• Journal of Advanced Navigation Technology
• /
• v.21 no.4
• /
• pp.365-370
• /
• 2017

This study analyze correlation between weekdays data and special days data of different power demand patterns, and builds a separate data set, and suggests ways to reduce power demand prediction error by using deep learning network suitable for each data set. In addition, we propose a method to improve the prediction rate by adding the environmental elements and the separating element to the meteorological element, which is a basic power demand prediction elements. The entire data predicted power demand using LSTM which is suitable for learning time series data, and the special day data predicted power demand using DNN. The experiment result show that the prediction rate is improved by adding prediction elements other than meteorological elements. The average RMSE of the entire dataset was 0.2597 for LSTM and 0.5474 for DNN, indicating that the LSTM showed a good prediction rate. The average RMSE of the special day data set was 0.2201 for DNN, indicating that the DNN had better prediction than LSTM. The MAPE of the LSTM of the whole data set was 2.74% and the MAPE of the special day was 3.07 %.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.7
• /
• pp.730-735
• /
• 2014

This paper introduces a GP (Genetic Programming) based robust technique for the prediction of a heavy rain newsflash. The nature of prediction for precipitation is very complex, irregular and highly fluctuating. Especially, the prediction of heavy precipitation is very difficult. Because not only it depends on various elements, such as location, season, time and geographical features, but also the case data is rare. In order to provide a robust model for precipitation prediction, a nonlinear and symbolic regression method using GP is suggested. The remaining part of the study is to evaluate the performance of prediction for a heavy rain newsflash using a GP based nonlinear regression technique in Korean regions. Analysis of the feature selection is executed and various fitness functions are proposed to improve performances. The KLAPS data of 2006-2010 is used for training and the data of 2011 is adopted for verification.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.521-529
• /
• 2020

Forest fires are one of the most important environmental risks that have adverse effects on many aspects of life, such as the economy, environment, and health. The early detection, quick prediction, and rapid response of forest fires can play an essential role in saving property and life from forest fire risks. For the rapid discovery of forest fires, there is a method using meteorological data obtained from local sensors installed in each area by the Meteorological Agency. Meteorological conditions (e.g., temperature, wind) influence forest fires. This study evaluated a Data Mining (DM) approach to predict the burned area of forest fires. Five DM models, e.g., Stochastic Gradient Descent (SGD), Support Vector Machines (SVM), Decision Tree (DT), Random Forests (RF), and Deep Neural Network (DNN), and four feature selection setups (using spatial, temporal, and weather attributes), were tested on recent real-world data collected from Gyeonggi-do area over the last five years. As a result of the experiment, a DNN model using only meteorological data showed the best performance. The proposed model was more effective in predicting the burned area of small forest fires, which are more frequent. This knowledge derived from the proposed prediction model is particularly useful for improving firefighting resource management.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.569-575
• /
• 2021

Deep learning shows differences in prediction performance depending on data quality and model. This study uses various input data and multiple deep learning models to build an optimal deep learning model for predicting solar radiation, which has the most influence on power generation prediction. did. As the input data, the weather data of the Korea Meteorological Administration and the clairvoyant meteorological image were used by segmenting the image of the Korea Meteorological Agency. , comparative evaluation, and predicting solar radiation by constructing multiple deep learning models connecting the models with the best error rate in each model. As an experimental result, the RMSE of model A, which is a multiple deep learning model, was 0.0637, the RMSE of model B was 0.07062, and the RMSE of model C was 0.06052, so the error rate of model A and model C was better than that of a single model. In this study, the model that connected two or more models through experiments showed improved prediction rates and stable learning results.

• Atmosphere
• /
• v.21 no.1
• /
• pp.1-16
• /
• 2011

Numerical prediction capability has been improved over the decades, but progress of prediction for high-impact weather (HIW) was unsatisfactory. One reason of low predictability for HIW is lack of observation data. The National Institute of Meteorological Research (NIMR) has been performed observation program for improvement of predictability, and reduction in social and economical cost for HIW. As part of this observation program, summer intensive observation program (ProbeX-2009) was performed at the observation-gap areas from 25 August to 6 September 2009. Sounding observations using radiosonde were conducted in the Gisang2000 research vessel (R/V) from the Korea Meteorological Administration (KMA) over the West Sea and the Eardo R/V from the Korea Ocean Research and Development Institute (KORDI) over the South Sea. Observation System Experiment (OSE) is carried out to examine the effect of ProbeX-2009 data. OSEs using Korea Local Analysis and Prediction System (KLAPS) and Weather Research and Forecasting (WRF) Model are conducted to investigate the predictability for a short time forecast. And, OSEs using WRF/3DVAR system and WRF forecast model are conducted to study the predictability for an extended time. Control experiment (K_CTL and CNTL) used only GTS observation and experiment (K_EXP and SWEXP) used ProbeX-2009 data from two system are performed. ETS for 3hr accumulated rainfall simulated by KLAPS-WRF shows that K_EXP is higher than K_CTL. Also, ETS for 12hr accumulated rainfall of SWEXP from 3DVAR-WRF is higher than CNTL. The results indicate that observation over the ocean has positive impact on HIW prediction.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.491-493
• /
• 2022

Flood damage due to torrential rains and typhoons is occurring in many parts of the world. In this paper, we propose a water level prediction model using water level, precipitation, and humidity data, which are key parameters for flood prediction, as input data. Based on the LSTM and GRU models, which have already proven time-series data prediction performance in many research fields, different input datasets were constructed using the ASOS(Automated Synoptic Observing System) data and AWS(Automatic Weather System) data provided by the Korea Meteorological Administration, and performance comparison experiments were conducted. As a result, the best results were obtained when using ASOS data. Through this paper, a performance comparison experiment was conducted according to the input data, and as a future study, it is thought that it can be used as an initial study to develop a system that can make an evacuation decision in advance in connection with the flood risk determination model.

• Journal of Environmental Impact Assessment
• /
• v.5 no.1
• /
• pp.95-105
• /
• 1996

Meteorological Joint Frequency Function required indispensably in long-term air quality prediction models were discussed for practical application in Korea. The algorithm, proposed by Turner(l964), is processed with daily solar insolation and cloudiness and height basically using Pasquill's atmospheric stability classification method. In spite of its necessity and applicability, the computer program, called STAR(STability ARray), had some significant difficulties caused from the difference in meteorological data format between that of original U.S. version and Korean's. To cope with the problems, revised STAR program for Korean users were composed of followings; applicability in any site of Korea with regard to local solar angle modification; feasibility with both of data which observed by two classes of weather service centers; and examination on output format associated with prediction models which should be used.

• Journal of Korean Society for Atmospheric Environment
• /
• v.20 no.4
• /
• pp.523-537
• /
• 2004

In order to raise the accuracy of meteorological data, several numerical experiments about the usefulness of data assimilation to prediction of air pollution was carried out. Used data for data assimilation are surface meteorological components observed by Automatical Weather System with high spatial density. The usage of surface data assimilation gives changes of temperature and wind fields and the change caused by the influence of land-use on meterological simulation is more sensitive at night than noon. The data quality in assimilation it also one of the important factors to predict the meteorological field precisely and through the static IOA (Index of Agreement), simulated meteorological components with selected limited surface data assimilation are agree well with observations.

• Atmosphere
• /
• v.22 no.2
• /
• pp.267-277
• /
• 2012

The objectives of this study are to develop a real-time drought monitoring and prediction system on the East Asia domain and to evaluate the performance of the system by using past historical drought records. The system is mainly composed of two parts: drought monitoring for providing current drought indices with meteorological and hydrological conditions; drought outlooks for suggesting future drought indices and future hydrometeorological conditions. Both parts represent the drought conditions on the East Asia domain (latitude $21.15{\sim}50.15^{\circ}$, longitude $104.40{\sim}149.65^{\circ}$), Korea domain (latitude $30.40{\sim}43.15^{\circ}$, longitude $118.65{\sim}135.65^{\circ}$) and South Korea domain (latitude $30.40{\sim}43.15^{\circ}$, longitude $118.65{\sim}135.65^{\circ}$), respectively. The observed meteorological data from ASOS (Automated Surface Observing System) and AWS (Automatic Weather System) of KMA (Korean Meteorological Administration) and model-driven hydrological data from LSM (Land Surface model) are used for the real-time drought monitoring, while the monthly and seasonal weather forecast information from UM (Unified Model) of KMA are utilized for drought outlooks. For the evaluation of the system, past historical drought records occurred in Korea are surveyed and are compared with the application results of the system. The results demonstrated that the selected drought indices such as KMA drought index, SPI (3), SPI (6), PDSI, SRI and SSI are reasonable, especially, the performance of SRI and SSI provides higher accuracy that the others.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.4
• /
• pp.844-853
• /
• 2005

Red tide(harmful algae) in the Korean Coastal Waters has a given a given damage to the fishery every year. However, the aim of our study understands the influence of meteorological factors (air and water temperature, precipitation sunshine, solar radiation, winds) relating to the mechanism of red tide occurrence and monitors red tide by satellite remote sensing, and analyzes the potential area for red tide occurrence by GIS. The meteorological factors have directly influenced on red tide formation. Thus, We want to predict and apply to red tide formation from statistical analyses on the relationships between red tide formation and meteorological factors. In future, it should be realized the near real time monitoring for red tide by the development of remote sensing technique and the construction of integrated model by the red tide information management system (the data base of red tide - meteorological informations. Finally our purpose is support to the prediction information for the possible red tide occurrence by coastal meteorological information and contribute to reduce the red tide disaster by the prediction technique for red tide.