입력자료 군집화에 따른 앙상블 머신러닝 모형의 수질예측 특성 연구 = The Effect of Input Variables Clustering on the Characteristics of Ensemble Machine Learning Model for Water Quality Prediction

다국어 초록 (Multilingual Abstract)

Water quality prediction is essential for the proper management of water supply systems. Increased suspended sediment concentration (SSC) has various effects on water supply systems such as increased treatment cost and consequently, there have been various efforts to develop a model for predicting SSC. However, SSC is affected by both the natural and anthropogenic environment, making it challenging to predict SSC. Recently, advanced machine learning models have increasingly been used for water quality prediction. This study developed an ensemble machine learning model to predict SSC using the XGBoost (XGB) algorithm. The observed discharge (Q) and SSC in two fields monitoring stations were used to develop the model. The input variables were clustered in two groups with low and high ranges of Q using the k-means clustering algorithm. Then each group of data was separately used to optimize XGB (Model 1). The model performance was compared with that of the XGB model using the entire data (Model 2). The models were evaluated by mean squared error-observation standard deviation ratio (RSR) and root mean squared error. The RSR were 0.51 and 0.57 in the two monitoring stations for Model 2, respectively, while the model performance improved to RSR 0.46 and 0.55, respectively, for Model 1.

참고문헌 (Reference)

1 박정수, "딥러닝과 앙상블 머신러닝 모형의 하천 탁도 예측 특성 비교 연구" 대한상하수도학회 35 (35): 83-91, 2021

2 송주원, "결측자료의 k-평균 군집분석" 한국자료분석학회 19 (19): 689-697, 2017

3 Chen, T., "Xgboost: A scalable tree boosting system" Association for Computing Machinery 785-794, 2016

4 Haghiabi, A. H., "Water quality prediction using machine learning methods" 53 : 3-13, 2018

5 United States Geological Survey(USGS)., "USGS(United States Geological Survey) Water-Data Report 2009" Redwood Creek at Orick 2009

6 Warrick, J. A., "Trends in the suspended-sediment yields of coastal rivers of northern California, 1955–2010" 489 : 108-123, 2013

7 Warrick, J. A., "Trend analyses with river sediment rating curves" 29 (29): 936-949, 2015

8 Uddameri, V., "Tree-based modeling methods to predict nitrate exceedances in the Ogallala aquifer in Texas" 12 : 1023-, 2020

9 Lin, W., "Treating high-turbidity water using full-scale floc blanket clarifiers" 130 (130): 1481-1487, 2004

10 Gray, A. B., "The effect of El Niño Southern Oscillation cycles on the decadal scale suspended sediment behavior of a coastal dry‐summer subtropical catchment" 40 : 272-284, 2015

11 Pedregosa, F., "Scikit-learn : Machine learning in Python" 12 : 2825-2830, 2011

12 Li, L., "Recent advances in artificial intelligence and machine learning for nonlinear relationship analysis and process control in drinking water treatment : A review" 405 : 126673-, 2021

13 Shin, Y., "Prediction of chlorophyll-a concentrations in the Nakdong river using machine learning methods" 12 : 1822-, 2020

14 Wang, Y., "Predicting water turbidity in a macro-tidal coastal bay using machine learning approaches, Estuarine" 252 : 107276-, 2021

15 United States Geological Survey, "National Water Information System (NWIS)"

16 Hollister, J. W., "Modeling lake trophic state: A random forest approach" 7 : e01321-, 2016

17 Moriasi, D. N., "Model evaluation guidelines for systematic quantification of accuracy in watershed simulations" 50 (50): 885-900, 2007

18 박정수, "LSTM 모형을 이용한 하천 고탁수 발생 예측 연구" 대한상하수도학회 34 (34): 35-43, 2020

19 박노경, "K-Means 군집모형과 계층적 군집(교차효율성 메트릭스에 의한 평균연결법, Ward법)모형 및 혼합모형을 이용한 컨테이너항만의 클러스터링 측정에 대한 실증적 비교 및 검증에 관한 연구" 한국항만경제학회 34 (34): 17-52, 2018

20 Packman, A. I., "Interplay of stream‐subsurface exchange, clay particle deposition, and streambed evolution" 39 (39): 1097-, 2003

21 Friedman, J. H., "Greedy function approximation : A gradient boosting machine" 29 (29): 1189-1232, 2001

22 Ayub, J., "Glaucoma detection through optic disc and cup segmentation using k-mean clustering" 143-147, 2016

23 Hicks, D. M., "Erosion thresholds and suspended sediment yields, Waipaoa river basin, New Zealand" 36 : 1129-1142, 2000

24 Singer, M. B., "Enduring legacy of a toxic fan via episodic redistribution of California gold mining debris" 110 : 18436-18441, 2013

25 Park, J., "Coupling fine particle and bedload transport in gravel-bedded streams" 552 : 532-543, 2017

26 Gray, A. B., "Conversion to drip irrigated agriculture may offset historic anthropogenic and wildfire contributions to sediment production" 556 : 219-230, 2016

27 Muhammad, S. Y., "Classification model for water quality using machine learning techniques" 9 : 45-52, 2015

28 Sutton, C. D., "Classification and regression trees, bagging, and boosting" 24 : 303-329, 2005

29 Bennett, N. D., "Characterising performance of environmental models" 40 : 1-20, 2013

30 Walling, D., "Assessing the accuracy of suspended sediment rating curves for a small basin" 13 (13): 531-538, 1977

31 Zhang, Y., "An empirical study to determine the optimal k in Ek-NNclus method" 260-268, 2018

32 Stevenson, M., "Advanced turbidity prediction for operational water supply planning" 119 : 72-84, 2019

33 Ahmad, A., "A k-mean clustering algorithm for mixed numeric and categorical data" 63 : 503-527, 2007

34 Zhang, D., "A data-driven design for fault detection of wind turbines using random forests and XGboost" 6 : 21020-21031, 2018