표층정보를 활용한 연직 해양환경 예측 및 음속장 구축

정성훈¹^{, *} ; 이호준²

1해군 소령/해군사관학교 기계시스템공학과 부교수
2해군 소령/해군사관학교 해양학과 조교수

Surface Information-Based Prediction of the Subsurface Ocean Environment and Sound-Speed Profiles

Sunghoon Jung¹^{, *} ; Hojun Lee²

1LCDR, ROK Navy/Associate professor, Dept. of Mechanical System Engineering, Republic of Korea Naval Academy
2LCDR, ROK Navy/Assistant professor, Dept. of Oceanography, Republic of Korea Naval Academy

Correspondence to: *Sunghoon Jung Tel: +82-55-907-5320 E-mail: shjung@navy.ac.kr

초록

본 연구는 한국해양자료센터(KODC) 정선해양조사자료를 이용하여 표층수온 및 표층 염분을 활용한 연직 해양환경 예측 및 음속장 구축 기법을 제안한다. 위도, 경도, 연도, 월, 수심 등의 기본입력자료와 표층수온 및 표층염분을 활용하여 연직 수온 및 염분분포를 예측하고, 예측 결과를 기반으로 Mackenzie 음속식을 이용하여 음속을 산출하였다. 실험 결과, 표층수온 및 표층염분 정보를 추가한 경우 연직 수온 및 염분분포와 음속의 예측 성능이 모두 향상되었으며, 특히 연직 염분분포의 예측 정확도가 크게 개선되었다. 제안한 기법은 다양한 해역의 연직 해양환경 및 음속장 구축에 활용될 수 있을 것으로 기대된다.

Abstract

This study proposes a method for predicting the subsurface ocean environment and constructing sound-speed profiles using sea-surface temperature and salinity based on the hydrographic observation dataset provided by the Korea Oceanographic Data Center (KODC). The vertical temperature and salinity profiles were predicted using latitude, longitude, year, month, and depth as the basic input variables, together with sea-surface temperature and sea-surface salinity. The predicted profiles were then used to calculate the sound-speed profiles based on the Mackenzie sound-speed equation. The experimental results show that incorporating sea-surface temperature and sea-surface salinity improved the prediction performance of vertical temperature and salinity profiles, as well as sound-speed profiles, with the greatest improvement observed in the prediction accuracy of the vertical salinity profiles. The proposed method is expected to facilitate the reconstruction of subsurface ocean environments and sound-speed profiles in various marine regions.

Keywords:

Subsurface Ocean Environment, Temperature Profile, Salinity Profile, Sound-Speed Profile, Machine Learning

키워드:

연직 해양환경, 수온 프로파일, 염분 프로파일, 음속 프로파일, 기계학습

Acknowledgments

이 논문은 2026년 해군사관학교 해양연구소 학술연구과제 연구비의 지원으로 수행된 연구임.

References

Young-Joo Kim, Soojin Lee, & Young-won Kim, ‘Prediction of Vertical Sea Water Temperature Profile in the East Sea Based on Machine Learning and XBT Data,’ Journal of the Korea Society of Computer and Information, VOL. 27, NO. 11, 2022, pp. 47-55.
Kwan-Seob Ko, Seong-Hyeon Byeon, & Young-Won Kim, ‘Prediction of Sea Water Temperature by Using Deep Learning Technology Based on Ocean Buoy,’ Korean Journal of Remote Sensing, VOL. 38, NO. 3, 2022, pp. 299-309.
GHRSST Science Team, Group for High Resolution Sea Surface Temperature (GHRSST). https://www.ghrsst.org
NASA Jet Propulsion Laboratory, Soil Moisture Active Passive (SMAP) Sea Surface Salinity. https://podaac.jpl.nasa.gov/SMAP, (accessed 2026.07.22.)
해양자료센터(KODC), 정선해양조사자료. https://www.nifs.go.kr/kodc/observe/line/data, (accessed 2026.07.22.)
Leo Breiman, ‘Random Forests,’ Machine Learning, VOL. 45, 2001, pp. 5-32. [https://doi.org/10.1023/A:1010933404324]
Tianqi Chen & Carlos Guestrin, ‘XGBoost: A Scalable Tree Boosting System,’ in proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785-794. [https://doi.org/10.1145/2939672.2939785]
David E. Rumelhart, Geoffrey E. Hinton, & Ronald J. Williams, ‘Learning Representations by Back-Propagating Errors,’ Nature, VOL. 323, 1986, pp. 533-536. [https://doi.org/10.1038/323533a0]
Kenneth V. Mackenzie, ‘Nine-Term Equation for Sound Speed in the Oceans,’ Journal of the Acoustical Society of America, VOL. 70, NO. 3, 1981, pp. 807-812. [https://doi.org/10.1121/1.386920]