Correlation-based Feature Selection 기법과 Random Forest 알고리즘을 이용한 한강유역 지류의 TDI 예측 연구 = A Study on Predicting TDI(Trophic Diatom Index) in tributaries of Han river basin using Correlation-based Feature Selection technique and Random Forest algorithm

다국어 초록 (Multilingual Abstract)

The purpose of this study is to predict Trophic Diatom Index (TDI) in tributaries of the Han River watershed using the random forest algorithm. The one year (2017) and supplied aquatic ecology health data were used. The data includes water quality(BOD, T-N, NH3-N, T-P, PO4-P, water temperature, DO, pH, conductivity, turbidity), hydraulic factors(water width, average water depth, average velocity of water), and TDI score. Seven factors including water temperature, BOD, T-N, NH3-N, T-P, PO4-P, and average water depth are selected by the Correlation Feature Selection. A TDI prediction model was generated by random forest using the seven factors. To evaluate this model, 2017 data set was used first. As a result of the evaluation, R2, % Difference, NSE(Nash-Sutcliffe Efficiency), RMSE(Root Mean Square Error) and accuracy rate show that this model is compatible with predicting TDI. To be more concrete, R2 is 0.93, % Difference is –0.37, NSE is 0.89, RMSE is 8.22 and accuracy rate is 70.4%. Also, additional evaluation using data set more than 17 times the measured point was performed. The results were similar when the 2017 data set were used. The Wilcoxon Signed Ranks Test shows there was no statistically significant difference between actual and predicted data for the 2017 data set. These results can specify the elements which probably affect aquatic ecology health. Also, these will provide direction relative to water quality management for a watershed that must be continuously preserved.

참고문헌 (Reference)

1 갈병석, "통합수질지수를 이용한 지류지천 수질평가" 한국습지학회 19 (19): 311-317, 2017

2 안광국, "유등천에서의 생태학적 건강도 평가 및 수질양상" 한국하천호수학회 38 (38): 341-351, 2005

3 황순진, "돌말(Epilithic Diatom) 지수를 이용한 국내 주요 하천(금강, 영산강, 섬진강)의 생물학적 수질평가" 한국물환경학회 22 (22): 784-795, 2006

4 나승민, "낙동강 지류·지천의 유량·수질 특성 및 하천관리를 위한 등급화 방안 연구" 한국습지학회 17 (17): 380-390, 2015

5 최재신, "낙동강 상류 수계인 내성천의 부착돌말 군집과 부착돌말지수를 이용한 생물학적 수질평가" 한국하천호수학회 50 (50): 470-477, 2017

6 조인환, "금강권역 주요 하천의 돌부착돌말류 분포 및 출현예측" 한국하천호수학회 48 (48): 153-167, 2015

7 Kelly, M. G., "The trophic diatom Index : a new index for monitoring eutrophication in rivers" 7 : 433-444, 1995

8 Prygiel, J., "The assessment of water quality in the Artois-Picardie water basin(France)by the use of diatom indices" 269 (269): 343-349, 1993

9 우소영, "SWAT 및 random forest를 이용한 기후변화에 따른 한강유역의 수생태계 건강성 지수 영향 평가" 한국수자원학회 51 (51): 863-874, 2018

10 Nash, J. E., "River flow forecasting through conceptual models. Part I-A discussion of principles" 10 (10): 282-290, 1970

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

12 Kong, D. S., "Necessity and approach of establishing biological water quality standards" 20 (20): 38-49, 2002

13 National Institute of Environmental Research, "Nationwide aquatic ecological monitoring program"

14 National Institute of Environmental Research, "National aquatic ecological monitoring program"

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

16 Ministry of Land, Infrastructure and Transport, "Korea river catalog"

17 Hall, M. A., "Correlation-based feature selection for machine learning" The University of Waikato 1999

18 National Institute of Environmental Research, "Biomonitoring survey and assessment manual"

19 Duda, P. B., "BASINS/HSPF : Model use, calibration and validation" 55 (55): 1523-1547, 2012