한국수자원학회논문집 (Journal of Korea Water Resources Association)

  • 제56권2호
  • /
  • Pages.91-101
  • /
  • 2023
  • /
  • 2799-8746(pISSN)
  • /
  • 2799-8754(eISSN)
한국수자원학회 (Korea Water Resources Association)
권호 표지
DOI QR코드

DOI QR Code

남양호와 백제보의 Chlorophyll-a 산정을 위한 초분광 영상기반 수체분광특성 비교 분석

Comparative analysis of water surface spectral characteristics based on hyperspectral images for chlorophyll-a estimation in Namyang estuarine reservoir and Baekje weir

  • 장원진 (건국대학교 일반대학원 사회환경플랜트공학과) ;
  • 김진욱 (건국대학교 일반대학원 사회환경플랜트공학과) ;
  • 김진휘 (건국대학교 공과대학 사회환경공학부) ;
  • 남귀숙 (한국농어촌공사 농어촌연구원) ;
  • 강의태 (한국농어촌공사 농어촌연구원) ;
  • 박용은 (건국대학교 공과대학 사회환경공학부) ;
  • 김성준 (건국대학교 공과대학 사회환경공학부)
  • Jang, Wonjin (Department of Civil, Environmental and Plant Engineering, Graduate School, Konkuk University) ;
  • Kim, Jinuk (Department of Civil, Environmental and Plant Engineering, Graduate School, Konkuk University) ;
  • Kim, Jinhwi (School of Civil and Environmental Engineering, College of Engineering, Konkuk University) ;
  • Nam, Guisook (Korea Rural Community Corporation, Rural Research Institute) ;
  • Kang, Euetae (Korea Rural Community Corporation, Rural Research Institute) ;
  • Park, Yongeun (School of Civil and Environmental Engineering, College of Engineering, Konkuk University) ;
  • Kim, Seongjoon (School of Civil and Environmental Engineering, College of Engineering, Konkuk University)
  • 투고 : 2022.10.21
  • 심사 : 2022.12.12
  • 발행 : 2023.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구에서는 담수를 대상으로 녹조의 발생을 모니터링하기 위해 내륙에 위치한 백제보와 남양호의 초분광영상을 이용하여 클로로필-a (Chl-a)의 농도를 추정하였다. 각 유역의 초분광이미지는 2016년부터 2017년까지 백재보에서 항공기로, 2020년부터 2021년까지 남양호에서 드론으로 촬영하였다. 이후, 순열 특성 중요도를 이용하여 Chl-a 농도와 관련성이 높은 30개의 반사 대역을 선택하였으며, 백제보는 400-530, 620-680, 710-730, 760-790 nm, 남양호는 400-430, 655-680, 740-800 nm 구간의 반사도가 선택되었다. 선택된 반사율을 입력자료로 하는 인공 신경망 기반의 Chl-a 산정 모델을 개발하였으며 모형의 성능은 결정계수(R2), 평균제곱근오차(RMSE), 평균절대오차(MAE)로 평가하였다. 유역별 산정모델의 성능은 각각 R2: 0.63, 0.82, RMSE: 9.67, 6.99, MAE: 11.25, 8.48로 나타났다. 본 연구에서 개발된 Chl-a 모델은 향후 담수호 녹조의 최적 관리를 위한 기초 도구로 활용될 수 있을 것으로 기대된다.

In this study, we estimated the concentration of chlorophyll-a (Chl-a) using hyperspectral water surface reflectance in an inland weir (Baekjae weir) and estuarine reservoir (Namyang Reservoir) for monitoring the occurrence of algae in freshwater in South Korea. The hyperspectral reflectance was measured by aircraft in Baekjae Weir (BJW) from 2016 to 2017, and a drone in Namyang Reservoir (NYR) from 2020 to 2021. The 30 reflectance bands (BJW: 400-530, 620-680, 710-730, 760-790 nm, NYR: 400-430, 655-680, 740-800 nm) that were highly related to Chl-a concentration were selected using permutation importance. Artificial neural network based Chl-a estimation model was developed using the selected reflectance in both water bodies. And the performance of the model was evaluated with the coefficient of determination (R2), the root mean square error (RMSE), and the mean absolute error (MAE). The performance evaluation results of the Chl-a estimation model for each watershed was R2: 0.63, 0.82, RMSE: 9.67, 6.99, and MAE: 11.25, 8.48, respectively. The developed Chl-a model of this study may be used as foundation tool for the optimal management of freshwater algal blooms in the future.

키워드

과제정보

본 결과물은 농림축산식품부의 재원으로 농림식품기술기획평가원의 농업기반및재해대응기술개발사업의 지원을 받아 연구되었음(320049-5). 본 결과물은 환경부의 재원으로 한국환경산업기술원의 수생태계 건강성 확보 기술개발사업의 지원을 받아 연구되었습니다(2020003050001).

참고문헌

  1. Ahn, C.Y., Lee, J.Y., and Oh, H.M. (2013). "Control of microalgal growth and competition by N: P ratio manipulation." Korean Society of Environmental Biology, Vol. 31, No. 2, pp. 61-68. https://doi.org/10.11626/KJEB.2013.31.2.061
  2. Bennett, A., and Bogorad, L. (1973). "Complementary chromatic adaptation in a filamentous blue-green alga." The Journal of Cell Biology, Vol. 58, No. 2, pp. 419-435. https://doi.org/10.1083/jcb.58.2.419
  3. Castro, C.C., Gomez, J.A.D., Martin, J.D., Sanchez, B.A.H., Arango, J.L.C., Tuya, F.A.C., and Diaz-Varela, R. (2020). "An UAV and satellite multispectral data approach to monitor water quality in small reservoirs." Remote Sensing, Vol. 12, No. 9, 1514.
  4. Dall'Olmo, G., and Gitelson, A.A. (2005). "Effect of bio-optical parameter variability on the remote estimation of chlorophyll-a concentration in turbid productive waters: experimental results." Applied Optics, Vol. 44, No. 3, pp. 412-422. https://doi.org/10.1364/AO.44.000412
  5. Dekker, A.G. (1993). Detection of optical water quality parameters for eutrophic waters by high resolution remote sensing. Institute for Environmental Studies, Amsterdam, The Netherlands.
  6. Dev, P.J., Sukenik, A,. Mishra, D.R., and Ostrovsky, L. (2022). "Cyanobacterial pigment concentrations in inland waters: Novel semi-analytical algorithms for multi- and hyperspectral remote sensing data." Science of The Total Environment, Vol. 805, 150423.
  7. Fisher, A., Rudin, C., and Dominici, F. (2019). "All models are wrong, but many are useful: Learning a variable's importance by studying an entire class of prediction models simultaneously." Journal of Machine Learning Research, Vol. 20, No. 177, pp. 1-81.
  8. Gitelson, A. (1992). "The peak near 700 nm on radiance spectra of Algae and water - relationships of its magnitude and position with chlorophyll concentration." International Journal of Remote Sensing, Vol. 13, No. 17, pp. 3367-3373. https://doi.org/10.1080/01431169208904125
  9. Gordon, H.R., and Morel, A.Y. (1983). Remote assessment of ocean color for interpretation of satellite visible imagery: A Review. Springer-Verlag, NY, U.S.
  10. Guyon, I, and Elisseeff, A. (2003). "An introduction to variable and feature selection." Journal of Machine Learning Research, Vol. 3, pp. 1157-1182.
  11. Han, S.R., Cho, K.C., Yoon, J.H., Lee, J.J., Yoo, S.A., Choi, I.C., Joo, H.J., Cheon, S.U., and Lim, B.J. (2016). "Phytoplankton community structure of midstream of Geum River on 2014 and 2015." Korean Journal of Ecology and Environment, Vol. 49, No. 4, pp. 375-384. https://doi.org/10.11614/KSL.2016.49.4.375
  12. Hunter, P.D., Tyler, A.N., Carvalho, L., Codd, G.A., and Maberly, S.C. (2010). "Hyperspectral remote sensing of cyanobacterial pigments as indicators for cell populations and toxins in Eutrophic lakes." Remote Sensing of Environment, Vol. 114, No. 11, pp. 2705-2718. https://doi.org/10.1016/j.rse.2010.06.006
  13. Jang, W.J., Park, Y.E., Pyo, J.C., Park, S.H., Kim, J.U., Kim, J.H., Cho, K.H., Shin, J.K, and Kim, S.J. (2022). "Optimal band selection for airborne hyperspectral imagery to retrieve a wide range of cyanobacterial pigment concentration using a data-driven approach." Remote Sensing, Vol. 14, No. 7, 1754.
  14. Kallio, K., Kutser, T., Hannonen, T., Koponen, S., Pulliainen, J., Vepsalainen, J., and Pyhalahti, T. (2001). "Retrieval of water quality from airborne imaging spectrometry of various lake types in different seasons." Science of The Total Environment, Vol. 268, pp. 59-77. https://doi.org/10.1016/S0048-9697(00)00685-9
  15. Keller, S., Maier, P.M., Riese, F.M., Norra, S., Holbach, A., Borsig, N., Wilhelms, A., Moldaenke, C., Zaake, A., and Hinz, S. (2018). "Hyperspectral data and machine learning for estimating CDOM, chlorophyll a, diatoms, green algae and turbidity." International Journal of Environmental Research and Public Health, Vol. 15, No. 9, 1881.
  16. Kim, H.M., Choe, E.Y., and Jang, S.W. (2022). "Analysis of chlorophyll-a and algal bloom indices using unmanned aerial vehicle based multispectral images on Nakdong River." Journal of the Korean Association of Geographic Information Studies, Vol. 25, No. 1, pp. 101-119.
  17. Kim, H.M., Jang, S.W., and Yoon, H.J. (2017). "Utilization of Unmanned Aerial Vehicle (UAV) image for detection of algal bloom in Nakdong River." Journal of The Korea Institute of Electronic Communication Sciences, Vol. 12, No. 3, pp. 457-464.
  18. Kim, J.U., Jang, W.J., Shin, J.K., Kang, E.T., Kim, J.H., Park, Y.E., and Kim, S.J. (2021). "Estimating TOC concentrations using an optically-active water quality factors in Estuarine reservoirs." Journal of Korean Society on Water Environment, Vol. 37, No. 6, pp. 531-538. https://doi.org/10.15681/KSWE.2021.37.6.531
  19. Lee, M.J., Seo, J.Y., and Baek, S.H. (2021). "Water quality characteristics and spatial distribution of phytoplankton during dry and rainy seasons in Bunam Lake and Cheonsu Bay, Korea." Korean Society of Environmental Biology, Vol. 39, No. 2, pp. 184-194. https://doi.org/10.11626/KJEB.2021.39.2.184
  20. Li, L., Sengpiel, R.E., Pascual, D.L., Tedesco, L.P., Wilson, J.S., and Soyeux, A. (2010). "Using hyperspectral remote sensing to estimate chlorophyll-a and phycocyanin in a mesotrophic reservoir." International Journal of Remote Sensing, Vol. 31, No. 15, pp. 4147-4162. https://doi.org/10.1080/01431161003789549
  21. Liu, H., Li, Q., Shi, T., Hu, S., Wu, G., and Zhou, Q. (2017). "Application of sentinel 2 MSI images to retrieve suspended particulate matter concentrations in Poyang Lake." Remote Sensing, Vol. 9, 761.
  22. Mishra, S., Mishra, D.R., and Schluchter, W.M. (2009). "A novel algorithm for predicting phycocyanin concentrations in cyanobacteria: A proximal hyperspectral remote sensing approach." Remote Sensing, Vol. 1, pp. 758-775. https://doi.org/10.3390/rs1040758
  23. Moses, W.J., Gitelson, A.A., Perk, R.L., Gurlin, D., Rundquist, D.C., Leavitt, B.C., Barrow, T.M., and Brakhage, P. (2012). "Estimation of chlorophyll-a concentration in turbid productive waters using airborne hyperspectral data." Water Research, Vol. 46, No. 4, pp. 993-1004. https://doi.org/10.1016/j.watres.2011.11.068
  24. O'Reilly, J.E., Maritorena, S., Mitchell, B.G., Siegel, D.A., Carder, K.L., Garver, S.A., Kahru, M., and McClain, C. (1998). "Ocean color chlorophyll algorithms for Sea WiFS." Journal of Geophysical Research: Oceans, Vol. 103, No. C11, pp. 24937-24953. https://doi.org/10.1029/98JC02160
  25. Park, J.S., and Park, S.G. (2020). "Reasonable river water permit and management plan in estuary reservoir." Water for Future, Vol. 53, No. 8, pp. 17-23.
  26. Pyo, J.C., Duan, H., Ligaray, M., Kim, M., Baek, S., Kwon, W.S., Lee, H., Kang, T., Kim, K., and Cha, Y.K. (2020). "An integrative remote sensing application of stacked autoencoder for atmospheric correction and cyanobacteria estimation using hyperspectral imagery." Remote Sensing, Vol. 12, No. 7, 1073.
  27. Pyo, J.C., Pachepsky, Y., Baek, S.S., Kwon, Y.S., Kim, M.J., Lee, H., Park, S., Cha, Y.K., Ha, R., and Nam, G. (2017). "Optimizing semi-analytical algorithms for estimating chlorophyll-a and phycocyanin concentrations in inland waters in Korea." Remote Sensing, Vol. 9, No. 6, 542.
  28. Shi, K., Li, Y., Li, L., Lu, H., Song, K., Liu, Z., Xu, Y., and Li, Z. (2013). "Remote chlorophyll-a estimates for inland waters based on a cluster-based classification." Science of The Total Environment, Vol. 444, pp. 1-15. https://doi.org/10.1016/j.scitotenv.2012.11.058
  29. Sindelar, R., and Babuska, R. (2004). "Input selection for nonlinear regression models." IEEE Transactions on Fuzzy Systems, Vol. 12, No. 5, pp. 688-696. https://doi.org/10.1109/TFUZZ.2004.834810
  30. Su, T.C., and Chou, H.T. (2015). "Application of multispectral sensors carried on unmanned aerial vehicle (UAV) to trophic state mapping of small reservoirs: A case study of Tain-Pu reservoir in Kinmen. Taiwan." Remote Sensing, Vol. 7, No. 8, pp. 10078-10097. https://doi.org/10.3390/rs70810078
  31. Sun, D., Li, Y., and Wang, Q. (2009). "A unified model for remotely estimating chlorophyll a in Lake Taihu, China, based on SVM and in situ hyperspectral data." IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, No. 8, pp. 2957-2965. https://doi.org/10.1109/TGRS.2009.2014688
  32. Sun, W., and Du, Q. (2019). "Hyperspectral band selection: A review." IEEE Geoscience and Remote Sensing Magazine, Vol. 7, No, 2, pp. 118-139. https://doi.org/10.1109/mgrs.2019.2911100