Journal of the Korean Society of Marine Environment & Safety (해양환경안전학회지)

The Korean Society of Marine Environment and safety (해양환경안전학회)
권호 표지
DOI QR코드

DOI QR Code

Statistical Method and Deep Learning Model for Sea Surface Temperature Prediction

수온 데이터 예측 연구를 위한 통계적 방법과 딥러닝 모델 적용 연구

  • Received : 2023.09.08
  • Accepted : 2023.10.27
  • Published : 2023.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

As climate change continues to prompt an increasing demand for advancements in disaster and safety management technologies to address abnormal high water temperatures, typhoons, floods, and droughts, sea surface temperature has emerged as a pivotal factor for swiftly assessing the impacts of summer harmful algal blooms in the seas surrounding Korean Peninsula and the formation and dissipation of cold water along the East Coast of Korea. Therefore, this study sought to gauge predictive performance by leveraging statistical methods and deep learning algorithms to harness sea surface temperature data effectively for marine anomaly research. The sea surface temperature data employed in the predictions spans from 2018 to 2022 and originates from the Heuksando Tidal Observatory. Both traditional statistical ARIMA methods and advanced deep learning models, including long short-term memory (LSTM) and gated recurrent unit (GRU), were employed. Furthermore, prediction performance was evaluated using the attention LSTM technique. The technique integrated an attention mechanism into the sequence-to-sequence (s2s), further augmenting the performance of LSTM. The results showed that the attention LSTM model outperformed the other models, signifying its superior predictive performance. Additionally, fine-tuning hyperparameters can improve sea surface temperature performance.

기후변화 영향으로 이상고수온, 태풍, 홍수, 가뭄 등 재난 및 안전 관리기술은 지속적으로 고도화를 요구받고 있으며, 특히 해수면 온도는 한반도 주변에서 발생되는 여름철 적조 발생과 동해안 냉수대 출현, 소멸 등에 영향을 신속하게 분석할 수 있는 중요한 인자이다. 따라서, 본 연구에서는 해수면 온도 자료를 해양 이상현상 및 연구에 적극 활용되기 위해 통계적 방법과 딥러닝 알고리즘을 적용하여 예측성능을 평가하였다. 예측에 사용된 해수면 수온자료는 흑산도 조위관측소의 2018년부터 2022년까지 자료이며, 기존 통계적 ARIMA 방법과 Long Short-Term Memory(LSTM), Gated Recurrent Unit(GRU)을 사용하였고, LSTM의 성능을 더욱 향상할 수 있는 Sequence-to-Sequence(s2s) 구조에 Attention 기법을 추가한 Attention Long Short-Term Memory (LSTM)기법을 사용하여 예측 성능 평가를 진행하였다. 평가 결과 Attention LSTM 모델이 타 모델과 비교하여 더 좋은 성능을 보였으며, Hyper parameter 튜닝을 통해 해수면 수온 성능을 개선할 수 있었다.

Keywords

Acknowledgement

이 논문은 해양수산과학기술진흥원의 '해양위성영상 분석 활용 기술 개발(20210046)' 연구사업의 지원을 받아 수행되었습니다.

References

  1. Breaker, L. C.(2006), Nonlinear aspects of sea surface temperature in Monterey Bay. Progress in Oceanography, 69(1), pp. 61-89. https://doi.org/10.1016/j.pocean.2006.02.015
  2. Cassola, F., F. Ferrari, A. Mazzino, and M. M. Miglietta (2016), The role of the sea on the flash floods events over Liguria (northwestern Italy). Geophysical Research Letters, 43(7), pp. 3534-3542. https://doi.org/10.1002/2016GL068265
  3. Chen, Y., J. T. Randerson, D. C. Morton, R. S. DeFries, G. J. Collatz, P. S. Kasibhatla, L. Giglio, Y. Jin, and M. E. Marlier(2011), Forecasting fire season severity in South America using sea surface temperature anomalies. Science, 334(6057), pp. 787-791. https://doi.org/10.1126/science.1209472
  4. Cho, Y. K. and K. Kim(1996), Seasonal variation of the East Korea Warm Current and its relation with the cold water. La mer, 34, pp. 172-182
  5. Kartal, S.(2023), Assessment of the spatiotemporal prediction capabilities of machine learning algorithms on Sea Surface Temperature data: A comprehensive study. Engineering Applications of Artificial Intelligence, 118, 105675.
  6. Lee, C. K., H. C. Kim, S. G. Lee, C. S. Jing, H. G. Kim, and W. A. Lim(2001), 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. Korean Journal of Fisheries and Aquatic Sciences, 34(5), pp. 536-544.
  7. Saunders, M. A. and A. S. Lea(2008), Large contribution of sea surface warming to recent increase in Atlantic hurricane activity. Nature, 451(7178), pp. 557-560. https://doi.org/10.1038/nature06422
  8. Sarkar, P. P., P. Janardhan, and P. Roy(2020), Prediction of sea surface temperatures using deep learning neural networks. SN Applied Sciences, 2(8), 1458.
  9. Shabbar, A. and W. Skinner(2004), Summer drought patterns in Canada and the relationship toglobal sea surface temperatures. Journal of Climate, 17(14), pp. 2866-2880. https://doi.org/10.1175/1520-0442(2004)017<2866:SDPICA>2.0.CO;2
  10. Thomson, M. C., F. J. Doblas-Reyes, S. J. Mason, R. Hagedorn, S. J. Connor, T. Phindela, A. P. Morse, and T. N. Palmer(2006), Malaria early warnings based on seasonal climate forecasts from multi-model ensembles. Nature, 439(7076), pp. 576-579. https://doi.org/10.1038/nature04503
  11. Verdin, J., C. Funk, G. Senay, and R. Choularton(2005), Climate science and famine early warning. Philosophical Transactions of the Royal Society B: Biological Sciences, 360(1463), pp. 2155-2168. https://doi.org/10.1098/rstb.2005.1754
  12. Xie, J., J. Zhang, J. Yu, and L. Xu(2019), An adaptive scale sea surface temperature predicting method based on deep learning with attention mechanism. IEEE Geoscience and Remote Sensing Letters, 17(5), pp. 740-744.
  13. Yamak, P. T., L. Yujian, and P. K. Gadosey(2019), A comparison between arima, lstm, and gru for time series forecasting, Proceedings of the 2019 2nd international conference on algorithms, computing and artificial intelligence, pp. 49-55.
  14. Zhang, Z., X. Pan, T. Jiang, B. Sui, C. Liu, and W. Sun (2020), Monthly and quarterly sea surface temperature prediction based on gated recurrent unit neural network. Journal of Marine Science and Engineering, 8(4), p. 249.