /
• pp.201-209
• /
• 2018

Benefits of the next generation geostationary meteorological satellite observation (e.g., GEO-KOMPSAT-2A) are qualitatively and comprehensively described and discussed. Main beneficial phenomena for application can be listed as tropical cyclones (typhoon), high impact weather (heavy rainfall, lightning, and hail), ocean, air pollution (particulate matter), forest fire, fog, aircraft icing, volcanic eruption, and space weather. The next generation satellites with highly enhanced spatial and temporal resolution images, expanding channels, and basic and additional products are expected to create the new valuable benefits, including the contribution to the reduction of socioeconomic losses due to weather-related disasters. In particular, the new satellite observations are readily applicable to early warning and very-short time forecast application of hazardous weather phenomena, global climate change monitoring and adaptation, improvement of numerical weather forecast skill, and technical improvement of space weather monitoring and forecast. Several policy plans for expanding the application of the next generation satellite data are suggested.

• Atmosphere
• /
• v.31 no.1
• /
• 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.

• Atmosphere
• /
• v.23 no.4
• /
• pp.485-500
• /
• 2013

This study conducted WRF-Fire simulations in order to investigate sensitivities of the resolution of fire fuel and terrain data sets, and the surface wind to simulated fire area. The sensitivity simulations were consisted of 8 different WRF-Fire runs, each of which used different combination of data sets of fire fuel and terrain with different resolution. From the results it was turned out that the surface wind was most sensitive. The next was fire fuel and then fire terrain. Unfortunately, every run produced too much fire area. In other words no simulations succeeded in simulating such proper fire area so as for the WRF-Fire to be used realistically. It was verified that the errors of fire area from each runs were contributed by 41%, 53%, and 6% from surface wind, fire fuel, and fire terrain, respectively. Finally this study suggested that the selection of Anderson fuel category in the area of interest seemed to be very critical in the performance of WRF-Fire simulations.

• Journal of Environmental Science International
• /
• v.27 no.7
• /
• pp.531-541
• /
• 2018

Road freezing caused by snowfall during wintertime causes traffic congestion and many accidents. To prevent such problems, we developed, in this study, a system to predict road freezing based on weather forecast data and the freezing generation modules. The weather forecast data were obtained from a high-resolution model with 1 km resolution for Jeju Island from 00:00 KST on December 1, 2017, to 23:00 KST on February 28, 2018. The results of the weather forecast data show that index of agreement (IOA) temperature was higher than 0.85 at all points, and that for wind speed was higher than 0.7 except in Seogwipo city. In order to evaluate the results of the freezing predictions, we used model evaluation metrics obtained from a confusion matrix. These metrics revealed that, the Imacho module showed good performance in precision and accuracy and that the Karlsson module showed good performance in specificity and FP rate. In particular, Cohen's kappa value was shown to be excellent for both modules, demonstrating that the algorithm is reliable. The superiority of both the modules shows that the new system can prevent traffic problems related to road freezing in the Jeju area during wintertime.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.101.2-101.2
• /
• 2011

We have developed solar and space weather monitoring system for space weather users since 2007 as a project named 'Construction of Korea Space Weather Prediction Center'. In this presentation we will introduce space weather monitoring system for Geostationary Satellites and Polar Routes. These were developed for satisfying demands of space weather user groups. 'Space Weather Monitoring System for Geostationary Satellites' displays integrated space weather information on geostationary orbit such as magnetopause location, nowcast and forecast of space weather, cosmic ray count rate, number of meteors and x-ray solar flux. This system is developed for space weather customers who are managing satellite systems or using satellite information. In addition, this system provides space weather warning by SMS in which short message is delivered to users' cell phones when space weather parameters reach a critical value. 'Space Weather Monitoring System for Polar Routes' was developed for the commercial airline companies operating polar routes. This provides D-region and polar cap absorption map, aurora and radiation particle distribution, nowcast and forecast of space weather, proton flux, Kp index and so on.