Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of Water Quality Index for Coastal Areas in Korea Using GOCI Satellite Data Based on Machine Learning Approaches

GOCI 위성영상과 기계학습을 이용한 한반도 연안 수질평가지수 추정

  • Jang, Eunna (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology) ;
  • Im, Jungho (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology) ;
  • Ha, Sunghyun (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology) ;
  • Lee, Sanggyun (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology) ;
  • Park, Young-Gyu (Korea Institute of Ocean Science and Technology)
  • 장은나 (울산과학기술원 도시환경공학부) ;
  • 임정호 (울산과학기술원 도시환경공학부) ;
  • 하성현 (울산과학기술원 도시환경공학부) ;
  • 이상균 (울산과학기술원 도시환경공학부) ;
  • 박영규 (해양과학기술원 해양순환.기후연구센터)
  • Received : 2016.05.11
  • Accepted : 2016.05.21
  • Published : 2016.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In Korea, most industrial parks and major cities are located in coastal areas, which results in serious environmental problems in both coastal land and ocean. In order to effectively manage such problems especially in coastal ocean, water quality should be monitored. As there are many factors that influence water quality, the Korean Government proposed an integrated Water Quality Index (WQI) based on in situmeasurements of ocean parameters(bottom dissolved oxygen, chlorophyll-a concentration, secchi disk depth, dissolved inorganic nitrogen, and dissolved inorganic phosphorus) by ocean division identified based on their ecological characteristics. Field-measured WQI, however, does not provide spatial continuity over vast areas. Satellite remote sensing can be an alternative for identifying WQI for surface water. In this study, two schemes were examined to estimate coastal WQI around Korea peninsula using in situ measurements data and Geostationary Ocean Color Imager (GOCI) satellite imagery from 2011 to 2013 based on machine learning approaches. Scheme 1 calculates WQI using estimated water quality-related factors using GOCI reflectance data, and scheme 2 estimates WQI using GOCI band reflectance data and basic products(chlorophyll-a, suspended sediment, colored dissolved organic matter). Three machine learning approaches including Random Forest (RF), Support Vector Regression (SVR), and a modified regression tree(Cubist) were used. Results show that estimation of secchi disk depth produced the highest accuracy among the ocean parameters, and RF performed best regardless of water quality-related factors. However, the accuracy of WQI from scheme 1 was lower than that from scheme 2 due to the estimation errors inherent from water quality-related factors and the uncertainty of bottom dissolved oxygen. In overall, scheme 2 appears more appropriate for estimating WQI for surface water in coastal areas and chlorophyll-a concentration was identified the most contributing factor to the estimation of WQI.

우리나라는 대규모 산업단지와 대도시들이 연안에 집중되면서 연안의 오염이 날로 심각해지고 있다. 이러한 연안 오염을 모니터링하기 위해서 위성 영상을 이용한 연안 수질평가지수 모니터링 연구가 수행될 필요가 있다. 수질평가지수란 저층 산소포화도, 엽록소 농도, 투명도, 용존무기질소 및 용존무기인 농도를 수질평가 항목으로 구성하여 해양환경관리법에 따른 해양환경기준을 통해 해역별로 기준을 설정하여 산출하는 지수이다. 이 연구는 한반도 주변의 연안지역을 대상으로 2011년부터 2013년까지의 현장관측 자료 및 Geostationary Ocean Color Imager (GOCI) 위성 영상을 이용하여 연안 표층 해수에 대한 기계학습 기반의 두 가지 수질평가지수 추정 기법을 개발하였다. 첫 번째 방법으로는 GOCI 반사도를 이용하여 추정된 수질평가 항목들로 수질평가지수를 계산하였고, 두 번째 방법은 GOCI 반사도 및 산출물(엽록소 농도, 총 부유물질, 용존유기물)을 이용하여 수질평가지수를 추정하였다. 기계학습으로는 Random Forest(RF), Support Vector Regression (SVR), Cubist를 사용하였다. 수질평가 항목 추정에서 투명도의 정확도가 가장 높게 나타났으며, 모든 수질평가 항목 추정에서 세 가지 기계학습 중 RF의 정확도가 가장 높았다. 하지만 추정된 수질평가 항목들로 계산한 수질평가지수는 추정된 수질평가 항목들의 오차와 저층 산소포화도의 불확실성으로 인해 정확도가 높지는 않았다. 반면 GOCI 반사도와 산출물을 이용하여 추정한 수질평가지수는 현장 관측 기반 수질평가지수와 비교했을 때 첫 번째 방법보다 정확도가 높게 나타났다. 또한 엽록소 농도가 수질평가지수 추정에 가장 중요한 변수로 나타났다.

Keywords

References

  1. Breiman, L., 2001. Random forests. Machine learning, 45(1): 5-32. https://doi.org/10.1023/A:1010933404324
  2. Harvey, E.T., S. Kratzer, and P. Philipson, 2015. Satellite-based water quality monitoring for improved spatial and temporal retrieval of chlorophyll-a in coastal waters. Remote Sensing of Environment, 158: 417-430. https://doi.org/10.1016/j.rse.2014.11.017
  3. Hunter, P.D., A.N. Tyler, L. Carvalho, G.A. Codd, and S.C. Maberly, 2010. Hyperspectral remote sensing of cyanobacterial pigments as indicators for cell populations and toxins in eutrophic lakes. Remote Sensing of Environment, 114(11): 2705-2718. https://doi.org/10.1016/j.rse.2010.06.006
  4. Johnson, R., P.G. Strutton, S.W. Wright, A. McMinn, and K.M. Meiners, 2013. Three improved satellite chlorophyll algorithms for the Southern Ocean. Journal of Geophysical Research: Oceans, 118(7): 3694-3703. https://doi.org/10.1002/jgrc.20270
  5. Kim, Y.H., J. Im, H.K. Ha, J.K. Choi, and S. Ha, 2014. Machine learning approaches to coastal water quality monitoring using GOCI satellite data. GIScience & Remote Sensing, 51(2): 158-174. https://doi.org/10.1080/15481603.2014.900983
  6. Kim, Y.J., H.C. Kim, Y.B. Son, M.O. Park, W.C. Shin, S.W. Kang, and T.K. Rho, 2012. Verification of CDOM algorithms based on ocean color remote sensing data in the East Sea. Korean Journal of Remote Sensing, 28(4): 421-434. (in Korean with English abstract) https://doi.org/10.7780/kjrs.2012.28.4.6
  7. Le, C., C. Hu, D. English, J. Cannizzaro, and C. Kovach, 2013. Climate-driven chlorophyll-a changes in a turbid estuary: Observations from satellites and implications for management. Remote Sensing of Environment, 130: 11-24. https://doi.org/10.1016/j.rse.2012.11.011
  8. 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 (in Korean with English abstract). https://doi.org/10.11108/kagis.2012.15.3.137
  9. Lumb, A., T.C. Sharma, and J.F. Bibeault, 2011. A review of genesis and evolution of water quality index(WQI) and some future directions. Water Quality, Exposure and Health, 3(1): 11-24. https://doi.org/10.1007/s12403-011-0040-0
  10. Min, J.E., J.H. Ryu, S. Lee, and S. Son, 2012. Monitoring of suspended sediment variation using Landsat and MODIS in the Saemangeum coastal area of Korea. Marine Pollution Bulletin, 64(2): 382-390. https://doi.org/10.1016/j.marpolbul.2011.10.025
  11. Ministry of Land, Transport and Maritime Affairs, 2011. The marine environmental standards on the Marine Environment Management Act, Ministry of Land, Transport and Maritime Affairs, South Korea.
  12. Mountrakis, G., J. Im, and C. Ogole, 2011. Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3): 247-259. https://doi.org/10.1016/j.isprsjprs.2010.11.001
  13. Novoa, S., G. Chust, J.M. Froidefond, C. Petus, J. Franco, E. Orive, S. Soane, and A. Borja, 2012. Water quality monitoring in Basque coastal areas using local chlorophyll-a algorithm and MERIS images. Journal of Applied Remote Sensing, 6(1): 063519-1. https://doi.org/10.1117/1.JRS.6.063519
  14. Park, S., and S.R. Lee, 2013. Marine disasters prediction system model using marine environment monitoring. The Journal of Korean Institute of Communications and Information Sciences, 38(3): 263-270.
  15. RuleQuest Research., 2012. RuleQuest Research data mining tools. from http://www.rulequest.com/.

Cited by

  1. Satellite Remote Sensing for Coastal Management: A Review of Successful Applications vol.60, pp.2, 2017, https://doi.org/10.1007/s00267-017-0880-x
  2. Comparison of Machine Learning Algorithms for Retrieval of Water Quality Indicators in Case-II Waters: A Case Study of Hong Kong vol.11, pp.6, 2016, https://doi.org/10.3390/rs11060617
  3. Selection of Input Factors and Comparison of Machine Learning Models for Prediction of Dissolved Oxygen in Gyeongan Stream vol.43, pp.3, 2016, https://doi.org/10.4491/ksee.2021.43.3.206