Application of Machine Learning Algorithms for Forecasting Sea Surface Temperature at Hon Dau Station
Main Article Content
Abstract
Sea Surface Temperature (SST) plays a crucial role in climate studies, tropical cyclone prediction, and marine resource management. This study analyzes SST observations at Hon Dau station from 2000–2022 and applies ARIMAX, SARIMAX, Prophet, and LSTM models for SST forecasting. Time series decomposition was conducted to separate trend, seasonal, and residual components to guide model selection. Results indicate that ARIMAX, SARIMAX, and Prophet achieved high accuracy with mean absolute errors (MAE) of 0.82–0.92 °C, while LSTM performed less effectively due to data limitations. For long-term projection, a linear regression model with Fourier harmonics suggests an increase of approximately +1.7 °C in mean annual SST by 2100 relative to 2021, consistent with moderate climate scenarios. These findings highlight the potential of machine learning methods for short-term SST forecasting and emphasize the need for integrating multi-source data with physics-informed deep learning models to improve the reliability of climate and marine applications.
Keywords:
Sea Surface Temperature (SST); Machine learning; Short-term forecasting; Climate trend.
References
[1] N. H. Saji et al., A Dipole Mode in the Tropical Indian Ocean, Nature, Vol. 401, 1999, pp. 360-363, https://doi.org/10.1038/43854.
[2] R. A. Betts et al., El Niño and a Record CO₂ Rise, Nature Climate Change, Vol. 6, No. 9, 2016,
pp. 806-810, https://doi.org/10.1038/nclimate3063.
[3] C. Deser et al., Sea Surface Temperature Variability: Patterns and Mechanisms, Annual Review of Marine Science, Vol. 2, 2010,
pp. 115-143, https://doi.org/10.1146/annurev-marine-120408-151453.
[4] D. Baird et al., Ecosystem Response to Increasing Ambient Water Temperatures due to Climate Warming in the Sylt- Rømø Bight, Northern Wadden Sea, Germany, Estuarine, Coastal and Shelf Science, Vol. 228, 2019, pp. 106-322, https://doi.org/10.1016/j.ecss.2019.106322.
[5] P. M. Forster et al., Indicators of Global Climate Change 2023: Annual Update of Key Indicators of the State of the Climate System and Human Influence, 2024, https://doi.org/10.5194/essd-16-2625-2024.
[6] G. Bonino et al., Machine Learning Methods to Predict Sea Surface Temperature and Marine Heatwave Occurrence: A Case Study of the Mediterranean Sea, Ocean Science, Vol. 20, No. 2, 2024, pp. 417-432, https://doi.org/10.5194/os-20-417-2024.
[7] P. Heimbach et al., Crafting the Future: Machine Learning for Ocean Forecasting, 2024, https://doi.org/10.5194/sp-2024-18.
[8] J. Wallcraft et al., Software Design Description for the HYbrid Coordinate Ocean Model (HYCOM), Version 2.2, 2009.
[9] V. Alari et al., Surface Wave Effects on Water Temperature in the Baltic Sea: Simulations with the Coupled NEMO-WAM Model, Ocean Dynamics, Vol. 66, No. 8, 2016, pp. 917-930, https://doi.org/10.1007/s10236-016-0963-x.
[10] B. Huang et al., Improvements of the Daily Optimum Interpolation Sea Surface Temperature (DOISST) version 2.1, Journal of Climate, Vol. 34, No. 8, 2021, pp. 2923-2939, https://doi.org/10.1175/JCLI-D-20-0166.1.
[11] S. Wolff et al., Statistical and Machine Learning Ensemble Modelling to Forecast Sea Surface Temperature, Journal of Marine Systems, Vol. 208, 2020, 103347, https://doi.org/10.1016/j.jmarsys.2020.103347.
[12] L. Breiman, Random Forests, Machine Learning, Vol. 45, 2001, pp. 5-32, https://doi.org/10.1023/A:1010933404324.
[13] Q. Zhang et al., Prediction of Sea Surface Temperature Using Long Short-Term Memory, IEEE Geoscience and Remote Sensing Letters, Vol. 14, No. 10, 2017, pp. 1745-1749.
[14] Y. Fu et al., Prediction and Analysis of Sea Surface Temperature Based on LSTM-Transformer Model, Regional Studies in Marine Science, Vol. 78, 2004, 103726, https://doi.org/10.1016/j.rsma.2024.103726.
[15] G. E. Hinton, Deep Learning - A Technology with the Potential to Transform AI, Communications of the ACM, Vol. 61, No. 6, 2018, pp. 53-59, https://doi.org/10.1145/3211562.
[16] P. Hao et al., Prediction of Sea Surface Temperature in the South China Sea Based on Deep Learning, Remote Sensing, Vol. 15, No. 6, 2023, https://doi.org/10.3390/rs15061656.
[17] Y. Miao et al., A Multivariable Convolutional Neural Network for Forecasting Synoptic-Scale Sea Surface Temperature Anomalies in the South China Sea, Weather and Forecasting, Vol. 38,
No. 6, 2023, pp. 849-863, https://doi.org/10.1175/WAF-D-22-0094.1.
[18] S. Cuomo et al., Scientific Machine Learning through Physics-Informed Neural Networks: Where We Are and What’s Next, 2022, http://arxiv.org/abs/2201.05624.
[19] T. Yuan et al., A Space-Time Partial Differential Equation Based Physics-Guided Neural Network for Sea Surface Temperature Prediction, Remote Sensing, Vol. 15, No. 14, 2023, https://doi.org/10.3390/rs15143498.
[20] S. Wu et al., PGTransNet: A Physics-Guided Transformer Network for 3D Ocean Temperature and Salinity Predicting in Tropical Pacific, Frontiers in Marine Science, Vol. 11, 2024, https://doi.org/10.3389/fmars.2024.1477710.
[21] Y. Wang et al., Impact of Physical and Attention Mechanisms on U-Net for SST Forecasting, Intelligent Marine Technology and Systems,
Vol. 2, No. 1, 2024, https://doi.org/10.1007/s44295-024-00025-4.
[22] X. Zhao et al., Deep Learning for Ocean Temperature Forecasting: A Survey, Intelligent Marine Technology and Systems, Vol. 2, No. 28, 2024,
https://doi.org/10.1007/s44295-024-00042-3.
[23] B. Wang et al., Multi - Scale Climate Variability of the South China Sea Monsoon: A Review, Dynamics of Atmospheres and Oceans, Vol. 47, No. 1-3, 2009, pp. 15-37, https://doi.org/10.1016/j.dynatmoce.2008.09.004.
[24] N. T. Hai et al., Analysis of Sea Surface Temperature Using MODIS Imagery, Journal of Hydro - Meteorology, Vol. 625, 2013, pp. 32-37 (in Vietnamese).
[25] V. V. Tac et al., Sea Surface Temperature Anomaly in South Central Vietnam Waters Related to ENSO Phenomenon, Vietnam Journal of Marine Science and Technology, Vol. 17, No. 2, 2017, pp. 111-120,
https://doi.org/10.15625/1859-3097/17/2/10153.
[26] N. T. Thanh et al., The Impact of Satellite Sea Surface Temperature on Intensity and Track of Tropical Cyclones over the Vietnam East Sea by Using WRF Model, Journal of Hydro - Meteorology, Vol. 676, 2017, pp. 47-55 (in Vietnamese).
[27] N. X. Hien et al., Trends in Sea Surface Temperature Changes in the East Vietnam Sea, Journal of Hydro - Meteorology, Vol. 639, 2014, pp. 5-9 (in Vietnamese).
[28] N. Q. Trinh et al., Assessment of Sea surface Temperature in the Vietnam Sea for the Period 2000-2022 According to Data from the HYCOM Model, Journal of Hydro - Meteorology, Vol. 761, 2024, pp. 70-81 (in Vietnamese).
[29] N. N. Tuan et al., Research of Rain and Air Temperature in the Gulf of Tonkin from Satellite Data, Journal of Hydro - Meteorology, Vol. 755, 2023, pp. 19-28 (in Vietnamese).
[30] K. E. Trenberth et al., Earth’s Energy Imbalance, Journal of Climate, Vol. 27, No. 9, 2014,
pp. 3129-3144, https://doi.org/10.1175/JCLI-D-13-00294.1.
[31] N. V. Huong et al., Study on Sea Surface Temperateture front Distribution in Viet Nam Waters for Forcast of Fishing Ground, Journal of Hydro - Meteorology, Vol. 719, 2020, pp. 66-75
(in Vietnamese).
[32] R. A. Betts et al., El Niño and a Record CO₂ Rise, Nature Climate Change, Vol. 6, No. 9, 2016,
pp. 806-810, https://doi.org/10.1038/nclimate3063.
[2] R. A. Betts et al., El Niño and a Record CO₂ Rise, Nature Climate Change, Vol. 6, No. 9, 2016,
pp. 806-810, https://doi.org/10.1038/nclimate3063.
[3] C. Deser et al., Sea Surface Temperature Variability: Patterns and Mechanisms, Annual Review of Marine Science, Vol. 2, 2010,
pp. 115-143, https://doi.org/10.1146/annurev-marine-120408-151453.
[4] D. Baird et al., Ecosystem Response to Increasing Ambient Water Temperatures due to Climate Warming in the Sylt- Rømø Bight, Northern Wadden Sea, Germany, Estuarine, Coastal and Shelf Science, Vol. 228, 2019, pp. 106-322, https://doi.org/10.1016/j.ecss.2019.106322.
[5] P. M. Forster et al., Indicators of Global Climate Change 2023: Annual Update of Key Indicators of the State of the Climate System and Human Influence, 2024, https://doi.org/10.5194/essd-16-2625-2024.
[6] G. Bonino et al., Machine Learning Methods to Predict Sea Surface Temperature and Marine Heatwave Occurrence: A Case Study of the Mediterranean Sea, Ocean Science, Vol. 20, No. 2, 2024, pp. 417-432, https://doi.org/10.5194/os-20-417-2024.
[7] P. Heimbach et al., Crafting the Future: Machine Learning for Ocean Forecasting, 2024, https://doi.org/10.5194/sp-2024-18.
[8] J. Wallcraft et al., Software Design Description for the HYbrid Coordinate Ocean Model (HYCOM), Version 2.2, 2009.
[9] V. Alari et al., Surface Wave Effects on Water Temperature in the Baltic Sea: Simulations with the Coupled NEMO-WAM Model, Ocean Dynamics, Vol. 66, No. 8, 2016, pp. 917-930, https://doi.org/10.1007/s10236-016-0963-x.
[10] B. Huang et al., Improvements of the Daily Optimum Interpolation Sea Surface Temperature (DOISST) version 2.1, Journal of Climate, Vol. 34, No. 8, 2021, pp. 2923-2939, https://doi.org/10.1175/JCLI-D-20-0166.1.
[11] S. Wolff et al., Statistical and Machine Learning Ensemble Modelling to Forecast Sea Surface Temperature, Journal of Marine Systems, Vol. 208, 2020, 103347, https://doi.org/10.1016/j.jmarsys.2020.103347.
[12] L. Breiman, Random Forests, Machine Learning, Vol. 45, 2001, pp. 5-32, https://doi.org/10.1023/A:1010933404324.
[13] Q. Zhang et al., Prediction of Sea Surface Temperature Using Long Short-Term Memory, IEEE Geoscience and Remote Sensing Letters, Vol. 14, No. 10, 2017, pp. 1745-1749.
[14] Y. Fu et al., Prediction and Analysis of Sea Surface Temperature Based on LSTM-Transformer Model, Regional Studies in Marine Science, Vol. 78, 2004, 103726, https://doi.org/10.1016/j.rsma.2024.103726.
[15] G. E. Hinton, Deep Learning - A Technology with the Potential to Transform AI, Communications of the ACM, Vol. 61, No. 6, 2018, pp. 53-59, https://doi.org/10.1145/3211562.
[16] P. Hao et al., Prediction of Sea Surface Temperature in the South China Sea Based on Deep Learning, Remote Sensing, Vol. 15, No. 6, 2023, https://doi.org/10.3390/rs15061656.
[17] Y. Miao et al., A Multivariable Convolutional Neural Network for Forecasting Synoptic-Scale Sea Surface Temperature Anomalies in the South China Sea, Weather and Forecasting, Vol. 38,
No. 6, 2023, pp. 849-863, https://doi.org/10.1175/WAF-D-22-0094.1.
[18] S. Cuomo et al., Scientific Machine Learning through Physics-Informed Neural Networks: Where We Are and What’s Next, 2022, http://arxiv.org/abs/2201.05624.
[19] T. Yuan et al., A Space-Time Partial Differential Equation Based Physics-Guided Neural Network for Sea Surface Temperature Prediction, Remote Sensing, Vol. 15, No. 14, 2023, https://doi.org/10.3390/rs15143498.
[20] S. Wu et al., PGTransNet: A Physics-Guided Transformer Network for 3D Ocean Temperature and Salinity Predicting in Tropical Pacific, Frontiers in Marine Science, Vol. 11, 2024, https://doi.org/10.3389/fmars.2024.1477710.
[21] Y. Wang et al., Impact of Physical and Attention Mechanisms on U-Net for SST Forecasting, Intelligent Marine Technology and Systems,
Vol. 2, No. 1, 2024, https://doi.org/10.1007/s44295-024-00025-4.
[22] X. Zhao et al., Deep Learning for Ocean Temperature Forecasting: A Survey, Intelligent Marine Technology and Systems, Vol. 2, No. 28, 2024,
https://doi.org/10.1007/s44295-024-00042-3.
[23] B. Wang et al., Multi - Scale Climate Variability of the South China Sea Monsoon: A Review, Dynamics of Atmospheres and Oceans, Vol. 47, No. 1-3, 2009, pp. 15-37, https://doi.org/10.1016/j.dynatmoce.2008.09.004.
[24] N. T. Hai et al., Analysis of Sea Surface Temperature Using MODIS Imagery, Journal of Hydro - Meteorology, Vol. 625, 2013, pp. 32-37 (in Vietnamese).
[25] V. V. Tac et al., Sea Surface Temperature Anomaly in South Central Vietnam Waters Related to ENSO Phenomenon, Vietnam Journal of Marine Science and Technology, Vol. 17, No. 2, 2017, pp. 111-120,
https://doi.org/10.15625/1859-3097/17/2/10153.
[26] N. T. Thanh et al., The Impact of Satellite Sea Surface Temperature on Intensity and Track of Tropical Cyclones over the Vietnam East Sea by Using WRF Model, Journal of Hydro - Meteorology, Vol. 676, 2017, pp. 47-55 (in Vietnamese).
[27] N. X. Hien et al., Trends in Sea Surface Temperature Changes in the East Vietnam Sea, Journal of Hydro - Meteorology, Vol. 639, 2014, pp. 5-9 (in Vietnamese).
[28] N. Q. Trinh et al., Assessment of Sea surface Temperature in the Vietnam Sea for the Period 2000-2022 According to Data from the HYCOM Model, Journal of Hydro - Meteorology, Vol. 761, 2024, pp. 70-81 (in Vietnamese).
[29] N. N. Tuan et al., Research of Rain and Air Temperature in the Gulf of Tonkin from Satellite Data, Journal of Hydro - Meteorology, Vol. 755, 2023, pp. 19-28 (in Vietnamese).
[30] K. E. Trenberth et al., Earth’s Energy Imbalance, Journal of Climate, Vol. 27, No. 9, 2014,
pp. 3129-3144, https://doi.org/10.1175/JCLI-D-13-00294.1.
[31] N. V. Huong et al., Study on Sea Surface Temperateture front Distribution in Viet Nam Waters for Forcast of Fishing Ground, Journal of Hydro - Meteorology, Vol. 719, 2020, pp. 66-75
(in Vietnamese).
[32] R. A. Betts et al., El Niño and a Record CO₂ Rise, Nature Climate Change, Vol. 6, No. 9, 2016,
pp. 806-810, https://doi.org/10.1038/nclimate3063.