Journal of the Korean Association of Geographic Information Studies (한국지리정보학회지)

The Korean Association of Geographic Information Studies (한국지리정보학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of Chlorophyll-a Concentration in Nakdong River Using UAV Multispectral Imagery and Machine Learning

UAV 다중분광 영상과 머신러닝을 활용한 낙동강 수계의 Chlorophyll-a 농도 추정

  • 노건우 (국립창원대학교, 환경공학과 ) ;
  • 박건웅 (주식회사 엔비랩스) ;
  • 송봉근 (주식회사 엔비랩스) ;
  • 김태경 (국립창원대학교, 환경공학과) ;
  • 김하늘 (국립창원대학교, 환경공학과) ;
  • 정다은 (주식회사 엔비랩스) ;
  • 박경훈 (국립창원대학교, 스마트그린공학부)
  • Received : 2026.01.26
  • Accepted : 2026.03.06
  • Published : 2026.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

High-resolution remote sensing techniques are increasingly required to overcome the limitations of conventional point-based water quality monitoring in managing recurring algal blooms. This study aims to develop a Chl-a estimation model using UAV-based multispectral imagery and machine learning algorithms for the Nakdong River basin, and to identify the optimal combination of spectral indices. To achieve this, a total of 93 matched datasets of UAV imagery and in-situ measurements were collected from 19 sites. Four spectral indices reflecting the optical characteristics of Chl-a were derived. The results indicated that the correlation between spectral indices and Chl-a varied depending on the water body type. In optically complex inland waters characterized by high turbidity, the RF model demonstrated significantly superior predictive performance compared to simple linear regression. Specifically, the combination of the 3BR and the NDCI with the RF model yielded the highest accuracy, achieving a coefficient of determination (R2) of 0.88 and an RMSE of 9.97mg/m3. Conversely, the inclusion of the NDVI and the EVI did not improve performance due to increased model complexity. These findings suggest that combining UAV multispectral imagery with optimized machine learning models is an effective tool for the precise monitoring of localized algal blooms.

매년 반복되는 녹조 현상에 대응하기 위해 기존의 지점 단위 수질 모니터링 한계를 극복할 수 있는 고해상도 원격탐사 기법의 필요성이 대두되고 있다. 본 연구는 낙동강 수계를 대상으로 UAV 기반 다중분광 영상과 머신러닝 기법을 활용하여 Chl-a 농도 추정 모델을 개발하고 최적의 분광지수 조합을 규명하는 것을 목적으로 한다. 이를 위해 19개 지점에서 총 93개의 동시 관측 데이터를 구축하였으며, Chl-a의 광학적 특성을 반영한 4종의 분광지수를 산출하였다. 분석 결과, 수체 유형에 따라 분광지수와 Chl-a 간의 상관성이 상이하게 나타났으며, 탁도가 높고 광학적으로 복잡한 내륙 수체 환경에서는 단순 선형 회귀보다 RF 모델이 월등히 우수한 예측 성능을 보였다. 특히 입력 변수 조합 분석 결과 3BR과 NDCI를 결합하여 RF 모델에 적용했을 때 결정계수(R2) 0.88, RMSE 9.97mg/m3로 가장 높은 정확도를 나타냈다. 반면, NDVI, EVI의 추가는 모델의 복잡도를 증가시켜 성능 향상에 기여하지 못했다. 본 연구 결과는 UAV 다중분광 영상과 최적화된 머신러닝 모델의 결합이 국지적 녹조 분포를 정밀하게 모니터링하는 데 효과적인 도구임을 시사한다.

Keywords

Acknowledgement

본 과제(결과물)는 교육부와 경상남도의 재원으로 지원을 받아 수행된 경상남도 지역혁신중심 대학지원체계(RISE)의 지원(2025-RISE-16-002)과 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원-대학ICT연구센터(ITRC)의 지원을 받아 수행된 연구임.(IITP-2026-RS-2024-00438409)

References

  1. Aranda, Y.N., P. Bhatt, N. Ates, B.A. Engel and H. Simsek. 2023. Cyanophage-cyanobacterial interactions for sustainable aquatic environment. Environmental Research 229, 115728.
  2. Choe, E., K.M. Jung, J.S. Yoon, J.H. Jang, M.J. Kim and H.J. Lee. 2021. Application of spectral indices to drone-based multispectral remote sensing for algal bloom monitoring in the river. Korean Journal of Remote Sensing 37(3):419-430 (최은영, 정경미, 윤종수, 장정희, 김미정, 이호중. 2021. 하천 녹조 모니터링을 위한 드론 다중분광영상의 분광지수 적용성 평가. 대한원격탐사학회지 37(3):419-430). https://doi.org/10.7780/KJRS.2021.37.3.5
  3. Dekker, A.G. 1993. Detection of optical water quality parameters for eutrophic waters by high resolution remote sensing.
  4. Fu, B., Li, S., Z. Lao, B. Yuan, Y. Liang, W. He and H. He. 2023. Multi-sensor and multi-platform retrieval of water chlorophyll a concentration in karst wetlands using transfer learning frameworks with ASD, UAV, and Planet CubeSate reflectance data. Science of the Total Environment 901:165963.
  5. Gilerson, A.A., A.A. Gitelson, J. Zhou, D. Gurlin, W. Moses, I. Ioannou and S.A. Ahmed. 2010. Algorithms for remote estimation of chlorophyll-a in coastal and inland waters using red and near infrared bands. Optics Express 18(23):24109-24125. https://doi.org/10.1364/OE.18.024109
  6. 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 13(17):3367-3373. https://doi.org/10.1080/01431169208904125
  7. Gitelson, A.A., G. Dall'Olmo, W. Moses, D.C. Rundquist, T. Barrow, T.R. Fisher and J. Holz. 2008. A simple semi-analytical model for remote estimation of chlorophyll-a in turbid waters: Validation. Remote Sensing of Environment 112(9): 3582-3593. https://doi.org/10.1016/j.rse.2008.04.015
  8. Gurlin, D., A.A. Gitelson and W.J. Moses. 2011. Remote estimation of chl-a concentration in turbid productive waters-Return to a simple two-band NIR-red model? Remote Sensing of Environment 115(12):3479-3490. https://doi.org/10.1016/j.rse.2011.08.011
  9. Kim, H.M., E.Y. Choe and S.W. Jang. 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 25(1):101-119 (김흥민, 최은영, 장선웅. 2022. 무인항공기 기반 다중분광영상을 이용한 낙동강 Chlorophyll-a 및 녹조발생지수 분석. 한국지리정보학회지 25(1): 101-119). https://doi.org/10.11108/KAGIS.2022.25.1.101
  10. Huete, A., K. Didan, T. Miura, E.P. Rodriguez, X. Gao and L.G. Ferreira. 2002. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote sensing of environment 83(1-2):195-213. https://doi.org/10.1016/S0034-4257(02)00096-2
  11. Johan, F.B., M.Z.B.M. Jafri, L.H. San, W.M.W. Omar and T.C. Ho. 2018. Chlorophyll a concentration of fresh water phytoplankton analysed by algorithmic based spectroscopy.Paper presented at the Journal of Physics: Conference Series.
  12. Jw, R. 1973. Monitoring vegetation systems in the great plains with ERTS. In Third NASA Earth Resources Technology Satellite Symposium 1:309-317.
  13. Kim, S.H., B.H. Moon, B.G. Song and K.H. Park. 2019. An analysis on the usability of unmanned aerial vehicle image to identify water quality characteristics in agricultural streams. Journal of the Korean Association of Geographic Information Studies 22(3):10-20 (김성현, 문병현, 송봉근, 박경훈. 2019. 농업지역 소하천의 수질 특성 파악을 위한 UAV 영상 활용 가능성 분석. 한국지리정보학회지 22(3): 10-20). https://doi.org/10.11108/KAGIS.2019.22.3.010
  14. Kuhn, C., A. de Matos Valerio, N. Ward, L. Loken, H.O. Sawakuchi, M. Kampel and R. Striegl. 2019. Performance of Landsat-8 and Sentinel-2 surface reflectance products for river remote sensing retrievals of chlorophyll-a and turbidity. Remote Sensing of Environment 224: 104-118. https://doi.org/10.1016/j.rse.2019.01.023
  15. Lee, J., D.H. Kwon, H. Jeong, G. Nam, E. Hwang, J.H. Kim and H.G. Kim. 2025. Improving chlorophyll-a stimation using Sentinel-2 data: a comparative analysis of augmented datasets. GIScience & Remote Sensing 62(1):2496551. https://doi.org/10.1080/15481603.2025.2496551
  16. Lee, K.H. and S.H. Lee. 2012. Monitoring of floating green algae using ocean color satellite remote sensing. Journal of the Korean Association of Geographic Information Studies 15(3):137-147 (이권호, 이소현. 2012. 해색위성 원격탐사를 이용한 부유성 녹조 모니터링. 한국지리정보학회지 15(3):137-147). https://doi.org/10.11108/KAGIS.2012.15.3.137
  17. Liu, W. and R. Qiu. 2007. Water eutrophication in China and the combating strategies. Journal of Chemical Technology & Biotechnology: International Research in Process, Environmental & Clean Technology 82(9):781-786. https://doi.org/10.1002/jctb.v82:9
  18. Lu, Q., W. Si, L. Wei, Z. Li, Z. Xia, S. Ye and Y. Xia. 2021. Retrieval of water quality from UAV-borne hyperspectral imagery: A comparative study of machine learning algorithms. Remote Sensing 13(19):3928. https://doi.org/10.3390/rs13193928
  19. Mishra, S. and D.R. Mishra. 2012. Normalized difference chlorophyll index: A novel model for remote estimation of chlorophyll-a concentration in turbid productive waters. Remote Sensing of Environment 117:394-406. https://doi.org/10.1016/j.rse.2011.10.016
  20. Modiegi, M., I.T. Rampedi and S.G. Tesfamichael. 2020. Comparison of multi-source satellite data for quantifying water quality parameters in a mining environment. Journal of Hydrology 591:25322. https://doi.org/10.1016/j.jhydrol.2020.125322
  21. Paerl, H.W. and M.A. Barnard. 2020. Mitigating the global expansion of harmful cyanobacterial blooms: Moving targets in a human-and climatically-altered world. Harmful algae 96:101845. https://doi.org/10.1016/j.hal.2020.101845
  22. Pahlevan, N., S.K. Chittimalli, S.V. Balasubramanian and V. Vellucci. 2019. Sentinel-2/Landsat-8 product consistency and implications for monitoring aquatic systems. Remote sensing of Environment 220:19-29. https://doi.org/10.1016/j.rse.2018.10.027
  23. Pang, Z., Z. Zhou, J.E. Fu, W. Jiang, X. Qin and M. Sun. 2025. Deep learning-based remote sensing retrieval of inland water quality: A review. Journal of Hydrology: Regional Studies 61:102759. https://doi.org/10.1016/j.ejrh.2025.102759
  24. Tian, S., H. Guo, W. Xu, X. Zhu, B. Wang, Q. Zeng and J.J. Huang. 2023. Remote sensing retrieval of inland water quality parameters using Sentinel-2 and multiple machine learning algorithms. Environmental Science and Pollution Research 30(7):18617-18630. https://doi.org/10.1007/s11356-022-23431-9
  25. Wu, D., J. Jiang, F. Wang, Y. Luo, X. Lei, C. Lai and M. Xu. 2023. Retrieving eutrophic water in highly urbanized area coupling UAV multispectral data and machine learning algorithms. Water 15(2):354. https://doi.org/10.3390/w15020354
  26. Yang, H., J. Kong, H. Hu, Y. Du, M. Gao and F. Chen. 2022. A review of remote sensing for water quality retrieval: Progress and challenges. Remote Sensing 14(8):1770. https://doi.org/10.3390/rs14081770
  27. Yang, W., B. Fu, S. Li, Z. Lao, T. Deng, W. He and Z. Chen. 2023. Monitoring multi-water quality of internationally important karst wetland through deep learning, multi-sensor and multi-platform remote sensing images: A case study of Guilin, China. Ecological Indicators 154:110755. https://doi.org/10.1016/j.ecolind.2023.110755
  28. Zhao, X., Y. Li, Y. Chen and X. Qiao. 2022. A method of cyanobacterial concentrations prediction using multispectral images. Sustainability 14(19):12784. https://doi.org/10.3390/su141912784