머신러닝 기법을 활용한 유황별 LOADEST 모형의 적정 회귀식 선정 연구: 낙동강 수계를 중심으로
Study of Selection of Regression Equation for Flow-conditions using Machine-learning Method: Focusing on Nakdonggang Waterbody
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
This study is to determine the coefficients of regression equations and to select the optimal regression equation in the LOADEST model after classifying the whole study period into 5 flow conditions for 16 watersheds located in the Nakdonggang waterbody. The optimized coefficients of regression equations were derived using the gradient descent method as a learning method in Tensorflow which is the engine of machine-learning method. In South Korea, the variability of streamflow is relatively high, and rainfall is concentrated in summer that can significantly affect the characteristic analysis of pollutant loads. Thus, unlike the previous application of the LOADEST model (adjusting whole study period), the study period was classified into 5 flow conditions to estimate the optimized coefficients and regression equations in the LOADEST model. As shown in the results, the equation #9 which has 7 coefficients related to flow and seasonal characteristics was selected for each flow condition in the study watersheds. When compared the simulated load (SS) to observed load, the simulation showed a similar pattern to the observation for the high flow condition due to the flow parameters related to precipitation directly. On the other hand, although the simulated load showed a similar pattern to observation in several watersheds, most of study watersheds showed large differences for the low flow conditions. This is because the pollutant load during low flow conditions might be significantly affected by baseflow or point-source pollutant load. Thus, based on the results of this study, it can be found that to estimate the continuous pollutant load properly the regression equations need to be determined with proper coefficients based on various flow conditions in watersheds. Furthermore, the machine-learning method can be useful to estimate the coefficients of regression equations in the LOADEST model.
Abstract
This study is to determine the coefficients of regression equations and to select the optimal regression equation in the LOADEST model after classifying the whole study period into 5 flow conditions for 16 watersheds located in the Nakdonggang waterbody. The optimized coefficients of regression equations were derived using the gradient descent method as a learning method in Tensorflow which is the engine of machine-learning method. In South Korea, the variability of streamflow is relatively high, and rainfall is concentrated in summer that can significantly affect the characteristic analysis of pollutant loads. Thus, unlike the previous application of the LOADEST model (adjusting whole study period), the study period was classified into 5 flow conditions to estimate the optimized coefficients and regression equations in the LOADEST model. As shown in the results, the equation #9 which has 7 coefficients related to flow and seasonal characteristics was selected for each flow condition in the study watersheds. When compared the simulated load (SS) to observed load, the simulation showed a similar pattern to the observation for the high flow condition due to the flow parameters related to precipitation directly. On the other hand, although the simulated load showed a similar pattern to observation in several watersheds, most of study watersheds showed large differences for the low flow conditions. This is because the pollutant load during low flow conditions might be significantly affected by baseflow or point-source pollutant load. Thus, based on the results of this study, it can be found that to estimate the continuous pollutant load properly the regression equations need to be determined with proper coefficients based on various flow conditions in watersheds. Furthermore, the machine-learning method can be useful to estimate the coefficients of regression equations in the LOADEST model.
참고문헌 (17)
- Arnold, J. G., "Large area hydrologic modeling and assessment – Part 1:Model development", Journal of the American Water Resources Association, 34(1), pp.73~89 (1998)
- Dean, J., "Large scale distributed deep networks", Proceedings of NIPS, pp.1232~1240 (2012)
- GWLF, generalized watershed loading functions, version 2.0, user’s manual, "Haith, D. A.", Dept. of Agricultural & Biological Engineering, Cornell University, ~ (1992)
- Jha, B., "Rating Curve Estimation of Surface Water Quality Data Using LOADEST", Journal of Environmental Protection, 4, pp.849~856 (2013)
- Kang, H. W., "Enhancement of SWAT Auto-calibration using K-means Clustering Algorithm", 2010 Autumn Conference of the Korean Society on Water Quality &Korean Society of Water and Wastewater, pp.197~198 (2010)
- 김상단, "유역모형 구축을 위한 8일간격 유량측정자료의 일유량 확장 가능성", 한국물환경학회지, 23(1), pp.64~71 (2007), 한국물환경학회
- 이재운, "낙동강수계 권역별 비점오염원 오염도 평가", 환경영향평가, 23(5), pp.393~405 (2014), 한국환경영향평가학회[DOI]
- Marcin Andrychowicz, "Learning to learn by gradient descent", 30th Conference on Neural Information Processing Systems (NIPS 2016) (2016)
- Ministry of Environment, "Total Maximum Daily Loads Handbook", pp.1~69 (2004), Ministry of Environment, Ministry of Environment (ME)
- The Study on the Optimum Assessment Methods for Achievement of Target Water Quality and Estimation of Allocation Loads Using a Dynamic Model, "National Institute of Environment Research", National Institute of Environment Research, 1~31, pp.NIER-RP2013-274 (2013)
- Oh, J., "The role of retrospective weather forecasts in developing daily forecasts of nutrient loadings over the Southeast US", Hydrology and Earth System Sciences Discussions, 10, pp.15625~15657 (2013)
- Park, Y. S., "Use of pollutant load regression models with various sampling frequencies for annual load estimation", Water, 6, pp.1685~1697 (2014)
- 박윤식, "한강수계에서의 부유사 예측을 위한 LOADEST 모형의 회귀식의 평가", 한국농공학회논문집, 57(2), pp.37~45 (2015), 한국농공학회
- Shin, M. H., "Estimation of LOADEST Model application for NPS pollutants from agricultural watershed", the 2008 KSAE Annual Conference (2008)
- Better Assessment Science Integrating Point and Nonpoint Sources (BASINS) v. 3.0 User’s Manual, "USEPA", U. S. Environment Protection Agency, ~ (2001)
- Using APEX to identify alternative practices for animal waste management, "Ramanarayanan, T. S.", 97~2209, pp.Paper No. 97-2209 (1997)
- Runkel, R. L., "U.S. Geological Survey Techniques and Methods Book 4", pp.69~ (2004)