Journal of Korean Society of Coastal and Ocean Engineers (한국해안·해양공학회논문집)

Korean Society of Coastal and Ocean Engineers (한국해안·해양공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Prediction of the Surface Drifter Trajectories in the Korean Strait

대한해협에서 표층 뜰개 이동 예측 연구

  • Ha, Seung Yun (Oceanographic Forecast Division, Korea Hydrographic and Oceanographic Agency) ;
  • Yoon, Han-Sam (Department of Ecological Engineering, Pukyong National University) ;
  • Kim, Young-Taeg (Oceanographic Forecast Division, Korea Hydrographic and Oceanographic Agency)
  • 하승윤 (국립해양조사원 해양예보과) ;
  • 윤한삼 (부경대학교 생태공학과) ;
  • 김영택 (국립해양조사원 해양예보과)
  • Received : 2022.01.10
  • Accepted : 2022.01.27
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In order to improve the accuracy of particle tracking prediction techniques near the Korean Strait, this study compared and analyzed a particle tracking model based on a seawater flow numerical model and a machine learning based on a particle tracking model using field observation data. The data used in the study were the surface drifter buoy movement trajectory data observed in the Korea Strait, prediction data by machine learning (linear regression, decision tree) using the tide and wind data from three observation stations (Gageo Island, Geoje Island, Gyoboncho), and prediciton data by numerical models (ROMS, MOHID). The above three data were compared through three error evaluation methods (Correlation Coefficient (CC), Root Mean Square Errors (RMSE), and Normalized Cumulative Lagrangian Separation (NCLS)). As a final result, the decision tree model had the best prediction accuracy in CC and RMSE, and the MOHID model had the best prediction results in NCLS.

본 연구는 대한해협 인근 입자추적 예측 기법의 정확도 개선을 위해서 해수유동 수치모델 결과를 이용하여 만든 입자추적 모델과 현장 관측 자료를 이용한 기계학습 기반 입자 추적 모델을 비교 및 분석하였다. 세부 연구 방법으로는 대한해협에서 관측된 표층 뜰개 이동 궤적 자료, 3개 관측소(가거도, 거제도, 교본초 관측소)의 조위 및 바람자료를 학습시켜 만든 기계 학습(선형 회귀, 의사결정나무) 기반 예측자료, 수치모델 예측자료(ROMS, MOHID)를 3가지 오차평가방법(CC, RMSE, NCLS)을 통해 비교하였다. 최종 결과로서 CC와 RMSE에서는 의사결정나무 모델의 예측 정확도가 가장 우수하였고 NCLS에서는 MOHID 모델의 예측 결과가 가장 우수하였다.

Keywords

References

  1. Ha, S.Y. (2021). A study on the trajectory prediction of drifting buoys considering machine learning methods in the Korea Strait. Pukyong National Univ., Master's thesis (in Korean).
  2. Heo, M.S. (2020), My First Machine Leaning/Deep Learning. Wikibooks (in Korean).
  3. Kim, G.D. and Kim, Y.H. (2018). Correction of drifter data using recurrent neural networks. Journal of the Korea Convergence Society, 9(3), 15-21 (In Korean). https://doi.org/10.15207/JKCS.2018.9.3.015
  4. Kim, T.Y. and Yoon, H.S. (2011). Skill assessments for evaluating the performance of the hydrodynamic model. Journal of the Korean Society for Marine Environment & Energy, 14(2), 107-113 (In Korean). https://doi.org/10.7846/JKOSMEE.2011.14.2.107
  5. Lee, C.H., Kim, G.D. and Kim, Y.H. (2017). Performance comparison of machine learning based on neural networks and statistical methods for prediction of drifter movement. Journal of the Korea Convergence Society, 8(10), 45-52 (In Korean). https://doi.org/10.15207/JKCS.2017.8.10.045
  6. Liu, Y. and Weisberg, R.H. (2011). Evaluation of trajectory modeling in different dynamic regions using Normalized Cumulative Lagrangian separation. Journal of Geophysical Research: Oceans. 116(C9).
  7. Park, S.H. (2020). A Piece of Python for Machine Learning. Bjpublic (in Korean).
  8. Ryu, H.J., Song, M.S., Jung, J.Y. and Ahn, Y.H. (2002). Surface current measurement by tracking a buoy drifted from Mara-do. Journal of the Korea Society for Marine Environmental Engineering, 5(4), 41-47 (In Korean).