• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.264-268
• /
• 2008

미래 발생 가능한 수문 및 기상현상의 예측과정은 지식의 부족과 자연현상의 다양성으로 인해 불확실성을 포함하게 된다. 하지만 많은 예측들은 아직까지 확정적으로 제공되고 있으며, 결과적으로 예측결과의 불확실성 정도를 제공하지 못하고 있다. 앙상블 유량예측(ESP, Ensemble Streamflow Prediction)은 이러한 불확실성을 고려하여 수자원시스템의 의사결정에 있어 중요한 요소 중 하나인 유량예측을 수행할 수 있는 방법이다. 하지만 ESP의 결과는 기상자료, 유역 초기조건, 수문모형의 매개변수, 단순화된 수문모형에 의해 비교적 큰 불확실성을 포함하게 되며, 따라서 실제적인 현업에서의 사용을 위해서는 불확실성 정도를 줄이기 위한 사전 및 사후처리 과정이 요구된다. 본 연구에서는 국내에서 활용 가능한 기후 예보자료를 사용하여 앙상블 유량예측에 적용할 수 있는 사전처리 방안들을 검토하고, 국내에서 사후처리를 위해 적용되었던 최적선형 보정기법에 더해 다양한 기법들을 강우유출모형인 TANK모형의 모의결과 보정에 적용하였다. 사전 및 사후처리를 적용한 결과 기상자료와 유량예측과정에 존재하는 불확실성을 저감시키는 것이 가능하였다. 특히 사전 및 사후 처리가 동시에 적용되었을 경우 그 향상 정도가 단순히 각각의 방법에 의한 향상 정도를 합한 것보다 높게 나타날 수 있음이 확인되었다. 사전 및 사후처리를 동시에 적용한 경우 이수기에는 RPS(Ranked Probability Score) 평가방법 내에서 54%를, 홍수기에는 8%를 향상시키는 것이 가능하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.95-95
• /
• 2023

Common hydrological problems of developing countries include poor data management, insufficient measuring devices and ungauged watersheds, leading to small or unreliable data availability. This has greatly affected the adoption of artificial intelligence techniques for flood risk mitigation and damage control in several developing countries. While climate datasets have recorded resounding applications, but they exhibit more uncertainties than ground-based measurements. To encourage AI adoption in developing countries with small ground-based dataset, we propose data augmentation for regression tasks and compare performance evaluation of different AI models with and without data augmentation. More focus is placed on simple models that offer lesser computational cost and higher accuracy than deeper models that train longer and consume computer resources, which may be insufficient in developing countries. To implement this approach, we modelled and predicted streamflow data of the Asa River Watershed located in Ilorin, Kwara State Nigeria. Results revealed that adequate hyperparameter tuning and proper model selection improve streamflow prediction on small water dataset. This approach can be implemented in data-scarce regions to ensure timely flood intervention and early warning systems are adopted in developing countries.

• Journal of Wetlands Research
• /
• v.26 no.2
• /
• pp.147-159
• /
• 2024

Lack of streamflow observations makes model calibration difficult and limits model performance improvement. Satellite-based remote sensing products offer a new alternative as they can be actively utilized to obtain hydrological data. Recently, several studies have shown that artificial intelligence-based solutions are more appropriate than traditional conceptual and physical models. In this study, a data-driven approach combining various recurrent neural networks and decision tree-based algorithms is proposed, and the utilization of satellite remote sensing information for AI training is investigated. The satellite imagery used in this study is from MODIS and SMAP. The proposed approach is validated using publicly available data from 25 watersheds. Inspired by the traditional regionalization approach, a strategy is adopted to learn one data-driven model by integrating data from all basins, and the potential of the proposed approach is evaluated by using a leave-one-out cross-validation regionalization setting to predict streamflow from different basins with one model. The GRU + Light GBM model was found to be a suitable model combination for target basins and showed good streamflow prediction performance in ungauged basins (The average model efficiency coefficient for predicting daily streamflow in 25 ungauged basins is 0.7187) except for the period when streamflow is very small. The influence of satellite remote sensing information was found to be up to 10%, with the additional application of satellite information having a greater impact on streamflow prediction during low or dry seasons than during wet or normal seasons.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.169-169
• /
• 2020

According to the IPCC analysis, severe climate changes are projected to occur in Korea as the temperature is expected to rise by 3.2 ℃, the precipitation by 15.6% and the sea level by 27cm by 2050. It is predicted that the occurrence of abnormal climate phenomena - especially those such as increase of concentrated precipitation and extreme heat in the summer season and severe drought in the winter season - that have happened in Korea in the past 30 years (1981-2010) will continuously be intensified and accelerated. As a result, the impact on and vulnerability of the water management sector is expected to be exacerbated. This research aims to predict the climate change impacts on streamflow of Daecheong Lake area of Geum River in South Korea during the summer and winter seasons, which show extreme meteorological events, and ultimately develop an integrated policy model in response. We projected and compared the streamflow changes of Daecheong Lake area of Geum River in South Korea in the near future period (2020-2040) and the far future period (2041-2060) with the reference period (1991-2010) using the HEC-HMS model. The data from a global climate model HadGEM2-AO, which is the fully-coupled atmosphere-ocean version of the Hadley Centre Global Environment Model 2, and RCP scenarios (RCP4.5 and RCP8.5) were used as inputs for the HEC-HMS model to identify the river basins where cases of extreme flooding or drought are likely to occur in the near and far future. The projections were made for the summer season (July-September) and the winter season(November-January) in order to reflect the summer monsoon and the dry winter. The results are anticipated to be used by policy makers for preparation of adaptation plans to secure water resources in the nation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.18-18
• /
• 2011

Climate change is impacting and will increasingly impact both the quantity and quality of the world's water resources in a variety of ways. In some areas warming climate results in increased rainfall, surface runoff, and groundwater recharge while in others there may be declines in all of these. Water quality is described by a number of variables. Some are directly impacted by climate change. Temperature is an obvious example. Notably, increased atmospheric concentrations of $CO_2$ triggering climate change increase the $CO_2$ dissolving into water. This has manifold consequences including decreased pH and increased alkalinity, with resultant increases in dissolved concentrations of the minerals in geologic materials contacted by such water. Climate change is also expected to increase the number and intensity of extreme climate events, with related hydrologic changes. A simple framework has been developed in New Zealand for assessing and predicting climate change impacts on water resources. Assessment is largely based on trend analysis of historic data using the non-parametric Mann-Kendall method. Trend analysis requires long-term, regular monitoring data for both climate and hydrologic variables. Data quality is of primary importance and data gaps must be avoided. Quantitative prediction of climate change impacts on the quantity of water resources can be accomplished by computer modelling. This requires the serial coupling of various models. For example, regional downscaling of results from a world-wide general circulation model (GCM) can be used to forecast temperatures and precipitation for various emissions scenarios in specific catchments. Mechanistic or artificial intelligence modelling can then be used with these inputs to simulate climate change impacts over time, such as changes in streamflow, groundwater-surface water interactions, and changes in groundwater levels. The Waimea Plains catchment in New Zealand was selected for a test application of these assessment and prediction methods. This catchment is predicted to undergo relatively minor impacts due to climate change. All available climate and hydrologic databases were obtained and analyzed. These included climate (temperature, precipitation, solar radiation and sunshine hours, evapotranspiration, humidity, and cloud cover) and hydrologic (streamflow and quality and groundwater levels and quality) records. Results varied but there were indications of atmospheric temperature increasing, rainfall decreasing, streamflow decreasing, and groundwater level decreasing trends. Artificial intelligence modelling was applied to predict water usage, rainfall recharge of groundwater, and upstream flow for two regionally downscaled climate change scenarios (A1B and A2). The AI methods used were multi-layer perceptron (MLP) with extended Kalman filtering (EKF), genetic programming (GP), and a dynamic neuro-fuzzy local modelling system (DNFLMS), respectively. These were then used as inputs to a mechanistic groundwater flow-surface water interaction model (MODFLOW). A DNFLMS was also used to simulate downstream flow and groundwater levels for comparison with MODFLOW outputs. MODFLOW and DNFLMS outputs were consistent. They indicated declines in streamflow on the order of 21 to 23% for MODFLOW and DNFLMS (A1B scenario), respectively, and 27% in both cases for the A2 scenario under severe drought conditions by 2058-2059, with little if any change in groundwater levels.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.22 no.4
• /
• pp.108-114
• /
• 1980

A deterministic conceptual erosion model which simulates detachment, entrainment, transport and deposition of eroded soil particles by rainfall impact and flowing water is presented. Both upland and channel phases of sediment yield are incorporated into the erosion model. The algorithms for the soil erosion and sedimentation processes including land and crop management effects are taken from the literature and then solved using a digital computer. The erosion model is used in conjunction with the modified Kentucky Watershed Model which simulates the hydrologic characteristics from watershed data. The two models are linked together by using the appropriate computer code. Calibrations for both the watershed and erosion model parameters are made by comparing the simulated results with actual field measurements in the Four Mile Creek watershed near Traer, Iowa using 1976 and 1977 water year data. Two water years, 1970 and 1978 are used as test years for model verification. There is good agreement between the mean daily simulated and recorded streamflow and between the simulated and recorded suspended sediment load except few partial differences. The following conclusions were drawn from the results after testing the watershed and erosion model. 1. The watershed and erosion model is a deterministic lumped parameter model, and is capable of simulating the daily mean streamflow and suspended sediment load within a 20 percent error, when the correct watershed and erosion parameters are supplied. 2. It is found that soil erosion is sensitive to errors in simulation of occurrence and intensity of precipitation and of overland flow. Therefore, representative precipitation data and a watershed model which provides an accurate simulation of soil moisture and resulting overland flow are essential for the accurate simulation of soil erosion and subsequent sediment transport prediction. 3. Erroneous prediction of snowmelt in terms of time and magnitute in conjunction with The frozen ground could be the reason for the poor simulation of streamflow as well as sediment yield in the snowmelt period. More elaborate and accurate snowmelt submodels will greatly improve accuracy. 4. Poor simulation results can be attributed to deficiencies in erosion model and to errors in the observed data such as the recorded daily streamflow and the sediment concentration. 5. Crop management and tillage operations are two major factors that have a great effect on soil erosion simulation. The erosion model attempts to evaluate the impact of crop management and tillage effects on sediment production. These effects on sediment yield appear to be somewhat equivalent to the effect of overland flow. 6. Application and testing of the watershed and erosion model on watersheds in a variety of regions with different soils and meteorological characteristics may be recommended to verify its general applicability and to detact the deficiencies of the model. Futhermore, by further modification and expansion with additional data, the watershed and erosion model developed through this study can be used as a planning tool for watershed management and for solving agricultural non-point pollution problems.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2002.05a
• /
• pp.43-50
• /
• 2002

Accurate quantitative forecasting of rainfall for basins with a short response time is essential to predict streamflow and flash floods. Previously, neural networks were used to develop a Quantitative Precipitation Forecasting (QPF) model that highly improved forecasting skill at specific locations in Pennsylvania, using both Numerical Weather Prediction (NWP) output and rainfall and radiosonde data. The objective of this study was to improve an existing artificial neural network model and incorporate the evolving structure and frequency of intense weather systems in the mid-Atlantic region of the United States for improved flood forecasting. Besides using radiosonde and rainfall data, the model also used the satellite-derived characteristics of storm systems such as tropical cyclones, mesoscale convective complex systems and convective cloud clusters as input. The convective classification and tracking system (CCATS) was used to identify and quantify storm properties such as life time, area, eccentricity, and track. As in standard expert prediction systems, the fundamental structure of the neural network model was learned from the hydroclimatology of the relationships between weather system, rainfall production and streamflow response in the study area. The new Quantitative Flood Forecasting (QFF) model was applied to predict streamflow peaks with lead-times of 18 and 24 hours over a five year period in 4 watersheds on the leeward side of the Appalachian mountains in the mid-Atlantic region. Threat scores consistently above .6 and close to 0.8 ∼ 0.9 were obtained fur 18 hour lead-time forecasts, and skill scores of at least 4％ and up to 6％ were attained for the 24 hour lead-time forecasts. This work demonstrates that multisensor data cast into an expert information system such as neural networks, if built upon scientific understanding of regional hydrometeorology, can lead to significant gains in the forecast skill of extreme rainfall and associated floods. In particular, this study validates our hypothesis that accurate and extended flood forecast lead-times can be attained by taking into consideration the synoptic evolution of atmospheric conditions extracted from the analysis of large-area remotely sensed imagery While physically-based numerical weather prediction and river routing models cannot accurately depict complex natural non-linear processes, and thus have difficulty in simulating extreme events such as heavy rainfall and floods, data-driven approaches should be viewed as a strong alternative in operational hydrology. This is especially more pertinent at a time when the diversity of sensors in satellites and ground-based operational weather monitoring systems provide large volumes of data on a real-time basis.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.275-288
• /
• 2006

This study develops ESP (Ensemble Streamflow Prediction) system by using medium-term numerical weather prediction model which is GDAPS(T213) of KMA. The developed system forecasts medium- and long-range exceedance Probability for streamflow and RPSS evaluation scheme is used to analyze the accuracy of probability forecasts. It can be seen that the daily probability forecast results contain high uncertainties. A sensitivity analysis with respect to forecast time resolution shows that uncertainties decrease and accuracy generally improves as the forecast time step increase. Weekly ESP results by using the GDAPS output with a lead time of up to 28 days are more accurately predicted than traditional ESP results because conditional probabilities are stably distributed and uncertainties can be reduced. Therefore, it can be concluded that the developed system will be useful tool for medium- and long-term reservoir inflow forecasts in order to manage water resources.

• Journal of Korea Water Resources Association
• /
• v.56 no.12
• /
• pp.969-980
• /
• 2023

Since the 2000s, ensemble streamflow prediction (ESP) has been actively utilized in South Korea, primarily for hydrological forecasting purposes. Despite its notable success in hydrological forecasting, the original objective of enhancing water resources system management has been relatively overlooked. Consequently, this study aims to demonstrate the utility of ESP in water resources management by creating a simple hypothetical exercise for dam operators and applying it to actual multi-purpose dams in South Korea. The hypothetical exercise showed that even when the means of ESP are identical, different costs can result from varying standard deviations. Subsequently, using sampling stochastic dynamic programming (SSDP) and considering the capacity-inflow ratio (CIR), optimal release patterns were derived for Soyang Dam (CIR = 1.345) and Chungju Dam (CIR = 0.563) based on types W and P. For this analysis, Type W was defined with standard deviation equal to the mean inflow, and Type P with standard deviation ten times of the mean inflow. Simulated operations were conducted from 2020 to 2022 using the derived optimal releases. The results indicate that in the case of Dam Chungju, more aggressive optimal release patterns were derived under types with smaller standard deviations, and the simulated operations demonstrated satisfactory outcomes. Similarly, Soyang Dam exhibited similar results in terms of optimal release, but there was no significant difference in the simulation between types W and P due to its large CIR. Ultimately, this study highlights that even with the same mean values, the standard deviation of ESP impacts optimal release patterns and outcomes in simulation. Additionally, it underscores that systems with smaller CIRs are more sensitive to such uncertainties. Based on these findings, there is potential for improvements in South Korea's current operational practices, which rely solely on single representative values for water resources management.

• Journal of Korea Water Resources Association
• /
• v.50 no.7
• /
• pp.489-502
• /
• 2017

The objective of this study is to propose and evaluate the BAYES-ESP, which is a dam inflow prediction method based on Ensemble Streamflow Prediction method (ESP) and Bayesian theory. ABCD rainfall-runoff model was used to predict monthly dam inflow. Monthly meteorological data collected from KMA, MOLIT and K-water and dam inflow data collected from K-water were used for the model calibration and verification. To estimate the performance of ABCD model, ESP and BAYES-ESP method, time series analysis and skill score (SS) during 1986~2015 were used. In time series analysis monthly ESP dam inflow prediction values were nearly similar for every years, particularly less accurate in wet and dry years. The proposed BAYES-ESP improved the performance of ESP, especially in wet year. The SS was used for quantitative analysis of monthly mean of observed dam inflows, predicted values from ESP and BAYES-ESP. The results indicated that the SS values of ESP were relatively high in January, February and March but negative values in the other months. It also showed that the BAYES-ESP improved ESP when the values from ESP and observation have a relatively apparent linear relationship. We concluded that the existing ESP method has a limitation to predict dam inflow in Korea due to the seasonality of precipitation pattern and the proposed BAYES-ESP is meaningful for improving dam inflow prediction accuracy of ESP.