합리적인 하천수 관리체계 구축을 위한 자료기반 방류량 예측모형 개발 = Development of a Data-Driven Model for Forecasting Outflow to Establish a Reasonable River Water Management System

다국어 초록 (Multilingual Abstract)

In most cases of the water balance analysis, the return flow ratio for each water supply was uniformly determined and applied, so it has been contained a problem that the volume of available water would be incorrectly calculated. Therefore, sewage and wastewater among the return water were focused in this study and the data-driven model was developed to forecast the outflow from the sewage treatment plant. The forecasting results of LSTM (Long Short-Term Memory), GRU (Gated Recurrent Units), and SVR (Support Vector Regression) models, which are mainly used for forecasting the time series data in most fields, were compared with the observed data to determine the optimal model parameters for forecasting outflow. As a result of applying the model, the root mean square error (RMSE) of the GRU model was smaller than those of the LSTM and SVR models, and the Nash-Sutcliffe coefficient (NSE) was higher than those of others. Thus, it was judged that the GRU model could be the optimal model for forecasting the outflow in sewage treatment plants. However, the forecasting outflow tends to be underestimated and overestimated in extreme sections. Therefore, the additional data for extreme events and reducing the minimum time unit of input data were necessary to enhance the accuracy of forecasting. If the water use of the target site was reviewed and the additional parameters that could reflect seasonal effects were considered, more accurate outflow could be forecasted to be ready for climate variability in near future. And it is expected to use as fundamental resources for establishing a reasonable river water management system based on the forecasting results.

참고문헌 (Reference)

• 1 여운기, "인공신경망과 유전자알고리즘의 결합모형을 이용한 수위예측에 관한 연구" 한국수자원학회 43 (43): 721-731, 2010
• 2 오지환, "실제 물이용 체계를 고려한 한강 동해 권역 물수급 평가" 한국방재학회 19 (19): 529-543, 2019
• 3 유형주, "시계열 자료의 예측을 위한 자료 기반 신경망 모델에 관한 연구: 한강대교 수위예측 적용" 한국방재안전학회 12 (12): 73-82, 2019
• 4 최시중, "수자원 계획 수립을 위한 물 수급 전망 개선 방안 연구" 한국방재학회 18 (18): 589-596, 2018
• 5 이재영, "수문모형과 기계학습을 연계한 실시간 하천홍수 예측" 대한토목학회 40 (40): 303-314, 2020
• 6 이승욱, "물수지 분석을 위한 불확실성 정량화" 한국수자원학회 38 (38): 281-292, 2005
• 7 이기하, "메콩강 유출모의를 위한 물리적 및 데이터 기반 모형의 비교 ․ 분석" 한국수자원학회 51 (51): 503-514, 2018
• 8 트란 광 카이, "딥러닝 기반 침수 수위 예측: 미국 텍사스 트리니티강 사례연구" 한국정보과학회 44 (44): 607-612, 2017
• 9 Zhang, D., "Use Long Short-term Memory to Enhance Internet of Things for Combined Sewer Overflow Monitoring" 556 : 409-418, 2018
• 10 Pascanu, R., "Understanding the Exploding Gradient Problem"
• 11 Olah, C., "Understanding Lstm Networks, August 2015"
• 12 Hochreiter, S., "The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions" 6 (6): 107-116, 1998
• 13 Ruxton, G. D., "The Unequal Variance t-test is an Underused Alternative to Student's t-test and the Mann–Whitney U test" 17 (17): 688-690, 2006
• 14 최서혜, "TDSVM을 이용한 하천수 취수량 예측" 한국수자원학회 52 (52): 1075-1086, 2019
• 15 Vapnik, V., "Support Vector Machines" 20 (20): 273-297, 1995
• 16 Ministry of Land Infrastructure and Transport(MOLIT), "National Water Resources Plan(2011~2020)"
• 17 Cho, K., "Learning Phrase Representations using RNN Encoder-decoder for Statistical Machine Translation"
• 18 Greff, K., "LSTM : A Search Space Odyssey" 28 (28): 2222-2232, 2016
• 19 Korea Meteorological Administration(KMA), "Korea Climate Change Assessment Report 2020" KMA 2020
• 20 Chung, J., "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling"
• 21 Zhang, J., "Developing a Long Short-Term Memory(LSTM)based Model for Predicting Water Table Depth in Agricultural Areas" 561 : 918-929, 2018
• 22 Agarap, A. F., "Deep Learning using Rectified Linear Units(RELU)"
• 23 Yoo, H. J., "Data Driven Water Surface Elevation Forecasting Model with Hybrid Activation Function—A Case Study for Hangang River, South Korea" 10 (10): 1424-, 2020
• 24 Chen, W. B., "Comparison of ANN Approach with 2D and 3D Hydrodynamic Models for Simulating Estuary Water Stage" 45 (45): 69-79, 2012
• 25 Jozefowicz, R., "An Empirical Exploration of Recurrent Network Architectures" 2342-2350, 2015