• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.155-155
• /
• 2018

Uncertainty in flood forecasting using a coupled meteorological and hydrological model is arisen from various sources, especially the uncertainty comes from the inaccuracy of Quantitative Precipitation Forecasts (QPFs). In order to improve the capability of flood forecast, the uncertainty estimation and mitigation are required to perform. This study is conducted to investigate and reduce such uncertainty. First, ensemble QPFs are generated by using Monte - Carlo simulation, then each ensemble member is forced as input for a hydrological model to obtain ensemble streamflow prediction. Likelihood measures are evaluated to identify feasible member. These members are retained to define upper and lower limits of the uncertainty interval and assess the uncertainty. To mitigate the uncertainty for very short lead time, a blending method, which merges the ensemble QPFs with radar-based rainfall prediction considering both qualitative and quantitative skills, is proposed. Finally, blending bias ratios, which are estimated from previous time step, are used to update the members over total lead time. The proposed method is verified for the two flood events in 2013 and 2016 in the Yeonguol and Soyang watersheds that are located in the Han River basin, South Korea. The uncertainty in flood forecasting using a coupled Local Data Assimilation and Prediction System (LDAPS) and Sejong University Rainfall - Runoff (SURR) model is investigated and then mitigated by blending the generated ensemble LDAPS members with radar-based rainfall prediction that uses McGill algorithm for precipitation nowcasting by Lagrangian extrapolation (MAPLE). The results show that the uncertainty of flood forecasting using the coupled model increases when the lead time is longer. The mitigation method indicates its effectiveness for mitigating the uncertainty with the increases of the percentage of feasible member (POFM) and the ratio of the number of observations that fall into the uncertainty interval (p-factor).

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2008년도 정기총회 및 학술발표대회
• /
• pp.669-673
• /
• 2008

In this study, the new methodology which combines Kohonen self-organizing map(KSOM) neural networks model and the conventional neural networks models such as feedforward neural networks model and generalized neural networks model is introduced to forecast flood stage in Nakdong river, Republic of Korea. It is possible to train without output data in KSOM neural networks model. KSOM neural networks model is used to classify the input data before it combines with the conventional neural networks model. Four types of models such as SOM-FFNNM-BP, SOM-GRNNM-GA, FFNNM-BP, and GRNNM-GA are used to train and test performances respectively. From the statistical analysis for training and testing performances, SOM-GRNNM-GA shows the best results compared with the other models such as SOM-FFNNM-BP, FFNNM-BP, and GRNNM-GA and FFNNM-BP shows vice-versa. From this study, we can suggest the new methodology to forecast flood stage and construct flood warning system in river basin.

• 한국농공학회지
• /
• 제36권2호
• /
• pp.79-87
• /
• 1994

A real-time flood forecasting system(FLOFS) was developed for the real-time and predictive determination of flood discharges and stages, and to aid in flood management decisions in the Keum River Estuary Dam. The system consists of three subsystems : data subsystem, model subsystem, and user subsystem. The data subsystem controls and manages data transmitted from telemetering systems and simulated by models. The model subsystem combines various techniques for rainfall-runoff modeling, tidal-level forecasting modeling, one-dimensional unsteady flood routing, Kalman filtering, and autoregressivemovingaverage(ARMA) modeling. The user subsystem in a menu-driven and man-machine interface system.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2002년도 학술발표회 발표논문집
• /
• pp.285-288
• /
• 2002

For real-time flood forecasting and effective control flood at the Youngsan estuary dam, the Flood Forecasting and Control User Interface System II (FFCUS II) has been developed. This paper describes the features and application of FFCUS II. FFCUS II is composed of the database management subsystem, the model subsystem, and the graphic user interface. The database management subsyem collects rainfall data and stream flow data, updates, processes, and searches the data. The model subsystem predicts the inflow hydrograph, the tide, forecasts flood hydrograph, and simulates the release rate from the sluice gates. The graphic user interface subsystem aids the user's decision-making process by displaying the operation results of the database management subsystem and model subsystem.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2007년도 학술발표회 논문집
• /
• pp.1427-1431
• /
• 2007

In this study, the new methodology which combines Kohonen self-organizing map(KSOM) neural networks model and the conventional neural networks models such as feedforward neural networks model and generalized neural networks model is introduced to forecast flood stage in Nakdong river, Republic of Korea. It is possible to train without output data in KSOM neural networks model. KSOM neural networks model is used to classify the input data before it combines with the conventional neural networks model. Four types of models such as SOM-FFNNM-BP, SOM-GRNNM-GA, FFNNM-BP, and GRNNM-GA are used to train and test performances respectively. From the statistical analysis for training and testing performances, SOM-GRNNM-GA shows the best results compared with the other models such as SOM-FFNNM-BP, FFNNM-BP, and GRNNM-GA and FFNNM-BP shows vice-versa. From this study, we can suggest the new methodology to forecast flood stage and construct flood warning system in river basin.

• 한국방재학회 논문집
• /
• 제8권3호
• /
• pp.157-164
• /
• 2008

하천의 홍수범람 예보시스템개발을 위한 초기연구로 부정류 모형인 FLDWAV 모형을 사용하여 홍수범람을 해석하고, 모형결과인 홍수 범람 현상의 시간적 변화를 그래픽을 사용하여 효과적으로 볼 수 있도록 한 홍수범람 가시화 시스템을 개발하였다. FLDWAV를 이용한 모형결과의 신뢰성을 확인하기 위해 HEC-RAS 모형을 동시에 적용하여 모의결과를 비교한 결과, 두 모형에 의한 결과는 거의 일치하였다. 본 연구에서 개발된 가시화시스템을 활용하면, 강우로 인해 발생되는 자연하천에서 홍수파 전파와 하천 범람을 신속하고 자세하게 그래픽으로 관찰할 수 있다. 본 시스템은 수리학적 지식이 없는 사람들도 홍수범람 모의 결과를 쉽게 이해하게 하며, 홍수범람 예보와 하천 범람으로 인한 재해의 방지대책을 신속하게 수립하는 데 도움을 주어 홍수범람으로 인한 자연재해를 경감하는 데 기여할 것이다.

• 한국농공학회논문집
• /
• 제63권1호
• /
• pp.11-25
• /
• 2021

The objective of this study was to analyze the impact of activation functions on flood forecasting model based on Artificial neural networks (ANNs). The traditional activation functions, the sigmoid and tanh functions, were compared with the functions which have been recently recommended for deep neural networks; the ReLU, leaky ReLU, and ELU functions. The flood forecasting model based on ANNs was designed to predict real-time runoff for 1 to 6-h lead time using the rainfall and runoff data of the past nine hours. The statistical measures such as R2, Nash-Sutcliffe Efficiency (NSE), Root Mean Squared Error (RMSE), the error of peak time (ETp), and the error of peak discharge (EQp) were used to evaluate the model accuracy. The tanh and ELU functions were most accurate with R2=0.97 and RMSE=30.1 (㎥/s) for 1-h lead time and R2=0.56 and RMSE=124.6~124.8 (㎥/s) for 6-h lead time. We also evaluated the learning speed by using the number of epochs that minimizes errors. The sigmoid function had the slowest learning speed due to the 'vanishing gradient problem' and the limited direction of weight update. The learning speed of the ELU function was 1.2 times faster than the tanh function. As a result, the ELU function most effectively improved the accuracy and speed of the ANNs model, so it was determined to be the best activation function for ANNs-based flood forecasting.

• 대한토목학회논문집
• /
• 제26권1B호
• /
• pp.39-50
• /
• 2006

홍수를 예측하기 위해서 국내 5대강 유역의 홍수통제소는 저류함수모형을 사용하고 있으며 현재까지 홍수예측에 대한 많은 연구가 이루어지고 있다. 이에 본 논문에서는 현재 홍수통제소에서 사용되고 있는 저류함수모형과 과거의 강우-수위 관계를 이용한 회귀분석(regression analysis), 그리고 인공신경망(artificial neural network)을 이용하여 홍수를 예측하고 이를 비교, 분석하고자 하였다. 저류함수모형의 경우는 홍수통제소의 대표매개변수와 보정된 최적(평균)매개변수를 적용하였다. 그리고 회귀분석과 인공신경망은 1995~2001년까지의 홍수사상 중 4개의 홍수사상을 선택하여 회귀계수를 구하고 역전파(backpropagation) 알고리즘을 사용하여 학습을 시켰다. 그 결과 저류함수모형의 경우 최적 매개변수를 이용하였을 때 기존의 홍수통제소에서 사용하고 있는 대표매개변수보다 예측이 개선되었으며, 회귀분석의 방법인 다중회귀분석, Robust 회귀분석, Stepwise 회귀분석을 이용한 홍수예측은 비교적 정확한 결과를 얻을 수 있었다. 역전파 알고리즘을 사용한 인공신경망의 경우도 회귀분석을 이용한 홍수예측보다는 다소 못하였지만 정확한 결과를 얻을 수 있었다.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2001년도 학술발표회 발표논문집
• /
• pp.295-299
• /
• 2001

To protect the flooding damages in Medium and Small watershed, it needs to set up flood warning system and develope Flood forecasting Model in real-time basis for medium and small watershed. In this study, it was able to minimize the error range between forecasted flood inflow and actual flood inflow, and forecast accurately the flood discharge some hours in advance by using simplex method recursively for the determination of the best parameters of RETFLO model. The result of RETFLO performance applied to several storm of Yugu river during 3 past years was very good with relative errors of 10% for comparison of total runoff volume and with one hour delayed peak time.

• 한국농공학회지
• /
• 제36권3호
• /
• pp.60-66
• /
• 1994

This paper is to validate the proposed models for the real-time forecasting for the Keum river estuary dam such as tidal-level forecasting model, one-dimensional unsteady flood routing model, and Kalman filter models. The tidal-level forecasting model was based on semi-range and phase lag of four tidal constituents. The dynamic wave routing model was based on an implicit finite difference solution of the complete one-dimensional St. Venant equations of unsteady flow. The Kalman filter model was composed of a processing equation and adaptive filtering algorithm. The processng equations are second ordpr autoregressive model and autoregressive moving average model. Simulated results of the models were compared with field data and were reviewed.