• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.373-373
• /
• 2021

Rainfall forecasting is an important issue that is applied in many areas, such as agriculture, flood warning, and water resources management. In this context, this study proposed a statistical and machine learning-based forecasting model for monthly rainfall. The Bayesian Gaussian process was chosen to optimize the hyperparameters of the Stacked Long Short-term memory (SLSTM) model. The proposed SLSTM model was applied for predicting monthly precipitation of Seoul station, South Korea. Data were retrieved from the Korea Meteorological Administration (KMA) in the period between 1960 and 2019. Four schemes were examined in this study: (i) prediction with only rainfall; (ii) with deseasonalized rainfall; (iii) with rainfall and minimum temperature; (iv) with deseasonalized rainfall and minimum temperature. The error of predicted rainfall based on the root mean squared error (RMSE), 16-17 mm, is relatively small compared with the average monthly rainfall at Seoul station is 117mm. The results showed scheme (iv) gives the best prediction result. Therefore, this approach is more straightforward than the hydrological and hydraulic models, which request much more input data. The result indicated that a deep learning network could be applied successfully in the hydrology field. Overall, the proposed method is promising, given a good solution for rainfall prediction.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.2
• /
• pp.69-79
• /
• 2017

In this study, we developed real-time urban stream discharge forecasting model using short-term rainfall forecasts data simulated by a regional climate model (RCM). The National Centers for Environmental Prediction (NCEP) Climate Forecasting System (CFS) data was used as a boundary condition for the RCM, namely the Global/Regional Integrated Model System(GRIMs)-Regional Model Program (RMP). In addition, we make ensemble (ESB) forecast with different lead time from 1-day to 3-day and its accuracy was validated through temporal correlation coefficient (TCC). The simulated rainfall is compared to observed data, which are automatic weather stations (AWS) data and Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis (TMPA 3B43; 3 hourly rainfall with $0.25^{\circ}{\times}0.25^{\circ}$ resolution) data over midland of Korea in July 26-29, 2011. Moreover, we evaluated urban rainfall-runoff relationship using Storm Water Management Model (SWMM). Several statistical measures (e.g., percent error of peak, precent error of volume, and time of peak) are used to validate the rainfall-runoff model's performance. The correlation coefficient (CC) and the Nash-Sutcliffe efficiency (NSE) are evaluated. The result shows that the high correlation was lead time (LT) 33-hour, LT 27-hour, and ESB forecasts, and the NSE shows positive values in LT 33-hour, and ESB forecasts. Through this study, it can be expected to utilizing the real-time urban flood alert using short-term weather forecast.

• Journal of Korea Water Resources Association
• /
• v.49 no.1
• /
• pp.41-49
• /
• 2016

This study proposed a new drought index considering the accumulative pattern of daily rainfall, i.e., Rainfall Accumulation Drought Index (RADI). The RADI can be easily calculated at daily scale by comparing the long-term averaged cumulative rainfall to the observed cumulative rainfall for a specific duration. This study evaluated the availability of the RADI in the field of monitoring short-term and long-term droughts by investigating the spatial and temporal variability and the recurrence cycle of drought in South Korea. To present the short-term and long-term droughts, the various SPIs with different durations should be used in practice. However, the RADI can present and monitor both short-term and long-term droughts as a single index. By investigating the national average of the RADI, specific drought patterns of 20-year cycle were identified in this study. This study also proposed a five-level drought classification considering occurrence probability that would be a suitable alternative as a drought criterion for drought forecast/response.

• Journal of Korea Water Resources Association
• /
• v.43 no.8
• /
• pp.695-707
• /
• 2010

The frequency and size of typhoon and local severe rainfall are increasing due to the climate change and the damage also increasing from typhoon and severe rainfall. The flood forecasting and warning system to reduce the damage from typhoon and severe rainfall needs forecasted rainfall using radar data and short-term rainfall forecasting model. For this reason, this study examined the applicability of short-term rainfall forecast using translation model with weather radar data to point out that the utilization of flood forecasting in Korea. This study estimated the radar rainfall using Least-square fitting method and estimated rainfall was used as initial field of translation model. The translation model have verified accuracy of forecasted radar rainfall through the comparison of forecasted radar rainfall and observed rainfall quantitatively and qualitatively. Almost case studies showed that accuracy is over 0.6 within 4 hours leading time and mean of correlation coefficient is over 0.5 within 1 hours leading time in Kwanak and Jindo radar site. And, as the increasing the leading time, the forecast accuracy of precipitation decreased. The results of the calculated Mean Area Precipitation (MAP) showed forecast rainfall tend to be underestimated than observed rainfall but the correlation coefficient more than 0.5. Therefore it showed that translation model could be accurately predicted the rainfall relatively. The present results indicate that possibility of translation model application of Korea just within 2 hours leading forecasted rainfall.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.2
• /
• pp.44-55
• /
• 1994

This paper describes the development of real-time irrigation reservoir operation models that adequately allocate available water resources for paddy rice irrigation. Water requirement deficiency index(WRDI) was proposed as a guide to evaluate the operational performance of release schemes by comparing accumulated differences between daily release requirements for irrigated areas and actual release amounts. Seven reservoir release rules were developed, which are constant release rate method (CRR), mean storage curve method(MSC), frequency analysis method of reservoir storage rate(FAS), storage requirement curve method(SRC), constant optimal storage rate method (COS), ten-day optimal storage rate method(TOS), and release optimization method(ROM). Long-term forecasting reservoir operation model(LFROM) was formulated to find an optimal release scheme which minimizes WRDIs with long-term weather generation. Rainfall sequences, rainfall amount, and evaporation amount throughout the growing season were to be forecasted and the results used as an input for the model. And short-term forecasting reservoir operation model(SFROM) was developed to find an optimal release scheme which minimizes WRDIs with short-term weather forecasts. The model uses rainfall sequences forecasted by the weather service, and uses rainfall and evaporation amounts generated according to rainfall sequences.

• Korean Journal of Remote Sensing
• /
• v.32 no.2
• /
• pp.155-169
• /
• 2016

In this study, we developed a multi-sensor blending short-term rainfall forecasting technique using radar and satellite data during extreme rainfall occurrences in Busan and Gyeongnam region in August 2014. The Tropical Z-R relationship ($Z=32R^{1.65}$) has applied as a optimal radar Z-R relation, which is confirmed that the accuracy is improved during 20mm/h heavy rainfall. In addition, the multi-sensor blending technique has applied using radar and COMS (Communication, Ocean and Meteorological Satellite) data for quantitative precipitation estimation. The very-short-term rainfall forecasting performance was improved in 60 mm/h or more of the strong heavy rainfall events by multi-sensor blending. AWS (Automatic Weather System) and MAPLE data were used for verification of rainfall prediction accuracy. The results have ensured about 50% or more in accuracy of heavy rainfall prediction for 1-hour before rainfall prediction, which are correlations of 10-minute lead time have 0.80 to 0.53, and root mean square errors have 3.99 mm/h to 6.43 mm/h. Through this study, utilizing of multi-sensor blending techniques using radar and satellite data are possible to provide that would be more reliable very-short-term rainfall forecasting data. Further we need ongoing case studies and prediction and estimation of quantitative precipitation by multi-sensor blending is required as well as improving the satellite rainfall estimation algorithm.

• Atmosphere
• /
• v.21 no.4
• /
• pp.481-495
• /
• 2011

This study is performed to consider the threshold values of heavy rain warning in Korea using 98 surface meteorological station data and 590 Automatic Weather System stations (AWSs), damage data of National Emergency Management Agency for the period of 2005 to 2009. It is in need to arrange new criteria for heavy rain considering concept of rainfall intensity and rainfall damage to reflect the changed characteristics of rainfall according to the climate change. Rainfall values from the most frequent rainfall damage are at 30 mm/1 hr, 60 mm/3 hr, 70 mm/6 hr, and 110 mm/12 hr, respectively. The cumulative probability of damage occurrences of one in two due to heavy rain shows up at 20 mm/1 hr, 50 mm/3 hr, 80 mm/6 hr, and 110 mm/12 hr, respectively. When the relationship between threshold values of heavy rain warning and the possibility of rainfall damage is investigated, rainfall values for high connectivity between heavy rain warning criteria and the possibility of rainfall damage appear at 30 mm/1 hr, 50 mm/3 hr, 80 mm/6 hr, and 100 m/12 hr, respectively. It is proper to adopt the daily maximum precipitation intensity of 6 and 12 hours, because 6 hours rainfall might be include the concept of rainfall intensity for very-short-term and short-term unexpectedly happened rainfall and 12 hours rainfall could maintain the connectivity of the previous heavy rain warning system and represent long-term continuously happened rainfall. The optimum combinations of criteria for heavy rain warning of 6 and 12 hours are 80 mm/6 hr or 100 mm/12 hr, and 70 mm/6 hr or 110 mm/12 hr.

• Journal of Korea Water Resources Association
• /
• v.48 no.5
• /
• pp.409-423
• /
• 2015

In this study the very short-term rainfall forecasting and storm water forecasting using the weather radar data were implemented in an urban stream basin. As forecasting time increasing, the very short-term rainfall forecasting results show that the correlation coefficient was decreased and the root mean square error was increased and then the forecasting model accuracy was decreased. However, as a result of the correlation coefficient up to 60-minute forecasting time is maintained 0.5 or higher was obtained. As a result of storm water forecasting in an urban area, the reduction in peak flow and outflow volume with increasing forecasting time occurs, the peak time was analyzed that relatively matched. In the application of storm water forecasting by radar rainfall forecast, the errors has occurred that we determined some of the external factors. In the future, we believed to be necessary to perform that the continuous algorithm improvement such as simulation of rapid generation and disappearance phenomenon by precipitation echo, the improvement of extreme rainfall forecasting in urban areas, and the rainfall-runoff model parameter optimizations. The results of this study, not only urban stream basin, but also we obtained the observed data, and expand the real-time flood alarm system over the ungaged basins. In addition, it is possible to take advantage of development of as multi-sensor based very short-term rainfall forecasting technology.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.2
• /
• pp.45-57
• /
• 2003

An artificial neural network model was developed to analyze and forecast Short-term river runoff from the Naju watershed, in Korea. Error back propagation neural networks (EBPN) of hourly rainfall and runoff data were found to have a high performance In forecasting runoff. The number of hidden nodes were optimized using total error and Bayesian information criterion. Model forecasts are very accurate (i.e., relative error is less than 3% and $R^2$is greater than 0.99) for calibration and verification data sets. Increasing the time horizon for application data sets, thus mating the model suitable for flood forecasting. decreases the accuracy of the model. The resulting optimal EBPN models for forecasting hourly runoff consists of ten rainfall and four runoff data(ANN0410 model) and ten rainfall and ten runoff data(ANN1010 model). Performances of the ANN0410 and ANN1010 models remain satisfactory up to 6 hours (i.e., $R^2$is greater than 0.92).

• Journal of Korea Water Resources Association
• /
• v.48 no.12
• /
• pp.995-1009
• /
• 2015

Weather radar rainfall data has been recognized for making valuable contributions to short-term flood forecasting and management over the past decades. There are several advantages to better monitoring rainfall in ungauged area compared to ground-based rain gauges with which spatial patterns of the rainfall are not effectively identified. Hence, this study aims to develop a new scheme to forecast spatio-temporal rainfall field. The proposed model was based on an advection scheme to track wind patterns and velocity. The results showd a promising forecasting skill with quantitative and qualitative measures. It was confirmed that the forecasted rainfall may be effectively used an input data for a distributed hydrological model.