• Journal of the Korean Professional Engineers Association
• /
• v.18 no.2
• /
• pp.1-5
• /
• 1985

In the flood prediction research, it is pointed out that the difficulty of flood prediction is the frequently experienced overestimation of flood peak. That is caused by the rainfall prediction difficulty and the nonlinearity of hydrological phenomena. Even though the former reason will remain still unsolved, but the latter one can be possibly resolved the method of the AMRA (Auto Regressive Moving Average) model for each runoff component as developed by Dr. Hino and Dr. Hasebe. The principle of the method consists of separating though the numerical filters the total runoff time series into long-term, intermediate and short-term components, or ground water flow, interflow, and surface flow components. As a total system, a hydrological system is a non-linear one. However, once it is separated into two or three subsystems, each subsystem may be treated as a linear system. Also the rainfall components into each subsystem a estimated inversely from the runoff component which is separated from the observed flood. That is why flood prediction can be done without rainfall data. In the prediction of surface flow, the Kalman filter will be applicable but this paper shows only impulse function method.

• Water for future
• /
• v.29 no.3
• /
• pp.187-195
• /
• 1996

In this study, a methodology for the hourly prediction of rainfall surfaces was applied to the Pyungchang river basin at the upstream of South Han river with meteorological radar and ground rainfall data. The methods for the exclusion of abnormal echoes, and suppression of ground clutter, and the augmentation of attenuation effects associated with rainfall phenomena were reviewed, and the relationship between radar reflectivity (Z) and rainfall rate (R) was analyzed. The transformation of augmented radar reflectivities into the rdar rainfall surfaces was carried out, and afterward they were synthesized with the ground rainfall data generating the hourly rainfall surfaces. For the prediction of hourly rainfall surface, the moving factors of rainfall field estimated by the cross correlation coefficient method and the temporal variation of radar rainfall intensities were considered. The synthesized hourly rainfall surfaces were used to predict the hourly rainfall surfaces up to 3 hours in advance and subsequently the results were compared with the measured and the synthesized. It seems that the prediction method need to be verified with more data and be complemented further to consider the physical characteristics of rainfall field and the topography of the basin.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.150-150
• /
• 2022

This study investigates the roles of decomposition methods on high accuracy in daily rainfall prediction from light gradient boosting machine (LightGBM) algorithm. Here, empirical mode decomposition (EMD) and singular spectrum analysis (SSA) methods were considered to decompose and reconstruct input time series into trend terms, fluctuating terms, and noise components. The decomposed time series from EMD and SSA methods were used as input data for LightGBM algorithm in two hybrid models, including empirical mode-based light gradient boosting machine (EMDGBM) and singular spectrum analysis-based light gradient boosting machine (SSAGBM), respectively. A total of four parameters (i.e., temperature, humidity, wind speed, and rainfall) at a daily scale from 2003 to 2017 is used as input data for daily rainfall prediction. As results from statistical performance indicators, it indicates that the SSAGBM model shows a better performance than the EMDGBM model and the original LightGBM algorithm with no decomposition methods. It represents that the accuracy of LightGBM algorithm in rainfall prediction was improved with the SSA method when using multivariate dataset.

• Journal of Korea Water Resources Association
• /
• v.56 no.8
• /
• pp.471-484
• /
• 2023

Deep learning models based on generative adversarial neural networks are specialized in generating new information based on learned information. The deep generative models (DGMR) model developed by Google DeepMind is an generative adversarial neural network model that generates predictive radar images by learning complex patterns and relationships in large-scale radar image data. In this study, the DGMR model was trained using radar rainfall observation data from the Ministry of Environment, and rainfall prediction was performed using an generative adversarial neural network for a heavy rainfall case in August 2021, and the accuracy was compared with existing prediction techniques. The DGMR generally resembled the observed rainfall in terms of rainfall distribution in the first 60 minutes, but tended to predict a continuous development of rainfall in cases where strong rainfall occurred over the entire area. Statistical evaluation also showed that the DGMR method is an effective rainfall prediction method compared to other methods, with a critical success index of 0.57 to 0.79 and a mean absolute error of 0.57 to 1.36 mm in 1 hour advance prediction. However, the lack of diversity in the generated results sometimes reduces the prediction accuracy, so it is necessary to improve the diversity and to supplement it with rainfall data predicted by a physics-based numerical forecast model to improve the accuracy of the forecast for more than 2 hours in advance.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.884-887
• /
• 2006

This paper focuses on minimizing flood damage in the Yeongdeok basin of South Korea by establishing a flood prediction model based on a geographic information system (GIS), remote sensing, and geomorphoclimatic instantaneous unit hydrograph (GcIUH) techniques. The GIS database for flash flood prediction was created using data from digital elevation models (DEMs), soil maps, and Landsat satellite imagery. Flood prediction was based on the peak discharge calculated at the sub-basin scale using hydrogeomorphologic techniques and the threshold runoff value. Using the developed flash flood prediction model, rainfall conditions with the potential to cause flooding were determined based on the cumulative rainfall for 20 minutes, considering rainfall duration, peak discharge, and flooding in the Yeongdeok basin.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2001.05a
• /
• pp.35-44
• /
• 2001

As one of advanced uses of radar, a physically based rainfall prediction method which uses a conceptual rainfall model assimilated by information from volume scanning radar is shown. As another example of advanced utilization of weather radar, results from analyzing a hierarchical time-scale structure in dependency of rainfall distribution en topography are shown.

• 한국정보통신설비학회:학술대회논문집
• /
• 2007.08a
• /
• pp.191-195
• /
• 2007

Recently, landslides frequently happen at a natural slope during period of intensive rainfall. With rapidly increasing population of steep terrain in Korea, landslides have become one of the most significant natural hazards. Thus, it is necessary to protect people from landslides and to minimize the damage of houses, roads and other facilities. To accomplish this goal, many landslide prediction methods have been developed in the world. In this study, a simple landslide prediction system that enables people to escape the endangered area is developed. The system is focused to debris flows which happen frequently during periods of intensive rainfall at steep slopes in Kangwondo. This system is based on the wireless sensor network that is composed of sensor nodes, gateway, and server system. Sensor nodes that are composed of sensing part and communication part are newly developed to detect sensitive ground movement. Sensing part is designed to measure tilt angle and acceleration accurately, and communication part is deployed with Bluetooth (IEEE 802.15. I) module to transmit the data to the gateway. To verify the feasibility of this landslide prediction system, a series of laboratory tests is performed at a small-scale earth slope supplying rainfall by artificial rainfall dropping device. It is found that sensing nodes installed at slope can detect the ground motion when the slope failure starts. It is expected that the landslide prediction system by wireless senor network can provide early warnings when landslides such as debris flow occurs, and can be applied to ubiquitous computing city (U-City) that is characterized by disaster free.

• Journal of Korea Water Resources Association
• /
• v.53 no.11
• /
• pp.1025-1037
• /
• 2020

This study attempted to evaluate the spatial characteristics and applicability of the predicted ensemble rainfall data used for heavy rain alarms. Limited area ENsemble prediction System (LENS) has 13 rainfall ensemble members, so it is possible to use a probabilistic method in issuing heavy rain warnings. However, the accessibility of LENS data is very low, so studies on the applicability of rainfall prediction data are insufficient. In this study, the evaluation index was calculated by comparing one point value and the area average value with the observed value according to the heavy rain warning system used for each administrative district. In addition, the accuracy of each ensemble member according to the LENS issuance time was evaluated. LENS showed the uncertainty of over or under prediction by member. Area-based prediction showed higher predictability than point-based prediction. In addition, the LENS data that predicts the upcoming 72-hour rainfall showed good predictive performance for rainfall events that may have an impact on a water disaster. In the future, the predicted rainfall data from LENS are expected to be used as basic data to prepare for floods in administrative districts or watersheds.

• Journal of Environmental Science International
• /
• v.28 no.1
• /
• pp.125-135
• /
• 2019

For the purposes of enhancing usability of Numerical Weather Prediction (NWP), the quantitative precipitation prediction scheme by machine learning has been proposed. In this study, heavy rainfall was corrected for by utilizing rainfall predictors from LENS and Radar from 2017 to 2018, as well as machine learning tools LightGBM and XGBoost. The results were analyzed using Mean Absolute Error (MAE), Normalized Peak Error (NPE), and Peak Timing Error (PTE) for rainfall corrected through machine learning. Machine learning results (i.e. using LightGBM and XGBoost) showed improvements in the overall correction of rainfall and maximum rainfall compared to LENS. For example, the MAE of case 5 was found to be 24.252 using LENS, 11.564 using LightGBM, and 11.693 using XGBoost, showing excellent error improvement in machine learning results. This rainfall correction technique can provide hydrologically meaningful rainfall information such as predictions of flooding. Future research on the interpretation of various hydrologic processes using machine learning is necessary.

• Atmosphere
• /
• v.27 no.3
• /
• pp.345-358
• /
• 2017

The decadal change in rainfall for Changma period over the South Korea in early-2000s is detected in this study. The Changma rainfall in P1 (1992~2002) decade is remarkably less than in P2 (2003~2013) decade. The much rainfall in P2 decade is associated with the increase of rainy day frequency during Changma period, including the frequent occurrences of rainy day with a intensity of 30 mm/day or more in P2 decade. This decadal change in the Changma rainfall is due to the decadal change of atmospheric circulation around the Korean Peninsula which affects the intensity and location of Changma rainfall. During P2 decade, the anomalous anti-cyclone over the south of the Korean Peninsula, which represents the expansion of the North Pacific high with warm and wet air mass toward East Asia, is stronger than in P1 decade. In addition, the upper level zonal wind and meridional gradient of low-level equivalent potential temperature in P2 decade is relatively strengthened over the northern part of the Korean Peninsula than in P1 decade, which corresponds with the intensification of meridional gradient between air mass related to the East Asian summer monsoon nearby the Korean Peninsula in P2 decade. The enhanced meridional gradient of atir mass during P2 decade is favorable condition for the intensification of Changma rainfall band and more Changma rainfall. The atmospheric conditions related to enhanced Changma rainfall during P2 decade is likely to be influenced by the teleconnection linked to the suppressed convection anomaly over the southern part of China and South China Sea in P2 decade.