• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.358-358
• /
• 2023

본 연구에서는 그동안 수자원분야 강우유출 해석분야에 활용되었던 대표적인 머신러닝&딥러닝(ML&DL) 모델을 활용하여 모델의 하이퍼파라미터 튜닝뿐만 아니라 모델의 특성을 고려한 기상 및 수문데이터의 조합과 전처리(lag-time, 이동평균 등)를 통하여 데이터 특성과 ML&DL모델의 조합시나리오에 따른 일 유입량 예측성능을 비교 검토하는 연구를 수행하였다. 이를 위해 소양강댐 유역을 대상으로 1974년에서 2021년까지 축적된 기상 및 수문데이터를 활용하여 1) 강우, 2) 유입량, 3) 기상자료를 주요 영향변수(독립변수)로 고려하고, 이에 a) 지체시간(lag-time), b) 이동평균, c) 유입량의 성분분리조건을 적용하여 총 36가지 시나리오 조합을 ML&DL의 입력자료로 활용하였다. ML&DL 모델은 1) Linear Regression(LR), 2) Lasso, 3) Ridge, 4) SVR(Support Vector Regression), 5) Random Forest(RF), 6) LGBM(Light Gradient Boosting Model), 7) XGBoost의 7가지 ML방법과 8) LSTM(Long Short-Term Memory models), 9) TCN(Temporal Convolutional Network), 10) LSTM-TCN의 3가지 DL 방법, 총 10가지 ML&DL모델을 비교 검토하여 일유입량 예측을 위한 가장 적합한 데이터 조합 특성과 ML&DL모델을 성능평가와 함께 제시하였다. 학습된 모형의 유입량 예측 결과를 비교·분석한 결과, 소양강댐 유역에서는 딥러닝 중에서는 TCN모형이 가장 우수한 성능을 보였고(TCN>TCN-LSTM>LSTM), 트리기반 머신러닝중에서는 Random Forest와 LGBM이 우수한 성능을 보였으며(RF, LGBM>XGB), SVR도 LGBM수준의 우수한 성능을 나타내었다. LR, Lasso, Ridge 세가지 Regression모형은 상대적으로 낮은 성능을 보였다. 또한 소양강댐 댐유입량 예측에 대하여 강우, 유입량, 기상계열을 36가지로 조합한 결과, 입력자료에 lag-time이 적용된 강우계열의 조합 분석에서 세가지 Regression모델을 제외한 모든 모형에서 NSE(Nash-Sutcliffe Efficiency) 0.8이상(최대 0.867)의 성능을 보였으며, lag-time이 적용된 강우와 유입량계열을 조합했을 경우 NSE 0.85이상(최대 0.901)의 더 우수한 성능을 보였다.

• Water Engineering Research
• /
• v.5 no.2
• /
• pp.101-109
• /
• 2004

Aggregating information by combining forecasts from two or more forecasting methods is an alternative to using forecasts from just a single method to improve forecast accuracy. This paper describes the development and use of a monthly inflow forecast model based on an optimal linear combination (OLC) of forecasts derived from naive, persistence, and Ensemble Streamflow Prediction (ESP) forecasts. Using the cross-validation technique, the OLC model made 1-month ahead probabilistic forecasts for the Chungju multi-purpose dam inflows for 15 years. For most of the verification months, the skill associated with the OLC forecast was superior to those drawn from the individual forecast techniques. Therefore this study demonstrates that OLC can improve the accuracy of the ESP forecast, especially during the dry season. This study also examined the value of the OLC forecasts in reservoir operations. Stochastic Dynamic Programming (SDP) derived the optimal operating policy for the Chungju multi-purpose dam operation and the derived policy was simulated using the 15-year observed inflows. The simulation results showed the SDP model that updated its probability from the new OLC forecast provided more efficient operation decisions than the conventional SDP model.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.4
• /
• pp.395-405
• /
• 2004

The filling pattern and an adaptive grid refinement based on the finite element method and Eulerian mesh advancement approach have been developed to analyze incompressible transient viscous flow with free surfaces. The governing equation for flow analysis is Navier-Stokes equation including inertia and gravity effects. The mixed FE formulation and predictor-corrector method are used effectively for unsteady numerical simulation. The flow front surface and the volume inflow rate are calculated using the filling pattern technique to select an adequate pattern among four filling patterns at each triangular control volume. By adaptive grid refinement, the new flow field that renders better prediction in flow surface shape is generated and the velocity field at the flow front part is calculated more exactly. In this domain the elements in the surface region are made finer than those in the remaining regions for more efficient computation. Using the proposed numerical technique, the collapse of a water dam has been analyzed to predict flow phenomenon of fluid and the predicted front positions with respect to time have been compared with the reported experimental results.

• Journal of Korean Society on Water Environment
• /
• v.35 no.6
• /
• pp.470-480
• /
• 2019

The Doam lake watershed was designated as a non-point pollution management area in 2007 to improve water quality based on watershed management implementation. There have been studies of non-point source reduction with respect to the watershed management impacting the pollutant transport of the reservoir. However, a little attention has been focused on the impact of water quality improvement by the management of the dam operation or the guidelines on the dam operation. In this study, the impact of in-lake management practices combined with watershed management is analyzed, and the appropriate guidelines on the operation of the dam are suggested. The integrated modeling system by coupling with the watershed model (HSPF) and reservoir water quality model (CE-QUAL-W2) was applied for analyzing the impact of water quality management practices. A scenario implemented with sedimentation basin and suspended matter barrier showed decrease in SS concentration up to 4.6%. The SS concentration increased in the scenarios adjusting withdrawal location from EL.673 m to the upper direction(EL.683 m and EL.688 m). The water quality was comparably high when the scenario implemented all in-lake practices with water intake at EL.673 m. However, there was improvement in water quality when the height of the water intake was moved to EL.688 m during the summer by preventing sediments inflow after the rainfall. Therefore, to manage water quality of the Doam lake, it is essential to control the water quality by modulating the height of water intake through consistent turbidity monitoring during rainfall.

• Journal of Korean Society on Water Environment
• /
• v.36 no.2
• /
• pp.89-97
• /
• 2020

North Han River is a very unique type of water system, where Hwacheon, Chuncheon, Soyanggang, Euiam and Cheongpyeong Dams are located consecutively. These dams are operated differently in the amount of discharge and release schedule according to their structure and purpose of use. They have different water quality characteristics depending on external pollutant inflow and internal mixing condition. Therefore, this study investigated the relationship between the upper dam and down stream river with respect to water quality indicators, such as water temperature, electrical conductivity, BOD, COD, TN and TP of the North Han River. The similarities and correlations representing the relationship were analyzed by Pearson's correlation r and t-test. The data was taken from the Ministry of Environment's water quality monitoring from 1999 to 2018. The results show that water temperature and electrical conductivity of the dam and river are similar and correlated. However, it turned out that there was no similarities and correlations in BOD, COD, TN and TP that are significantly affected by subaqueous reaction mechanism. The results of this study present the impact of the dam on the water quality of North Han River, which can be used as useful data for management of water quality.

• Journal of Korea Water Resources Association
• /
• v.51 no.6
• /
• pp.523-533
• /
• 2018

The objective of this study is to analyze uncertainties of ensemble-based streamflow prediction method for model parameters and input data. ESP (Ensemble Streamflow Prediction) and BAYES-ESP (Bayesian-ESP) based on ABCD rainfall-runoff model were selected as streamflow prediction method. GLUE (Generalized Likelihood Uncertainty Estimation) was applied for the analysis of parameter uncertainty. The analysis of input uncertainty was performed according to the duration of meteorological scenarios for ESP. The result showed that parameter uncertainty was much more significant than input uncertainty for the ensemble-based streamflow prediction. It also indicated that the duration of observed meteorological data was appropriate to using more than 20 years. And the BAYES-ESP was effective to reduce uncertainty of ESP method. It is concluded that this analysis is meaningful for elaborating characteristics of ESP method and error factors of ensemble-based streamflow prediction method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.1063-1067
• /
• 2008

최근 국지적 집중호우로 인한 인명과 재산피해가 증가하고 있는 실정이며 이러한 피해를 경감하기 위한 하나의 방책으로써 홍수예경보 시스템 구축에 관한 관심이 증가하고 있다. 기존의 홍수예보 시스템은 강우의 실제 관측치를 모형의 입력자료로 하여 홍수유출을 계산함으로 인해 예보시간이 촉박하였다. 실시간 강우를 이용하여 유출계산을 수행하고 그 결과가 위험하다고 판단될 때 홍수예경보를 하므로 집중호우와 같은 악기상 조건에서는 적용에 한계가 있다. 따라서 정확한 기상예보를 활용한 기상-수자원 연계기법을 개발하여 홍수예경보 시스템에 적용한다면 악기상 감시예측기술의 향상과 더불어 재해의 방지차원에서 매우 유용한 대책이 될 것이다. 이에 본 연구에서는 단기 예측강우의 국내유역 적용성 여부를 검토하기 위해 30km의 공간 해상도를 가진 단기지역예보모델인 RDAPS(Regional Data Assimilation and Prediction System) 강수자료를 활용하여 기상학적 및 수문학적 정확도를 분석하였으며, 이를 바탕으로 예측강수의 높은 활용성이 기대되는 실제 한강수계의 주요 댐 지점에 HEC-1 모형을 이용하여 댐 유입량을 산정하고 그 적용성을 평가하고자 한다.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.35 no.1
• /
• pp.50-58
• /
• 1993

The sedimentation patterns at a reservoir, important to the reservoir capacity curve were simulated using a depth averaged, two-dimensional sediment transport model, that is capable of depicting velocity distributions and sediment transportation. The Banweol reservoir, whose stage capacity relationships have been surveyed before and after the construction, was selected and the daily inflow rates and stages were simulated using a reservoir operation model(DI-ROM). The applicability of the transport model was tested from the comparisons of simulated sedimentation patterns to the surveyed results. The simulated inflow rates and water level fluctuations at the reservoir during twenty-one years from 1966 to 1986, showed that water levels exceeding 80 percent of the total capacity occurred for 70 percent of the periods and inflow rates less than 5000rn$^3$/day sustained for 54 percent of the spans. Dorminant flow directions were simulated from two streamflow inlets to the dam site. And simulated sediment concentrations were higher near the inlets and lower at the inside of the reservoir. Sediment was deposited heavily near the inlets, and portions of sediments were distributed along the flow paths within the reservoir. The comparisons between the simulation results and the surveyed depositions were partially matched. However, it was not possible to compare two results at the upper parts of the reservoir where dredging was carried out few times for the purpose of reservoir maintenance. This study demonstrates that sedimentation patterns within the reservoir are closely related to incoming sediment and flow rates, water level fluctuations, and flow circulation within the reservoir.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.307-307
• /
• 2022

최근 기후변화와 댐 상류 토지이용 변화 등과 같은 다양한 원인에 의해 댐 유입량의 변동성이 증가하면서 댐 관리 및 운영조작 의사 결정에 어려움이 발생하고 있다. 따라서 이러한 댐 유입량의 변동 특성을 반영하여 댐 유입량을 정확하고 효율적으로 예측할 수 있는 방안이 필요한 실정이다. 머신러닝 기술이 발전하면서 Auto-ML(Automated Machine Learning)이 다양한 분야에서 활용되고 있다. Auto-ML은 데이터 전처리, 최적 알고리즘 선택, 하이퍼파라미터 튜닝, 모델 학습 및 평가 등의 모든 과정을 자동화하는 기술이다. 그러나 아직까지 수문 분야에서 댐 유입량을 예측하기 위한 모델을 개발하는데 있어서 Auto-ML을 활용한 사례는 부족하고, 특히 댐 유입량의 예측 정확성을 확보하기 위해 High-inflow and low-inflow 의 변동 특성을 고려한 하이브리드 결합 방식을 통해 Auto-ML 기반 앙상블 모델을 개발하고 평가한 연구는 없다. 본 연구에서는 Auto-ML의 패키지 중 Auto-sklearn을 통해 홍수기, 비홍수기 유입량 변동 특성을 반영한 하이브리드 앙상블 댐 유입량 예측 모델을 개발하였다. 소양강댐을 대상으로 적용한 결과, 하이브리드 Auto-sklearn 앙상블 모델의 댐 유입량 예측 성능은 R² 0.868, RMSE 66.23 m³/s, MAE 16.45 m³/s로 단일 Auto-sklearn을 통해 구축 된 앙상블 모델보다 전반적으로 우수한 것으로 나타났다. 특히 FDC (Flow Duration Curve)의 저수기, 갈수기 구간에서 두 모델의 유입량 예측 경향은 큰 차이를 보였으며, 하이브리드 Auto-sklearn 모델의 예측 값이 관측 값과 더욱 유사한 것으로 나타났다. 이는 홍수기, 비홍수기 구간에 대한 앙상블 모델이 독립적으로 구축되는 과정에서 각 모델에 대한 하이퍼파라미터가 최적화되었기 때문이라 판단된다. 향후 본 연구의 방법론은 보다 정확한 댐 유입량 예측 자료를 생성하기 위한 방안 수립뿐만 아니라 다양한 분야의 불균형한 데이터셋을 이용한 앙상블 모델을 구축하는데도 유용하게 활용될 수 있을 것으로 사료된다.

• Journal of Korea Water Resources Association
• /
• v.42 no.1
• /
• pp.61-73
• /
• 2009

To efficiently carry out the flood management of a multipurpose dam, two flood forecasting models are developed, each of which has the capabilities of forecasting upstream inflows and flood discharges downstream of a dam, respectively. The models are calibrated, validated, and evaluated by comparison of the observed and the runoff forecasts upstream and downstream of Namgang Dam. The upstream inflow forecasting model is based on the Grey system theory and employs the sixth order differential equation. By comparing the inflows forecasted by the models calibrated using different data sets with the observed in validation, the most appropriate model is determined. To forecast flood discharges downstream of a dam, a Grey model is integrated with a modified Muskingum flow routing model. A comparison of the observed and the forecasted values in validation reveals that the model can provide good forecasts for the dam's flood management. The applications of the two models to forecasting floods in real situations show that they provide reasonable results. In addition, it is revealed that to enhance the prediction accuracy, the models are necessary to be calibrated and applied considering runoff stages; the rising, peak, and falling stages.