• Journal of Korean Society of Disaster and Security
• /
• v.12 no.2
• /
• pp.73-82
• /
• 2019

Recently, as the occurrence frequency of sudden floods due to climate change increased, the flood damage on riverside social infrastructures was extended so that there has been a threat of overflow. Therefore, a rapid prediction of potential flooding in riverside social infrastructure is necessary for administrators. However, most current flood forecasting models including hydraulic model have limitations which are the high accuracy of numerical results but longer simulation time. To alleviate such limitation, data driven models using artificial neural network have been widely used. However, there is a limitation that the existing models can not consider the time-series parameters. In this study the water surface elevation of the Hangang River bridge was predicted using the NARX model considering the time-series parameter. And the results of the ANN and RNN models are compared with the NARX model to determine the suitability of NARX model. Using the 10-year hydrological data from 2009 to 2018, 70% of the hydrological data were used for learning and 15% was used for testing and evaluation respectively. As a result of predicting the water surface elevation after 3 hours from the Hangang River bridge in 2018, the ANN, RNN and NARX models for RMSE were 0.20 m, 0.11 m, and 0.09 m, respectively, and 0.12 m, 0.06 m, and 0.05 m for MAE, and 1.56 m, 0.55 m and 0.10 m for peak errors respectively. By analyzing the error of the prediction results considering the time-series parameters, the NARX model is most suitable for predicting water surface elevation. This is because the NARX model can learn the trend of the time series data and also can derive the accurate prediction value even in the high water surface elevation prediction by using the hyperbolic tangent and Rectified Linear Unit function as an activation function. However, the NARX model has a limit to generate a vanishing gradient as the sequence length becomes longer. In the future, the accuracy of the water surface elevation prediction will be examined by using the LSTM model.

• Journal of Wetlands Research
• /
• v.23 no.2
• /
• pp.144-153
• /
• 2021

In recently, the green algae bloom is one of the most severe challenges. The seven days prior prediction is in operation to issues the water quality warning, but it also needs a longer time of prediction to take preemptive measures. The objective of the study is to establish a method to conduct a 3-month prior prediction of Chl-a concentration in the Daechong Lake and tested its applicability as a supplementary of current water quality warning. The historical record of water quality in the Daechong Lake and seasonal forecasting of ECMWF were obtained, and its time-series characteristics were analyzed. The Chl-a forecasting model was established using a correlation between Chl-a concentration and meteorological factor and NARX model, and its efficiency was compared.

• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.507-507
• /
• 2016

하천의 수온은 하천의 생태적 환경적인 시스템의 거동을 결정짓는 가장 중요한 요소이며, 특히 수생생물이나 하천 수질에 대해서는 중요한 제약요건으로 작용하게 된다. 특히, 냉수성 생물의 경우에는 수온의 변동이 치명적일 수 있으며 각종 수문환경 측면에서 악영향을 미치게 된다. 이러한 수온의 예측 및 모델링을 위하여 여러 가지 방법이 제시되고 있으나, 크게 회귀모형, 결정론적, 추계학적인 3가지 방법론으로 분류할 수 있다 (Cassie, 2006). 일반적으로 결정론적 방법은 지배방정식에 의거하여 하천 내에서의 다양한 열교환을 모의하며 복잡한 열평형을 모의하는데 적합하나 상대적으로 많은 자료를 요구하는 단점이 있다. 대조적으로 추계학적 방법의 경우에는 상대적으로 적은 인자를 통해서도 모의 가능한 장점이 있기 때문에 가용 자료가 부족할 경우에도 모의할 수 있는 장점이 있다. 본 연구에서는 캐나다 동북부 Quebec 지방의 Du Loup 지역의 소하천을 대상으로 하여 2011년부터 2014년 까지 수온을 측정하고 이를 결정론적/추계학적 방법론으로 통하여 모의하여 그 효율성을 고찰하고자 하였다. 이를 위하여 Hobo Pro thermograph (${\pm}0.2^{\circ}C$), Kipp & Zonen Pyranometer (${\pm}10uV/m^2$) 등을 설치하여 자료를 수집하였으며, 물리수문학적 수온모형인 CEQUEAU 모형과 추계학적 방법인 ARMAX 및 NARX 모형을 통하여 수온을 모의하였다. 모의 결과에 따라서, 저수지를 비롯한 불확정 요소가 존재할 경우에는 상대적으로 추계학적 모형이 안정적인 결과를 보여주는 것으로 나타났으며, 본 연구를 통하여 제시된 방법론은 향후 소하천 지역의 환경 및 수질 관련 분석에 유용한 자료로서 활용될 것으로 판단된다. 수 있을 것이다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.9
• /
• pp.729-738
• /
• 2021

Feedback flow control using an artificial neural network was numerically investigated for NACA0015 Airfoil to suppress flow separation on an airfoil. In order to achieve goal of flow control which is aimed to reduce the size of separation on the airfoil, Blowing&Suction actuator was implemented near the separation point. In the system modeling step, the proper orthogonal decomposition was applied to the pressure field. Then, some POD modes that are necessary for flow control are extracted to analyze the unsteady characteristics. NARX neural network based on decomposed modes are trained to represent the flow dynamics and finally operated in the feedback control loop. Predicted control signal was numerically applied on CFD simulation so that control effect was analyzed through comparing the characteristic of aerodynamic force and spatial modes depending on the presence of the control. The feedback control showed effectiveness in pressure drag reduction up to 29%. Numerical results confirm that the effect is due to dramatic pressure recovery around the trailing edge of the airfoil.

• Journal of Korea Water Resources Association
• /
• v.51 no.11
• /
• pp.1021-1029
• /
• 2018

A primary objective of this study is to develop a drought forecasting technique based on groundwater which can be exploit for water supply under drought stress. For this purpose, we explored the lagged relationships between regionalized SGI (standardized groundwater level index) and SPI (standardized precipitation index) in view of the drought propagation. A regional prediction model was constructed using a NARX (nonlinear autoregressive exogenous) artificial neural network model which can effectively capture nonlinear relationships with the lagged independent variable. During the training phase, model performance in terms of correlation coefficient was found to be satisfactory with the correlation coefficient over 0.7. Moreover, the model performance was described by root mean squared error (RMSE). It can be concluded that the proposed approach is able to provide a reliable SGI forecasts along with rainfall forecasts provided by the Korea Meteorological Administration.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.13-13
• /
• 2020

'20년 3월 현재 전국 3,502개 읍면동 중 73개 읍면동이 지하수를 상수원으로 급수 중이며, 48개 산업단지에서 지하수를 주 수원으로 사용 중이다. 또한 급수 소외지역의 물 공급을 위해 주로 사용되는 소규모수도시설 14,811개 중 12,073개(81.5%)는 지하수를 이용하고 있으며, 그 위치는 전국에 산재해 있다. 이처럼 지하수는 댐, 저수지 및 하천과 더불어 생·공용수의 중요한 수원이라 할 수 있다. 본 연구에서는 급수 소외지역의 주요 수원인 지하수위 현황을 이용한 가뭄 모니터링 및 전망 기법을 개발하고자 하였다. 국가 지하수관측망 중 10년 이상 장기 관측 자료를 보유한 253개 관측소의 일단위 관측자료를 기반으로, 과거 관측수위 분포를 핵밀도함수로 추정하고 Quantile Function을 이용해 현재 수위의 높고 낮은 정도를 Percentile 값으로 산정하였다. 관측소별 지하수위 Percentile은 티센망을 이용해 167개 시군별로 공간평균하고 Percentile의 범위에 따른 가뭄등급을 설정하여 지하수 가뭄 정도를 모니터링 할 수 있는 기법을 제시하였다. 또한 지하수 가뭄을 전망하기 위해 강수와 지하수위의 거시적인 응답특성을 이용하였다. 관측소별로 추정된 핵밀도함수의 누적확률을 표준정규분포의 Quantile로 변환하여 표준지하수지수I(Standardized Groundwater level Index, SGI)를 산정하고, 시군별로 공간을 일치시킨 1~12개월 지속기간별 표준강수지수(Standardized Precipitation Index, SPI)와의 상관관계를 이용해 NARX(nonlinear autoregressive exogenous) 인공신경망 예측모형을 구축하였다. 이를 통해 기상청 정량전망 강수량을 이용해 전국의 1~3개월 후 지하수 가뭄을 빠르게 전망할 수 있는 체계를 구축하고, 생·공용수 분야 국가 가뭄 예·경보의 미급수지역 가뭄현황 및 전망에 활용중이다.