Browse > Article
http://dx.doi.org/10.7780/kjrs.2021.37.3.19

LSTM Based Prediction of Ocean Mixed Layer Temperature Using Meteorological Data  

Ko, Kwan-Seob (Department of Defense Science, Korea National Defense University)
Kim, Young-Won (Department of Defense Science, Korea National Defense University)
Byeon, Seong-Hyeon (Department of Defense Science, Korea National Defense University)
Lee, Soo-Jin (Department of Defense Science, Korea National Defense University)
Publication Information
Korean Journal of Remote Sensing / v.37, no.3, 2021 , pp. 603-614 More about this Journal
Abstract
Recently, the surface temperature in the seas around Korea has been continuously rising. This temperature rise causes changes in fishery resources and affects leisure activities such as fishing. In particular, high temperatures lead to the occurrence of red tides, causing severe damage to ocean industries such as aquaculture. Meanwhile, changes in sea temperature are closely related to military operation to detect submarines. This is because the degree of diffraction, refraction, or reflection of sound waves used to detect submarines varies depending on the ocean mixed layer. Currently, research on the prediction of changes in sea water temperature is being actively conducted. However, existing research is focused on predicting only the surface temperature of the ocean, so it is difficult to identify fishery resources according to depth and apply them to military operations such as submarine detection. Therefore, in this study, we predicted the temperature of the ocean mixed layer at a depth of 38m by using temperature data for each water depth in the upper mixed layer and meteorological data such as temperature, atmospheric pressure, and sunlight that are related to the surface temperature. The data used are meteorological data and sea temperature data by water depth observed from 2016 to 2020 at the IEODO Ocean Research Station. In order to increase the accuracy and efficiency of prediction, LSTM (Long Short-Term Memory), which is known to be suitable for time series data among deep learning techniques, was used. As a result of the experiment, in the daily prediction, the RMSE (Root Mean Square Error) of the model using temperature, atmospheric pressure, and sunlight data together was 0.473. On the other hand, the RMSE of the model using only the surface temperature was 0.631. These results confirm that the model using meteorological data together shows better performance in predicting the temperature of the upper ocean mixed layer.
Keywords
Temperature; Submarine; Ocean Mixed Layer; Prediction; IEODO; LSTM; Deep-learning;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 KHOA (Korea Hydrograpic and Oceanographic Agency), 2021. Ocean Data in Grid Framework, http://www.khoa.go.kr/oceangrid/gis/category/reference/distribution.do, Accessed on Mar. 15, 2021.
2 Sepp, H. and S. Jurgen, 1997. Long Short-Term Memory, Neural Computation, 9(8): 1735-1780.   DOI
3 Zhang, Q., H. Wang, J. Dong, G. Zhong, and X. Sun, 2017. Prediction of sea surface temperature using long short-term memory, IEEE Geoscience and Remote Sensing Letters, 14(10): 1745-1749.   DOI
4 Kim, J.H., 2019. Korea-China Ieodo Jurisdiction Dispute and Korea's Countermeasures, Journal of Korea the Society for Naval Science & Technolohy, 2(1): 37-44 (in Korean with English abstrsct).
5 Aurelien Geron, 2018. Neural networks and deep learning, O'Reilly Media, Sebastopol, O'Reilly Media, Inc, CA, USA
6 Bae, S.R. and K.H, Son, 2010. Sound of submarine (noise and vibration), The Korean Society for Noise and Vibration Engineering, 20(2): 9-13 (in Korean with English abstrsct).
7 Jung, S.H., Y.J. Kim, S.M. Park, and J.H, Im, 2020. Prediction of Sea Surface Temperature and Detection of Ocean Heat Wavein the South Sea of Korea Using Time-series Deep-learning Approaches, Korean Journal of Remote Sensing, 36(5): 1077-1093 (in Korean with English abstract).   DOI
8 Kim, J.C. and D.G. KIM, 2018. A Study on Correlations between Sea Surface Temperature and Air-Temperature of The Yellow Sea of Korea, The Korean Association of Island, 30(1): 151-172 (in Korean with English abstract).   DOI
9 Moon, J.H., S.S. Park, and E.J. Hwang, 2019. A Multilayer Perceptron-Based Electric Load Forecasting Scheme via Effective Recovering Missing Data, Korean Information Processing Society, 8(2): 67-78 (in Korean with English abstract).   DOI
10 Song, J.H., 2018. RNN Based Temperature Prediction Methodfor Improving Accuracy of Forecasting Temperature (Master thesis), Kyung-Hee University, Seoul, KR.
11 Kim, Y.H., B.J. Choi, J.S. Lee, D.S. Byun, K.R. Kang, Y.G. Kim and Y.K. Cho, 2013, Korean Ocean Forecasting System: Present and Future, Journal of the Korean Society of Oceanography, 18(2): 89-103 (in Korean with English abstract).   DOI
12 Kim, Y.I., D.H. Kim, and S.O. Lee, 2020. Prediction of Temperature and Heat Wave Occurrence for Summer Season Using Machine Learning, Korean Society of Disaster & Security, 13(2): 27-38 (in Korean with English abstract).
13 KMA (Korea Meteorological Adminstration), 2020. Korean Peninsula Impact Typhoon Analysis Report, https://www.kma.go.kr/download_01/typhoon/typeffect_2020.pdf, Accessed on June. 11, 2021.
14 Ko, K.S. and S.J. Lee, 2021. Prediction of Sea Surface Temperature Using LSTM and Weather Data, Proc. of 2021 Korean Society for Internet Information conference, Gyeongju-si, KR, Apr. 23-24, vol. 22, pp. 49-51.
15 Lim, S.H., J.Y. Yun, Y.B. Kim, and S.H. Nam, 2007. Variability of Underwater Sound Propagation in the Northern Part of the East Sea, Korea Institute of Military Science and Technology, 10(4): 52-61 (in Korean with English abstract).
16 Oh, N.S. and S.T. Jeong, 2015. The Prediction of Water Temperature at Saemangeum Lake by Neural Network, Journal of Korean Society of Coastal and Ocean Engineers, 27(1): 56-62 (in Korean with English abstract).   DOI
17 Park, J.H., 2019. Prediction of Short-term Surface Water Temperature Using Artificial Neural Network (PhD thesis), University of Seoul, Seoul, KR.
18 Yang, S.J., 2001. The prediction of the Target Detection Range due to the Coastal Front and Sediment Type In the Eastern Part of the South-Sea Korea (Master thesis), Korea National Defense University, Seoul, KR.
19 KMA (Korea Meteorological Adminstration), 2021. Climate change shown by the average year of the new climate, https://www.kma.go.kr/kma/servlet/NeoboardProcess?mode=download&bid=press&num=1193998&fno=2&callback=https%3a%2f%2fwww.kma.go.kr%2fkma%2fnews%2fpress.jsp&ses=USERSESSION&k=ATC202103250933312_2eaa0f02-015a-43af-a1f9-ce45c4ae4559.pdf, Accessed on May. 6, 2021.
20 Kwak, G.H., M.G. Park, C.W. Park, K.D. Lee, S.I. Na, H.Y. Ahn, and N.W. Park, 2019. Combining 2D CNN and bidirectional LSTM to consider spatiotemporal features in crop classification, Korean Journal of Remote Sensing, 35(5-1): 681-692 (in Korean with English abstract).   DOI
21 Choi, H.M., M.K. KIM, and H. Yang, 2020. High water temperature prediction using RNN-based LSTM, Proc. of 2020 The Korean Institute of Information Scientists and Engineers conference, Online, Dec. 21-23, pp. 693-695.