• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.3
• /
• pp.303-314
• /
• 2020

The hydrological characteristics of watersheds and hydraulic systems of urban and river floods are highly nonlinear and contain uncertain variables. Therefore, the predicted time series of rainfall-runoff data in flood analysis is not suitable for existing neural networks. To overcome the challenge of prediction, a NARX (Nonlinear Autoregressive Exogenous Model), which is a kind of recurrent dynamic neural network that maximizes the learning ability of a neural network, was applied to forecast a flood in real-time. At the same time, NARX has the characteristics of a time-delay neural network. In this study, a hydrological model was constructed for the Taehwa river basin, and the NARX time-delay parameter was adjusted 10 to 120 minutes. As a result, we found that precise prediction is possible as the time-delay parameter was increased by confirming that the NSE increased from 0.530 to 0.988 and the RMSE decreased from 379.9 ㎥/s to 16.1 ㎥/s. The machine learning technique with NARX will contribute to the accurate prediction of flow rate with an unexpected extreme flood condition.

• Journal of Korea Water Resources Association
• /
• v.51 no.5
• /
• pp.425-438
• /
• 2018

Existing studies that analyze the causes and effects of water circulation use mostly rainfall - runoff models, which requires much effort in model development, calibration and verification. In this study, hydrological sensitivity analysis which can separate quantitatively the impacts by natural factors and anthropogenic factor was applied to the Hwacheon dam upper basin from 1967 to 2017. As a result of using various variable change point detection methods, 1999 was detected as a statistically significant change point. Especially, based on the hydrological sensitivity analysis using 5 Budyko based functions, it was estimated that the average inflow reduction amount by Imnam dam construction was $1.890\;billion\;m^3/year$. This results in this study was slightly larger than the those by existing researchers due to increase of rainfall and decrease of Hwacheon dam inflow. In future, it was suggested that effective water management measures were needed to resolve theses problems. Especially, it can be suggested that the monthly or seasonal analysis should be performed and also the prediction of discharge for future climate change should be considered to establish resonable measures.

• Journal of Korea Water Resources Association
• /
• v.33 no.5
• /
• pp.623-634
• /
• 2000

This study describes results of numerical simulations on river flow response due to global warming. Forecasts of changes in climatic conditions are required to estimate the hydrologic effects of increasing trace gas concentrations in the atmosphere. However, reliable forecasts of regional climate change are unavailable. In there absence, various approaches to the development of scenarios of future climatic conditions are used. The approach in this study is to prescribe climatic changes for a river basin in a simplified manner. As a rule, such scenarios specify air temperature increases from $0^{\circ}C\;to\;4.0^{\circ}C$ and precipitation change (increase or decrease) in the range of 0% to 15%. On the basis of acceptable supposition of warming scenarios. future daily streamflow is simulated using rainfall-runoff model in the Andong Dam basin. The numerical experiments have quantitatively revealed the change of discharge at 2010, 2020, 2030 and 2050 for each warming scenarios and compared it with the results for a non-warmmg scenano.cenano.

• Water for future
• /
• v.35 no.5
• /
• pp.31-43
• /
• 2002

This study describes results of numerical simulations on river flow response due to global warming. Forecasts of changes in climatic conditions are required to estimate the hydrologic effects of increasing trace gas concentratrions in the atmosphere. However, reliable forecasts of regional climate change are unavailable. In there absense various approaches to the development of scenarios of furture climatic conditions are used. The approach in this study is to prescribe climatic changes for a river basin in a simplified manner. As a rule, such scenarios apecify air temperature increases from $0^{\circ}C$ to $4.0^{\circ}C$ and precipitation change (increase or decrease) in the range of 0% to 15%. On the basis of acceptable supposition of warming scenarios, furute daily stream flow is simulated using rainfall-runoff model in the Andong Dam basin. The numerical experiments have quantitatively revealed the change of discharge at 2010, 2020, 2030 and 1050 for each warming scenarios and compared it with the results for a non-worming scenario.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.187-198
• /
• 2006

Korea Water Resources Corporation(KOWACO) has developed the Integrated Real-time Water Management System(IRWMS) that calculates monthly optimal ending target storages by using Sampling Stochastic Dynamic Programming(SSDP) with Ensemble Streamflow Prediction(ESP) running on the $1^{st}$ day of each month. This system, however, has a shortcoming: it cannot reflect the hydrolmeteorologic variations in the middle of the month. To overcome this drawback, in this study updated ESP forecasts three times each month by using the observed precipitation series from the $1^{st}$ day of the month to the forecast day and the historical precipitation ensemble for the remaining days. The improved accuracy and its effect on the reservoir operations were quantified as a result. SSDP/ESP21 that reflects within-a-month hydrolmeteorologic states saves $1\;X\;10^6\;m^3$ in water shortage on average than SSDP/ESP01. In addition, the simulation result demonstrated that the effect of ESP accuracy on the reduction of water shortage became more important when the total runoff was low during the drawdown period.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.334-334
• /
• 2019

기후변화에 능동적으로 대처하기 위해서는 기후변화에 따른 수자원가용량의 변화를 정량적으로 평가할 수 있어야 한다. 평가결과의 신뢰도를 높이기 위해서 기후변화 시나리오는 지역기후 및 유역특성에 적합한 결과를 포함하여야 한다. 또한, 기후변화가 유역의 물순환계에 미치는 영향이 있다면, 물순환 개선 기술을 통해 지속가능한 유역 물환경을 구축하는 것이 필요하다. 유역 물순환 개선 기술은 기후변화가 진행 중에 있거나 예상되는 지역에 대하여 강우로부터 발생되는 유출을 지연, 저류, 침투시켜 지속가능한 물순환 체계를 유지하고 회복하도록 하는 기법이라 할 수 있다. 한국건설기술연구원에서는 기후변화에 따른 영향을 평가하고 적응 대책을 수립하기 위한 실무적인 유역 물순환 개선 및 평가 모형인 CAT3(Catchment hydrologic cycle Assessment Tool 3)을 개발하였으며 본 모형은 침투시설, 저류시설, 습지, 빗물저장시설과 같은 물순환 개선시설에 대한 효과를 정량적으로 평가할 수 있다. 본 연구에서는 팔당댐 상류의 경안천 유역을 대상으로 APCC 기후변화 시나리오 통계적 상세화 자료를 활용하여 물순환 개선 기술의 적용성을 평가하였다. 통계적 상세화 자료는 APCC에서 개발된 AIMS(APCC Integrated Modeling Solution) 플랫폼을 이용하였다. AIMS는 다양한 기후정보를 기반으로 사용자 관점에서 상세화를 수행할 수 있는 장점이 있다. 상세화 기법은 SDQDM(Spatial Disaggregation Quantile Delta Mapping) 방법을 이용하였다. 상세화된 기후자료는 과거자료의 재현성 및 미래 기간에 대한 왜곡도를 평가하기 위해 극한기후지수(Climate Index)를 이용하는데 본 연구에서는 장기간에 걸친 수자원가용량의 평가 및 예측을 위해 연강수량(PRCPTOT)을 사용하였으며 증발산량의 평가 및 예측에 영향을 미치는 온도 관련 극한기후지수는 평균기온 개념의 DTR(TMAX&TMIN)을 이용하였다. 통계적 상세화 과정을 통해 최종적으로 HadGEM2-CC, INMCM4, CanESM2 시나리오를 선택하였으며 각 시나리오별 물순환 개선 기술을 적용한 후 미래의 수문학적 변동성을 평가하였다.

• Journal of Korea Water Resources Association
• /
• v.44 no.2
• /
• pp.97-107
• /
• 2011

For the purpose of enhancing usability of NWP (Numerical Weather Prediction), the quantitative precipitation prediction scheme was suggested. In this research, precipitation by leading time was predicted using 3-hour rainfall accumulation by meso-scale numerical weather model and AWS (Automatic Weather Station), precipitation water and relative humidity observed by atmospheric sounding station, probability of rainfall occurrence by leading time in June and July, 2001 and August, 2002. Considering the nonlinear process of ranfall producing mechanism, the ANN (Artificial Neural Network) that is useful in nonlinear fitting between rainfall and the other atmospheric variables. The feedforward multi-layer perceptron was used for neural network structure, and the nonlinear bipolaractivation function was used for neural network training for converting negative rainfall into no rain value. The ANN simulated rainfall was validated by leading time using Nash-Sutcliffe Coefficient of Efficiency (COE) and Coefficient of Correlation (CORR). As a result, the 3 hour rainfall accumulation basis shows that the COE of the areal mean of the Korean peninsula was improved from -0.04 to 0.31 for the 12 hr leading time, -0.04 to 0.38 for the 24 hr leading time, -0.03 to 0.33 for the 36 hr leading time, and -0.05 to 0.27 for the 48 hr leading time.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.123-123
• /
• 2011

가뭄은 다른 기상재해들과 달리 특정한 기후현상에 의해 발생하는 사건이 아닌 장기간의 강우 부족으로 인한 물 부족으로부터 기인하며, 가뭄의 특성상 가뭄의 시작과 끝을 명확히 구분하기 힘들며, 심도를 결정짓는 것 또한 어려움이 있다. 이러한 가뭄의 특성을 파악하기 위한 연구는 계속되고 있으며, SPI(Standardized Precipitation Index), PDSI(Palmer Drought Severity Index), SWSI(Surface Water Supply Index), EDI(Effective Drought Index), CMI(Crop Moisture Index)등과 같은 가뭄의 특성을 잘 반영한 가뭄지수의 개발 또한 끊임없이 이어지고 있다. 하지만 이러한 가뭄지수들은 기상학적, 기후학적, 농업적, 수문학적등과 같은 분류에 의해 가뭄의 표현이 상이한 결과를 보여주며, 동일한 방법으로 산정된 가뭄평가지수라 하더라도 지역적인 적합성 정도에서 또한 차이를 보인다. 본 연구에서는 우리나라의 실제 가뭄의 발생사례를 바탕으로 각종 가뭄지수들의 적합도와 가뭄의 변동특성을 파악하고자 한다. 우리나라의 가뭄특성을 확인하기 위하여 보고서 등 각종 문헌과 신문기사를 통해 1973년부터 2009년까지 실제 가뭄발생 기록을 정량화하고 행정구역단위의 우리나라 전역에 공간분포로 표현하였다. 69개 기상관측소의 강수 및 기온 자료를 통해 기상청과(SPI, PDSI, PN, 강수량십분위) 동일한 방법으로 가뭄지수를 산정 후 마찬가지로 행정구역단위의 우리나라 전역에 확장하였으며, 이렇게 생성된 각종 가뭄지수 및 기후변수의 공간분포와 실제 가뭄발생사례의 공간분포를 비교 분석함으로서 각 가뭄지수 및 기후변수의 적합성을 평가하였다. 각 가뭄지수 및 기후변수의 적합성을 평가하기 위하여 ROC space 상의 검정통계량을 이용하였다. 분석결과 PN(Percent of Normal)이 실제 가뭄의 현상을 가장 잘 표현했으며, 강수량, SPI 3, 강수량 십분위 등이 높은 상관성을 보였다. 또한 SPI12, PDSI, PN, 강수량십분위 등이 행정구역에 따른 산포정도가 비교적 낮게 나타났다. 본 연구를 통해 우리나라 전 지역 가뭄의 시 공간적인 가뭄변동특성을 파악하고, 기존에 사용되고 있는 가뭄지수의 적합도 평가를 통해 우리나라 가뭄특성을 가장 잘 반영한 가뭄지수의 선정과 각종 기후특성을 잘 반영하는 좀 더 향상된 가뭄지수 개발에 도움을 줄 수 있으며, 가뭄의 시 공간적인 예측에 대해 적합한 가뭄지수 선택에 도움을 줄 것으로 판단된다.

• Korean Journal of Remote Sensing
• /
• v.30 no.5
• /
• pp.587-596
• /
• 2014

Soil moisture is one of the most important interests in hydrological response and the interaction between the land surface and atmosphere. Estimation of Antecedent Wetness Conditions (AWC) which is soil moisture condition prior to a rainfall in the basin should be considered for rainfall-runoff prediction. In this study, Soil Wetness Index (SWI), Antecedent Precipitation Index ($API_5$), remotely sensed Soil Moisture ($SM_{rs}$), and 5 days ground Soil Moisture ($SM_{g5}$) were selected to estimate the AWC at four study area in the Korean Peninsula. The remotely sensed soil moisture data were taken from the AMSR-E soil moisture archive. The maximum potential retention ($S_{obs}$) was obtained from direct runoff and rainfall using Soil Conservation Service-Curve Number (SCS-CN) method by rainfall data of 2011 for each study area. Results showed the great correlations between the maximum potential retention and SWI with a mean correlation coefficient which is equal to -0.73. The results of time length representing the time scale of soil moisture showed a gap from region to region. It was due to the differences of soil types and the characteristics of study area. Since the remotely sensed soil moisture has been proved as reasonable hydrological variables to predict a wetness in the basin, it should be continuously monitored.

• Journal of Environmental Science International
• /
• v.30 no.12
• /
• pp.1053-1065
• /
• 2021

In this study, the prediction technology of Hydrological Quantitative Precipitation Forecast (HQPF) was improved by optimizing the weather predictors used as input data for machine learning. Results comparison was conducted using bias and Root Mean Square Error (RMSE), which are predictive accuracy verification indicators, based on the heavy rain case on August 21, 2021. By comparing the rainfall simulated using the improved HQPF and the observed accumulated rainfall, it was revealed that all HQPFs (conventional HQPF and improved HQPF 1 and HQPF 2) showed a decrease in rainfall as the lead time increased for the entire grid region. Hence, the difference from the observed rainfall increased. In the accumulated rainfall evaluation due to the reduction of input factors, compared to the existing HQPF, improved HQPF 1 and 2 predicted a larger accumulated rainfall. Furthermore, HQPF 2 used the lowest number of input factors and simulated more accumulated rainfall than that projected by conventional HQPF and HQPF 1. By improving the performance of conventional machine learning despite using lesser variables, the preprocessing period and model execution time can be reduced, thereby contributing to model optimization. As an additional advanced method of HQPF 1 and 2 mentioned above, a simulated analysis of the Local ENsemble prediction System (LENS) ensemble member and low pressure, one of the observed meteorological factors, was analyzed. Based on the results of this study, if we select for the positively performing ensemble members based on the heavy rain characteristics of Korea or apply additional weights differently for each ensemble member, the prediction accuracy is expected to increase.