• Journal of Korea Water Resources Association
• /
• v.55 no.7
• /
• pp.495-504
• /
• 2022

With the recent development of artificial intelligence, a Long Short-Term Memory (LSTM) model that is efficient with time-series analysis is being used to increase the accuracy of predicting the inflow of dams. In this study, we predict the inflow of the Soyang River dam, using the LSTM model with the Sequence-to-Sequence (LSTM-s2s) and attention mechanism (LSTM-s2s with attention) that can further improve the LSTM performance. Hourly inflow, temperature, and precipitation data from 2013 to 2020 were used to train the model, and validate and test for evaluating the performance of the models. As a result, the LSTM-s2s with attention showed better performance than the LSTM-s2s in general as well as in predicting a peak value. Both models captured the inflow pattern during the peaks but detailed hourly variability is limitedly simulated. We conclude that the proposed LSTM-s2s with attention can improve inflow forecasting despite its limits in hourly prediction.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.887-896
• /
• 2016

The Neyman-Scott Rectangular Pulse (NSRP) model is used to model the hourly rainfall series. This model uses a modest number of parameters to represent the rainfall processes and underlying physical phenomena such as the arrival of a storm or rain cells. In this paper, we proposed approximated likelihood function for the NSRP model and applied the proposed method to precipitation data in Seoul.

• Journal of Korea Water Resources Association
• /
• v.41 no.4
• /
• pp.379-394
• /
• 2008

Recently, extreme precipitation events beyond design capacity of hydraulic system have been occurred and this is the causes of failure of hydraulic structure for flood prevention and of severe flood damage. Therefore it is very important to understand temporal and spatial characteristics of extreme precipitation events as well as expected changes in extreme precipitation events and distributional characteristics during design period under future climate change. In this paper, climate change scenarios were used to assess the impacts of future climate change on extreme precipitation. Furthermore, analysis of future extreme precipitation characteristics and I-D-F analysis were carried out. This study used SRES B2 greenhouse gas scenario and YONU CGCM to simulate climatic conditions from 2031 to 2050 and statistical downscaling method was applied to establish weather data from each of observation sites operated by the Korean Meteorological Administration. Then quantile mapping of bias correction methods was carried out by comparing the simulated data with observations for bias correction. In addition Modified Bartlett Lewis Rectangular Pulse(MBLRP) model (Onof and Wheater, 1993; Onof 2000) and adjust method were applied to transform daily precipitation time series data into hourly time series data. Finally, rainfall intensity, duration, and frequency were calculated to draw I-D-F curve. Although there are 66 observation sites in Korea, we consider here the results from only Seoul, Daegu, Jeonju, and Gwangju sites in this paper. From the results we found that the rainfall intensity will be increased and the bigger intensity will be occurred for longer rainfall duration when we compare the climate conditions of 2030s with present conditions.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.5
• /
• pp.1119-1131
• /
• 2016

The Neyman-Scott Rectangular Pulses Model (NSRPM) is mainly used to construct hourly rainfall series. This model uses a modest number of parameters to represent the rainfall processes and underlying physical phenomena, such as the arrival of storms or rain cells. In NSRPM, the method of moments has often been used because it is difficult to know the distribution of rainfall intensity. Recently, approximated likelihood function for NSRPM has been introduced. In this paper, we propose a hierarchical model for applying a spatial structure to the NSRPM parameters using the approximated likelihood function. The proposed method is applied to summer hourly precipitation data observed at 59 weather stations (Korea Meteorological Administration) from 1973 to 2011.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.415-423
• /
• 2021

Recently, an R-based point time series data validation system has been established for the statistical post processing and improvement of the National Center for AgroMeteorology-Land Atmosphere Modeling Package (NCAM-LAMP) medium-range prediction data. The time series verification system was used to compare the NCAM-LAMP with the AWS observations and GDAPS medium-range prediction model data operated by Korea Meteorological Administration. For this comparison, the model latitude and longitude data closest to the observation station were extracted and a total of nine points were selected. For each point, the characteristics of the model prediction error were obtained by comparing the daily average of the previous prediction data of air temperature, wind speed, and hourly precipitation, and then we tried to improve the next prediction data using Support Vector Machine( SVM) method. For three months from August to October 2017, the SVM method was used to calibrate the predicted time series data for each run. It was found that The SVM-based correction was promising and encouraging for wind speed and precipitation variables than for temperature variable. The correction effect was small in August but considerably increased in September and October. These results indicate that the SVM method can contribute to mitigate the gradual degradation of medium-range predictability as the model boundary data flows into the model interior.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.5
• /
• pp.819-826
• /
• 2020

The UHF band wind profiler radars of the Korea Meteorological Administration (KMA), which produces the vertical profile of the wind, need to be calibrated for better performance. The capabilities of the radar in detecting even light precipitation were used for the calibration of which reference takes the hourly series of ground rainfall rate measured by a rain gauge at the radar site. This calibration must be renewed regularly according to the methodology implemented in this work since errors occur on the wind vectors in the clear sky without reflectivity calibration. Comparing the wind by wind profiler with that by radiosonde, the optimal radar constant contributed to the improvement of wind accuracy.

• Journal of Korea Water Resources Association
• /
• v.53 no.2
• /
• pp.97-105
• /
• 2020

Recently, Artificial Neural Network receives attention as a data prediction method. Among these, a Long Shot-term Memory (LSTM) model specialized for time-series data prediction was utilized as a prediction method of hydrological time series data. In this study, the LSTM model was constructed utilizing deep running open source library TensorFlow which provided by Google, to predict inflows of multipurpose dams. We predicted the inflow of the Yongdam Multipurpose Dam which is located in the upper stream of the Geumgang. The hourly flow data of Yongdam Dam from 2006 to 2018 provided by WAMIS was used as the analysis data. Predictive analysis was performed under various of variable condition in order to compare and analyze the prediction accuracy according to four learning parameters of the LSTM model. Root mean square error (RMSE), Mean absolute error (MAE) and Volume error (VE) were calculated and evaluated its accuracy through comparing the predicted and observed inflows. We found that all the models had lower accuracy at high inflow rate and hourly precipitation data (2006~2018) of Yongdam Dam utilized as additional input variables to solve this problem. When the data of rainfall and inflow were utilized together, it was found that the accuracy of the prediction for the high flow rate is improved.

• Journal of the Korean association of regional geographers
• /
• v.17 no.4
• /
• pp.432-442
• /
• 2011

Climatic variables such as temperature and precipitation tend to vary both in space and in time simultaneously. Thus, it is necessary to include space-time autocorrelation into conventional spatial interpolation methods for reliable time-series mapping. This paper introduces and applies space-time variogram modeling and space-time kriging to generate time-series temperature maps using hourly Automatic Weather System(AWS) temperature observation data for a one-month period. First, temperature observation data are decomposed into deterministic trend and stochastic residual components. For trend component modeling, elevation data which have reasonable correlation with temperature are used as secondary information to generate trend component with topographic effects. Then, space-time variograms of residual components are estimated and modelled by using a product-sum space-time variogram model to account for not only autocorrelation both in space and in time, but also their interactions. From a case study, space-time kriging outperforms both conventional space only ordinary kriging and regression-kriging, which indicates the importance of using space-time autocorrelation information as well as elevation data. It is expected that space-time kriging would be a useful tool when a space-poor but time-rich dataset is analyzed.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.21 no.1
• /
• pp.9-17
• /
• 2003

Typhoon RUSA, which caused serious damage was passed over in Korea peninsula during 30 August to 1 September, 2002. We estimated tropospheric wet delay using GPS data and meteorological data during this period. Integrated Water Vapor(IWV) gives the total amount of water vapor from tropospheric wet delay and Precipitable Water Vapor(PWV) is calculated the IWV scaled by the density of water. We obtained GPS PWV at 13th GPS permanent stations(Seoul, Wonju. Seosan, Sangju, Junju, Cheongju, Taegu, Wuljin, Jinju, Daejeon, Mokpo, Sokcho, Jeju). We retrieve GPS data hourly and use Gipsy-Oasis II software and we compare PWV and precipitation. GPS observed PWV time series demonstrate that PWV is, in general, high before and during the occurrence of the typhoon RUSA, and low after the typhoon RUSA. GPS PWV peak time at each station is related to the progress of a typhoon RUSA. We got very near result as we compare GMS Satellite image with tomograph using GPS PWV and we could present practical use possibility by numerical model for weather forecast.

• Journal of Korean Society of Forest Science
• /
• v.94 no.6
• /
• pp.481-487
• /
• 2005

In this study, a GIS model to simulate the behavior of surface forest fires was developed on the basis of forest fire growth prediction algorithm. This model consists of three modules for data-handling, simulation and report writing. The data-handling module was designed to interpret such forest fire environment factors as terrain, fuel and weather and provide sets of data required in analyzing fire behavior. The simulation module simulates the fire and determines spread velocity, fire intensity and burnt area over time associated with terrain slope, wind, effective humidity and such fuel condition factors as fuel depth, fuel loading and moisture content for fire extinction. The module is equipped with the functions to infer the fuel condition factors from the information extracted from digital vegetation map sand the fuel moisture from the weather conditions including effective humidity, maximum temperature, precipitation and hourly irradiation. The report writer has the function to provide results of a series of analyses for fire prediction. A performance test of the model with the 2002 Chungyang forest fire showed the predictive accuracy of 61% in spread rate.