DOI QR코드

DOI QR Code

Assessment of climate change impact on aquatic ecology health indices in Han river basin using SWAT and random forest

SWAT 및 random forest를 이용한 기후변화에 따른 한강유역의 수생태계 건강성 지수 영향 평가

  • Woo, So Young (Department of Civil, Environmental and Plant Engineering, Konkuk University) ;
  • Jung, Chung Gil (Department of Civil, Environmental and Plant Engineering, Konkuk University) ;
  • Kim, Jin Uk (Department of Civil, Environmental and Plant Engineering, Konkuk University) ;
  • Kim, Seong Joon (Department of Civil, Environmental and Plant Engineering, Konkuk University)
  • 우소영 (건국대학교 공과대학 사회환경플랜트공학과) ;
  • 정충길 (건국대학교 공과대학 사회환경플랜트공학과) ;
  • 김진욱 (건국대학교 공과대학 사회환경플랜트공학과) ;
  • 김성준 (건국대학교 공과대학 사회환경플랜트공학과)
  • Received : 2018.08.02
  • Accepted : 2018.09.04
  • Published : 2018.10.31

Abstract

The purpose of this study is to evaluate the future climate change impact on stream aquatic ecology health of Han River watershed ($34,148km^2$) using SWAT (Soil and Water Assessment Tool) and random forest. The 8 years (2008~2015) spring (April to June) Aquatic ecology Health Indices (AHI) such as Trophic Diatom Index (TDI), Benthic Macroinvertebrate Index (BMI) and Fish Assessment Index (FAI) scored (0~100) and graded (A~E) by NIER (National Institute of Environmental Research) were used. The 8 years NIER indices with the water quality (T-N, $NH_4$, $NO_3$, T-P, $PO_4$) showed that the deviation of AHI score is large when the concentration of water quality is low, and AHI score had negative correlation when the concentration is high. By using random forest, one of the Machine Learning techniques for classification analysis, the classification results for the 3 indices grade showed that all of precision, recall, and f1-score were above 0.81. The future SWAT hydrology and water quality results under HadGEM3-RA RCP 4.5 and 8.5 scenarios of Korea Meteorological Administration (KMA) showed that the future nitrogen-related water quality in watershed average increased up to 43.2% by the baseflow increase effect and the phosphorus-related water quality decreased up to 18.9% by the surface runoff decrease effect. The future FAI and BMI showed a little better Index grade while the future TDI showed a little worse index grade. We can infer that the future TDI is more sensitive to nitrogen-related water quality and the future FAI and BMI are responded to phosphorus-related water quality.

본 연구에서는 SWAT 모형과 random forest를 이용하여 미래 기후변화에 따른 한강유역($34,148km^2$)의 수생태계 건강성을 평가하였다. 국립환경과학원에서 8년간(2008~2015년) 봄철(4~6월)에 모니터링한 부착돌말류 지수(TDI), 저서형 대형무척추동물지수(BMI), 어류평가지수(FAI)는 0~100점, A~E등급으로 평가되며, 이를 본 연구에서 사용하였다. 수생태 건강성에 영향을 미치는 변수로는 수질(T-N, $NH_4$, $NO_3$, T-P, $PO_4$)과 수온을 선정하였으며, 수질 오염도가 낮은 경우에는 수생태계 건강성 점수가 광범위하게 분포되지만 수질 오염도가 높은 경우 수생태계 건강성 점수가 낮아지는 역상관관계를 확인하였다. 기계학습의 분류 분석 기법 중 하나인 random forest 모델을 이용한 세 개의 수생태 건강성 지수 등급분류 결과 정밀도, 재현율, f1-score 모두 0.81 이상의 예측 정확도를 나타내었다. 기상청의 HadGEM3-RA RCP 4.5와 8.5 시나리오를 적용한 미래 SWAT 수문, 수질 결과 기저유출의 증가로 인해 질소 계열 수질 농도는 기준년도 대비 최대 43.2% 증가하였고, 지표유출 감소로 인해 인 계열수질 오염도는 최대 18.9% 감소하는 것으로 분석되었다. 미래 FAI, BMI의 등급은 개선되는 경향을 보이지만 TDI는 등급이 악화되는 것으로 나타났다. 이를 통해 TDI는 질소 계열 수질에 민감하고 FAI, BMI는 인 계열 수질에 더 민감하다고 판단하였다.

Keywords

References

  1. Ahn, S. R., and Kim, S. J. (2017). "Assessment of integrated watershed health based on the natural environment, hydrology, water quality, and aquatic ecology." Hydrology and Earth System Sciences, Vol. 21, No. 1, pp. 5583-5602. https://doi.org/10.5194/hess-21-5583-2017
  2. An, K., Lee, J., and Jang, H. (2005). "Ecological health assessments and water quality patterns in Youdeung stream." Korean Journal of Limnology, Vol. 38, No. 3, pp. 341.
  3. Arnold, J. G., Williams, J. R., Srinivasan, R., and King, K. W. (1996). SWAT manual. USDA, Agricultural Research Service and Blackland Research Center, Texas.
  4. Breiman, L. (2001). "Random forests." Machine Learning, Vol. 45, No. 1, pp. 5-32. https://doi.org/10.1023/A:1010933404324
  5. Goutte, C., and Gaussier, E. (2005). "A probabilistic interpretation of precision, recall and F-score, with implication for evaluation." Proceedings European Conference on Information Retrieval, Springer, Berlin, Heidelberg, pp. 345-359.
  6. Jung, S. W., Park, S. H., and Lee, J. H. (2008). "Environmental studies in the lower part of the Han river IIX. Assessment for water quality using epilithic diatom assemblage index to organic water pollution (DAIpo) in dry season." Korean Journal of Environmental Biology, Vol. 26, No. 3, pp. 233-239.
  7. Kim, S. (2015). "A corporate credit ratings model with random forests." Master thesis, Kookmin University, pp. 1-31.
  8. Kim, T. J., and Lee, O. M. (2009). "Assessment of water quality in the Sum-river and the Dal-stream using epilithic diatom-based indices." Journal of Korean Society on Water Quality, Vol. 25, No. 4, pp. 606-614.
  9. Langley, P., and Simon, H. A. (1995). "Applications of machine learning and rule induction." Communications of the ACM, Vol. 38, No. 11, pp. 54-64. https://doi.org/10.1145/219717.219768
  10. Lee, J. W., Jung, C. G., Kim, D. R., and Kim, S. J. (2018). "Assessment of future climate change impact on groundwater level behavior in Geum river basin using SWAT." Journal of Korea Water Resources Association, Vol. 51, No. 3, pp. 247-261. https://doi.org/10.3741/JKWRA.2018.51.3.247
  11. Meng, W., Zhang, N., Zhang, Y., and Zheng, B. (2009). "Integrated assessment of river health based on water quality, aquatic life and physical habitat." Journal of Environmental Sciences, Vol. 21, No. 8, pp. 1017-1027. https://doi.org/10.1016/S1001-0742(08)62377-3
  12. Ministry of Environment (2015). Nationwide Aquatic Ecological Monitoring Program, National Institute of Environmental Research, Incheon, South Korea.
  13. Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., and Veith, T. L. (2007). "Model evaluation guidelines for systematic quantification of accuracy in watershed simulations." Transactions of the ASABE, Vol. 50, No. 3, pp. 885-900. https://doi.org/10.13031/2013.23153
  14. Nash, J. E., and J. E. Sutcliffe (1970). "River flow forecasting though conceptual models: Part I, A discussion of principles." Journal of Hydrology, Vol. 10, No. 3, pp. 282-290. https://doi.org/10.1016/0022-1694(70)90255-6
  15. Neitsch, S. L., Arnold, J. G., Kiniry, J. R., and Williams, J. R. (2001). Soil and water assessment tool: theoretical documentation. U.S Agricultural Research Service, Temple, Texas, pp. 340-367.
  16. Pal, M. (2005). "Random forest classifier for remote sensing classification." International Journal of Remote Sensing, Vol. 26, No. 1, pp. 217-222. https://doi.org/10.1080/01431160412331269698
  17. Ponader, K. C., Charles, D. F., and Belton, T. J. (2007). "Diatombased TP and TN inference models and indices for monitoring nutrient enrichment of New Jersey streams." Ecological Indicators, Vol. 7, No. 1, pp. 79-93. https://doi.org/10.1016/j.ecolind.2005.10.003
  18. Santhi, C., Arnold, J. G., Williams, J. R., Dugas, W. A., Srinivasan, R., and Hauck, L. M. (2001). "Validation of the swat model on a large RWER basin with point and nonpoint sources." Journal of the American Water Resources Association, Vol. 37, No. 5, pp. 1169-1188. https://doi.org/10.1111/j.1752-1688.2001.tb03630.x
  19. Water Environment Information System (2018). http://water.nier.go.kr/waterData/easyDataBt.do?menuIdx=3_1_2.
  20. Won, D. H., Byun, M. S., Park, J. H., Lee, S. W., and Hwang, S. J. (2010). "Evaluation of the current status of aquatic ecosystem health in five major rivers in Korea." A Pulication of Korean Society of Civil Engineers, pp. 149-160.