Impacts of Seasonal and Interannual Variabilities of Sea Surface Temperature on its Short-term Deep-learning Prediction Model Around the Southern Coast of Korea

HO-JEONG Ju; JEONG-YEOB Chae; EUN-JOO Lee; YOUNG-TAEG Kim; JAE-HUN Park

doi:10.7850/jkso.2022.27.2.049

All Issue

2022 Vol.27, Issue 2 Next Page

Article

Impacts of Seasonal and Interannual Variabilities of Sea Surface Temperature on its Short-term Deep-learning Prediction Model Around the Southern Coast of Korea 한국 남부 해역 SST의 계절 및 경년 변동이 단기 딥러닝 모델의 SST 예측에 미치는 영향

31 May 2022. pp. 49-70

PDF XML

Abstract

Sea Surface Temperature (SST), one of the ocean features, has a significant impact on climate, marine ecosystem and human activities. Therefore, SST prediction has been always an important issue. Recently, deep learning has drawn much attentions, since it can predict SST by training past SST patterns. Compared to the numerical simulations, deep learning model is highly efficient, since it can estimate nonlinear relationships between input data. With the recent development of Graphics Processing Unit (GPU) in computer, large amounts of data can be calculated repeatedly and rapidly. In this study, Short-term SST will be predicted through Convolutional Neural Network (CNN)-based U-Net that can handle spatiotemporal data concurrently and overcome the drawbacks of previously existing deep learning-based models. The SST prediction performance depends on the seasonal and interannual SST variabilities around the southern coast of Korea. The predicted SST has a wide range of variance during spring and summer, while it has small range of variance during fall and winter. A wide range of variance also has a significant correlation with the change of the Pacific Decadal Oscillation (PDO) index. These results are found to be affected by the intensity of the seasonal and PDO-related interannual SST fronts and their intensity variations along the southern Korean seas. This study implies that the SST prediction performance using the developed deep learning model can be significantly varied by seasonal and interannual variabilities in SST.

Keywords

Short-term U-Net based SST prediction

PDO and Seasonal Variabilities

해수면 온도는 기후와 바다의 생태계 그리고 인간의 활동에까지 중요한 영향을 미치는 해수의 특성 중 하나로 이를 예측하는 것은 항상 중요하게 다뤄지는 문제다. 최근 들어 과거의 패턴을 학습하여 예측값을 생성할 수 있는 딥러닝을 활용한 해수면 온도 예측이 복잡한 수치모델을 이용한 예측의 대안으로 주목받고 있다. 딥러닝은 입력 자료 간의 비선형적인 관계를 추정할 수 있는 것이 큰 장점이며, 최근 컴퓨터 그래픽카드의 발달로 많은 양의 데이터를 반복적이고 빠르게 계산할 수 있게 되었다. 본 연구에서는 기존의 딥러닝 모델의 단점들을 보완하면서 시공간 자료를 다룰 수 있는 합성곱 신경망(Convolutional Neural Network) 기반의 U-Net을 통해 단기 해수면 온도 예측을 수행하였다. 개발한 딥러닝 모델을 이용한 한국 남부 근해 해수면 온도의 단기 예측은 예측일의 해수면 온도의 중장기 변동성에 따라 달라지는 성능을 보였다. 해수면 온도 변동성의 증감은 계절적 변동 뿐 아니라 Pacific Decadal Oscillation (PDO) 지수의 변동과도 유의미한 상관관계를 보였는데, 이는 계절 변동 및 PDO에 따른 기후 변화에 기인한 수온 전선의 강도 변화가 해수면 온도의 시공간적 변동성에 영향을 줌으로써 발생했음을 확인하였다. 본 연구는 해수면 수온 자료가 가지고 있는 계절적 변동성과 경년 변동성이 딥러닝 모델의 해수면 단기 수온 예측 성능에 기여함을 밝힌 것에 그 의의가 있다.

References

국립해양조사원(KHOA), 2021. "바다누리 해양정보 서비스". http://www.khoa.go.kr/oceangrid/gis/category/observe/ observeSearch.do?type=EYS#none, Accessed 12 January 2022.

기상청(KMA), 2022. "기상청 날씨누리" https://www.weather.go.kr/plus/sea/forecast/marine_daily.jsp?topArea=12E00000, Accessed 13 May 2022.

김성중, 우성호, 김백민, 허순도, 2011. 지난 130년 간 한반도 근해의 표층 수온 변화 경향. Ocean and Polar Research., 33(3): 281-290, doi: http://dx.doi.org/10.4217/OPR.2011.33.3.281. 10.4217/OPR.2011.33.3.281

민홍식, 김철호, 2006. 한국 연안 표층수온의 경년변동과 장기변화. Ocean and Polar Research, 28(4): 415-423, doi: http://dx.doi.org/10.4217/OPR.2006.28.4.415. 10.4217/OPR.2006.28.4.415

박영규, 2005. 기후 변화와 해양 열염분 순환. 한국기상학회, 15(1): 69-74. 10.1016/j.cupe.2004.10.008

정시훈, 김영준, 박수민, 임정호, 2020. 시계열 기계학습을 이용한 한반도 남해 해수면 온도 예측 및 고수온 탐지, 대한원격탐사학회지, 36(5): 1077-1093.

Aparna, S.G., S. D'Souza and N.B. Arjun, 2018. Prediction of daily sea surface temperature using artificial neural networks. International Journal of Remote sensing, 39(12): 4214-4231, doi: 10.1080/01431161.2018.1454623.

Bai, S., J.Z. Kolter and V. Koltun, 2018. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv preprint, arXiv:1803.01271.

Björnsson, H. and S.A. Venegas, 1997. A Manual for EOF and SVD analyses of Climate data. CCGCR Report, 97(1): 112-134.

Bolton, T. and L. Zanna, 2019. Applications of deep learning to ocean data inference and subgrid parameterization. Journal of Advances in Modeling Earth Systems, 11: 376-399, doi: 10.1029/2018MS001472.

Bryan, K., 1997. A Numerical Method for the Study of the Circulation of the World Ocean. Journal of Computational Physics, 135(2): 154-169, doi: 10.1006/jcph.1997.5699.

Donlon, C.J., M. Martin, J. Stark, J. Roberts-Jones, E. Fiedler and W. Wimmer, 2012. The Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA) system. Remote Sensing of Environment, 116: 140-158, doi: 10.1016/j.rse.2010.10.017.

Lei, M., L. Shiyan, J. Chuanwen, L. Hongling and Z. Yan, 2009. A review on the forecasting of wind speed and generated power. Renewable and Sustainable Energy Reviews, 13(4): 915-920, doi: 10.1016/j.rser.2008.02.002.

O'Carroll, A.G., E.M. Armstrong, H.M. Beggs, M. Bouali, K.S. Casey, G.K. Corlett, P. Dash, C.J. Donlon, C.L. Gentemann, J.L. Høyer, A. Ignatov, K. Kabobah, M. Kachi, Y. Kurihara, I. Karagali, E. Maturi, C.J. Merchant, S. Marullo, P.J. Minnett, M. Pennybacker, B. Ramakrishnan, R. Ramsankaran, R. Santoleri, S. Sunder, S.S. Picart, J. Vázquez-Cuervo and W. Wimmer, 2019. Observational Needs of Sea Surface Temperature. Frontiers in Marine Science, 6: 420, doi: 10.3389/fmars.2019.00420. 10.3389/fmars.2019.00420

Ronneberger, O., P. Fischer and T. Brox, 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv preprint, arXiv:1505.04597. 10.1007/978-3-319-24574-4_28

Ruder, S., 2017. An overview of gradient descent optimization algorithms. arXiv preprint, arXiv:1609.04747.

Shi, X., Z. Chen, H. Wang, D. Yeung, W. Wong and W. Woo, 2015. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems, 1: 802-810.

Sun, C., J. Li, F. Jin and R. Ding, 2013. Sea surface temperature inter-hemispheric dipole and its relation to tropical precipitation. Environmental Research Letters, 8: 044006, doi: 10.1088/1748-9326/8/4/044006. 10.1088/1748-9326/8/4/044006

Temizyurek, M. and F. Dadaser-Celik, 2018. Modelling the effects of meteorological parameters on water temperature using artificial neural networks. Water Science & Technology, 77(5-6): 1724-1733, doi: 10.2166/wst.2018.058.

Wu, Q.X., D. Pairman, S.J. McNeill and E.J. Barnes, 1992. Computing Advective Velocities from satellite Images of Sea Surface Temperature. IEEE Transactions on Geoscience and Remote Sensing, 30(1): 166-176, doi: 10.1109/36.124227. 10.1109/36.124227

Xiao, C., N. Chen, C. Hu, K. Wang, Z. Xu, Y. Cai, L. Xu, Z. Chen and J. Gong, 2019. A spatiotemporal deep learning model for sea surface temperature field prediction using time-series satellite data. Environmental Modelling & Software, 120: 104502, doi: 10.1016/j.envsoft.2019.104502.

Xu, M and H. Xu, 2015. Atmpospheric Responses to Kuroshio SST Front in the East China Sea under Different Prevailing Winds in Winter and Spring. Journal of Climate, 28(8): 3191-3211, doi: 10.1175/JCLI-D-13-00675.1. 10.1175/JCLI-D-13-00675.1

Zhai, Z., D.Q. Nguyen and K. Verspoor, 2018. Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition. arXiv preprint, arXiv:1808.08450. 10.18653/v1/W18-5605

Information

Publisher :The Korean Society of Oceanography
Publisher(Ko) :한국해양학회
Journal Title :The Sea Journal of the Korean Society of Oceanography
Journal Title(Ko) :한국해양학회지 바다
Volume : 27
No :2
Pages :49-70
Received Date : 2022-02-25
Revised Date : 2022-05-18
Accepted Date : 2022-05-23
DOI :https://doi.org/10.7850/jkso.2022.27.2.049

The Sea Journal of the Korean Society of Oceanography ISSN:1226-2978(Print) 2671-8820(Online) 한국해양학회지 바다

All Issue