댐 일유입량 예측을 위한 데이터 전처리 방법에 따른 머신러닝 및 딥러닝 모델 적용의 비교연구 = Comparative Study of Machine Learning and Deep Learning Models Applied to Data Preprocessing Methods for Dam Inflow Prediction

다국어 초록 (Multilingual Abstract)

In this study, we employed representative machine learning (ML) and deep learning (DL) models previously utilized in the fields of rainfall and runoff analysis in the water resources sector. We not only performed hyperparameter tuning of the models but also considered the characteristics of the model and the combination and preprocessing (such as lag-time and moving average) of meteorological and hydrological data. We then compared and evaluated the performance of the models according to various scenarios of data characteristics and ML & DL model combinations for predicting daily water inflow. To accomplish this, we utilized meteorological and hydrological data collected from 1974 to 2021 in the Soyang River Dam Basin to examine 1) precipitation, 2) inflow, and 3) meteorological data as primary independent variables. We then employed a total of 36 scenario combinations as input data for ML & DL, applying a) lag-time, b) moving average, and c) component separation conditions for inflow. To identify the most suitable data combination characteristics and ML & DL models for predicting daily inflow, we compared and evaluated 10 different ML & DL models: 1) Linear Regression, 2) Lasso, 3) Ridge, 4) Support Vector Regression, 5) Random Forest (RF), 6) Light Gradient Boosting Model, 7) XGBoost for ML, and 8) Long Short-Term Memory (LSTM) models, 9) Temporal Convolutional Network (TCN), and 10) LSTM-TCN for DL.

참고문헌 (Reference)

1 박명기 ; 윤영석 ; 이현호 ; 김주환, "다목적댐 유입량 예측을 위한 Recurrent Neural Network 모형의 적용 및 평가" 한국수자원학회 51 (51): 1217-1227, 2018

2 김동균 ; 강석구, "강수-일유출량 추정 LSTM 모형의 구축을 위한 자료 수집 방안" 한국수자원학회 54 (54): 795-805, 2021

3 Chen T, "XGBoost: a scalable tree boosting system" 2016

4 Singh VP, "Watershed models" CRC Press 2005

5 Abadi M, "TensorFlow: a system for large-scale machine learning" 2016

6 Cortes C, "Support-vector networks" 20 (20): 273-797, 1995

7 Gao S, "Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation" 589 : 125188-, 2020

8 Pedregosa F, "Scikit-learn : machine learning in python" 12 : 2825-2830, 2011

9 Nash JE, "River flow forecasting through conceptual models part I—A discussion of principles" 10 (10): 282-290, 1970

10 Bastola S, "Regionalisation of hydrological model parameters under parameter uncertainty : a case study involving TOPMODEL and basins across the globe" 357 (357): 188-120, 2008

11 Breiman L, "Random forests" 45 (45): 5-32, 2001

12 Kratzert F, "Rainfall–runoff modelling using Long Short-Term Memory(LSTM)networks" 22 (22): 6005-6022, 2018

13 Paszke A, "PyTorch : an imperative style, high-performance deep learning library" 2019

14 Leavesley GH, "Precipitation-runoff modeling system: user’s manual" USGS 1983

15 Hopfield JJ, "Neural networks and physical systems with emergent collective computational abilities" 79 (79): 2554-2558, 1982

16 Janiesch C, "Machine learning and deep learning" 31 (31): 685-695, 2021

17 Hochreiter S, "Long short-term memory" 9 (9): 1735-1780, 1997

18 Arnold JG, "Large area hydrologic modeling and assessment part I : model development 1" 34 (34): 73-89, 1998

19 Bicknell BR, "Hydrological simulation program–FORTRAN (HSPF), user’s manual for version 12.0" U.S. Environmental Protection Agency 2001

20 Dawson CW, "Hydrological modelling using artificial neural networks" 25 (25): 80-108, 2001

21 Ghoraba SM, "Hydrological modeling of the Simly Dam watershed(Pakistan)using GIS and SWAT model" 54 (54): 583-594, 2015

22 Hu C, "Deep learning with a long short-term memory networks approach for rainfallrunoff simulation" 10 (10): 1543-, 2018

23 Gupta HV, "Decomposition of the mean squared error and NSE performance criteria : implications for improving hydrological modelling" 377 (377): 80-89, 2009

24 Zhang J, "Daily runoff forecasting by deep recursive neural network" 596 : 126067-, 2021

25 Abu El-Nasr A, "Comparison of two methods to split the total discharge in its components" 2002 : 253-258, 2002

26 Fan H, "Comparison of long short term memory networks and the hydrological model in runoff simulation" 12 (12): 175-, 2020

27 Babur M, "Assessment of climate change impact on reservoir inflows using multi climate-models under RCPs—The case of Mangla Dam in Pakistan" 8 (8): 389-, 2016

28 Abbott MB, "An introduction to the European Hydrological System—Systeme Hydrologique Europeen, "SHE", 1 : history and philosophy of a physically-based, distributed modelling system" 87 (87): 45-59, 1986

29 Xiang Z, "A rainfall-runoff model with LSTMbased sequence-to-sequence learning" 56 (56): e2019WR025-, 2020

30 Gourley JJ, "A method for identifying sources of model uncertainty in rainfall-runoff simulations" 327 (327): 68-68, 2006

31 McCulloch WS, "A logical calculus of the ideas immanent in nervous activity" 5 (5): 115-133, 1943