The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Comparative Study on Machine Learning Models for Red Tide Detection

적조 탐지를 위한 기계학습 모델 비교 연구

  • 박미소 (부경대학교 공간정보시스템과학과) ;
  • 김나경 (부경대학교 공간정보시스템과학과) ;
  • 김보람 (부경대학교 공간정보시스템과학과) ;
  • 윤홍주 (부경대학교 공간정보시스템공학과)
  • Received : 2021.10.27
  • Accepted : 2021.12.17
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Red tide, defined as the major reproduction of harmful birds, has the characteristics of being generated and diffused in a wide area. This has limitations in detection only with the existing investigation method. Therefore, in this study, red tide was detected using a remote sensing technique. In addition, it was intended to increase the accuracy of detection by using optical characteristics, not just the concentration of chlorophyll. Red tide mainly occurs on the southern coast where sea signals are complex, and the main red tide control species on the southern coast is Cochlodinium polykirkoides. Therefore, it was intended to secure objectivity by reflecting features that could not be found depending on the researcher's observation and experience, not limited to visual judgment using machine learning techniques. In this study, support background machines and random forest were used among machine learning models, and as a result of calculating accuracy as performance evaluation indicators of the two models, the accuracy was 85.7% and 80.2%, respectively.

유해조류의 대번식으로 정의되는 적조는 광역적으로 발생·확산되는 특성을 가진다. 이는 기존의 조사 방법만으로는 탐지의 한계가 있다. 따라서 본 연구에서는 적조를 원격탐사 기법을 활용하여 탐지하였다. 또한 단순히 chlorophyll의 농도가 아닌 광특성을 이용하여 탐지의 정확도를 높이고자 하였다. 적조는 해수신호가 복잡한 남해안에서 주로 발생하며 남해안의 주 적조 종은 Cochlodinium polykirkoides이다. 따라서 기계학습 기법을 활용하여 시각적인 판단에 국한되지 않고 연구자의 관찰과 경험에 의존해 발견하지 못했던 특징을 반영하여 객관성을 확보하고자 하였다. 본 연구에서는 기계학습 모델 중에서 서포트백터머신과 랜덤포레스트를 사용하였고 두 모델의 성능 평가 지표로 정확도 등을 산출한 결과 각각 85.7% 80.2%의 정확도를 보였다.

Keywords

Acknowledgement

이 연구는 기상청 「효율적 해양기상정보 활용을 위한 민간 서비스 기술개발」(CD20210336)의 지원으로 수행되었습니다.

References

  1. J. Yang "The Outbreak of Red Tides in the Coastal Waters off Kohung, Chonnam, Korea: 1. Physical and Chemical Characteristics in 1997," The Sea J. of the Korean Society of Oceanography, vol. 5, no. 1, 2000, pp. 16~26.
  2. H. Kim, "Physico - Chemical Factors on the Growth of Cochlodinium polykrikoides and Nutrient Utilization," J. of the Korean Fisheries Society, vol. 34 no. 5 , 2001, pp.445~456.
  3. D. Park, "Countermeasure and Outbreak Mechanism of Cochlodinium polykrikoides red tide 1. Environmental characteristics on outbreak and disappearanceof C. polykrikoides bloom," The Sea J. of the Korean Society of Oceanography, vol. 6, no. 4 , 2001, pp. 259~264.
  4. C. Lee, "Abundance of Harmful Algae, Cochlodinium polykrikoides, Gyrodinium impudicum and Gymnodinium catenatum in the Coastal Area of South Sea of Korea and Their Effects of Temperature, Salinity, Irradiance and Nutrient on the Growth in Culture," J. of the Korean Fisheries Society, vol. 34 no. 5 , 2001, pp.536~544.
  5. C. Jeaong, "A study on the vertical movement of harmful red tide cochlodinium polykricoids day and night" The Korean Society of Fisheries and Aquatic Science, May, 2004, pp.180~182.
  6. J. Park, "Diurnal vertical migration of a harmful dinoflagellate, Cochlodinium polykrikoides (Dinophyceae), during a red tide in coastal waters of Namhae Island, Korea," Phycologia, vol. 40, no. 3 , 2001, pp. 292~297. https://doi.org/10.2216/i0031-8884-40-3-292.1
  7. K. Carder, "A remote-sensing reflectance model of a red-tide dinoflagellate off west Florida," Limnology and Oceanography, vol. 30, no. 2, 1985, pp. 286~298. https://doi.org/10.4319/lo.1985.30.2.0286
  8. Y, Kim, "Detection of Cochlodinium polykrikoides Red Tide Using MODIS Level 2 Data in Coastal Waters.," Journal of the Korean sosiety of civil engineers, vol. D, no. 27, 2007, pp. 535~540.
  9. J. Shin, "A Study on red tide surveillance system around the Korean coastal waters using GOCI." The Korean Society of Remote Sensing , vol. 33, no. 2, 2017, pp. 213~230.
  10. Y. Son, Y. Kang, and J. Ryu, "Monitoring Red Tide in South Sea of Korea(SSK) Using the Geostationary Ocean Color Imager(GOCI)," Korean J. of Remote Sensing, vol. 26, no. 5, 2012, pp. 531-548.
  11. H. Yoon, Marine Remote Sensing - The 4th Industrial Revolution and the Utilization of Marine Remote Sensing Big Data, WisdomPL 2018
  12. Y. Ahn, "Inherent Optical Properties of Red Tide Algal for Ocean Color Remote Sensing Application.," J. of the Korea Society for Marine Environmental Engineering, vol. 12, no. 1, 2009, pp. 47~54.
  13. S. Park "Analysis on optical property in the South Sea of Korea by using Satellite Image: Study of Case on red tide occurrence in August 2013," J. of the Korea Institute of Electronic Communication Sciences, vol. 11, no. 7, 2016, pp. 723~728. https://doi.org/10.13067/JKIECS.2016.11.7.723
  14. D. Hwang, "Pattern Analysis in East /Asian Coasts by using Sea Level Anomaly and Sea Surface Temperature Data," J. of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 3, 2021, pp. 525-532. https://doi.org/10.13067/JKIECS.2021.16.3.525
  15. H. Chong "Development of Image Defect Detection Model Using Machine Learning," J. of the Korea Institute of Electronic Communication Sciences, vol. 15, no. 3, 2020, pp. 513-520. https://doi.org/10.13067/JKIECS.2020.15.3.513
  16. J. Kim, "Comparison of Monthly Average Temperature Prediction Performance using Spatial Random Forest by Buffer Distance," J. of the Korean Data Analysis Society, vol. 22, no. 5, 2020, pp. 1809-1818. https://doi.org/10.37727/jkdas.2020.22.5.1809
  17. K. Kim, "Fuzzy One Class Support Vector Machine" J. of Korean Society for Internet Information, vol. 6, no. 3, 2005, pp. 159-170
  18. K. Lee, "First Retrieval of Data regarding Spatial Distribution of Asian Dust Aerosol from the Geostationary Ocean Color Imager" J. of Korean Society for Internet Information, vol. 47, no. 4, 2012, pp. 465-472.
  19. Y. Ahn,, "Spatial and Temporal Aspects of Phytoplankton Blooms in Complex Ecosystems Off the Korean Coast from Satellite Ocean Color Observations" Ocean science J., vol. 40, no. 2, 2005, pp. 67-78. https://doi.org/10.1007/BF03028587