A Gaussian process regression-based sea surface temperature interpolation algorithm -- Journal of Oceanology and Limnology,2021,39(4):1211-1221

	Cite this paper:
	Yongshun ZHANG, Miao FENG, Weimin ZHANG, Huizan WANG, Pinqiang WANG. A Gaussian process regression-based sea surface temperature interpolation algorithm[J]. Journal of Oceanology and Limnology, 2021, 39(4): 1211-1221

A Gaussian process regression-based sea surface temperature interpolation algorithm

Yongshun ZHANG¹, Miao FENG¹, Weimin ZHANG^1,2, Huizan WANG¹, Pinqiang WANG¹

1 College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China;
2 Key Laboratory of Software Engineering for Complex Systems, National University of Defense Technology, Changsha 410073, China

Abstract:

The resolution of ocean reanalysis datasets is generally low because of the limited resolution of their associated numerical models. Low-resolution ocean reanalysis datasets are therefore usually interpolated to provide an initial or boundary field for higher-resolution regional ocean models. However, traditional interpolation methods (nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation) lack physical constraints and can generate significant errors at land-sea boundaries and around islands. In this paper, a machine learning method is used to design an interpolation algorithm based on Gaussian process regression. The method uses a multiscale kernel function to process two-dimensional space meteorological ocean processes and introduces multiscale physical feature information (sea surface wind stress, sea surface heat flux, and ocean current velocity). This greatly improves the spatial resolution of ocean features and the interpolation accuracy. The effectiveness of the algorithm was validated through interpolation experiments relating to sea surface temperature (SST). The root mean square error (RMSE) of the interpolation algorithm was 38.9%, 43.7%, and 62.4% lower than that of bilinear interpolation, bicubic interpolation, and nearest neighbor interpolation, respectively. The interpolation accuracy was also significantly better in offshore area and around islands. The algorithm has an acceptable runtime cost and good temporal and spatial generalizability.

Key words: Gaussian process regression|sea surface temperature (SST)|machine learning|kernel function|spatial interpolation

Received: 2020-01-21 Revised: 2020-04-21

Tools

PDF (2394 KB) Free

Print this page

Add to favorites

Email this article to others

Authors

Articles by Yongshun ZHANG

Articles by Miao FENG

Articles by Weimin ZHANG

Articles by Huizan WANG

Articles by Pinqiang WANG

References:
Antonić O, Križan J, Marki A, Bukovec D. 2001. Spatiotemporal interpolation of climatic variables over large region of complex terrain using neural networks. Ecological Modelling, 138(1-3):255-263, https://doi.org/10.1016/S0304-3800(00)00406-3.
Appelhans T, Mwangomo E, Hardy D R, Hemp A, Nauss T. 2015. Evaluating machine learning approaches for the interpolation of monthly air temperature at Mt. Kilimanjaro, Tanzania. Spatial Statistics, 14:91-113, https://doi.org/10.1016/j.spasta.2015.05.008.
Balmaseda M A, Trenberth K E, Källén E. 2013. Distinctive climate signals in reanalysis of global ocean heat content. Geophysical Research Letters, 40(9):1 754-1 759, https://doi.org/10.1002/grl.50382.
Bryan B A, Adams J M. 2002. Three-Dimensional Neurointerpolation of Annual Mean Precipitation and Temperature Surfaces for China. Geographical Analysis, 34(2):93-111, https://doi.org/10.1111/j.1538-4632.2002.tb01078.x.
Du Y, Qu T D. 2010. Three inflow pathways of the Indonesian throughflow as seen from the simple ocean data assimilation. Dynamics of Atmospheres and Oceans, 50(2):233-256, https://doi.org/10.1016/j.dynatmoce.2010.04.001.
Du Y, Wang D, Xie Q, Church J. 2003. Harmonic analysis of sea surface temperature and wind stress in the vicinity of the maritime continent. Acta Meteorologica Sinica, 17(S1):226-237.
Grover A, Kapoor A, Horvitz E. 2015. A deep hybrid model for weather forecasting. In:Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, Sydney. p.379-386, https://doi.org/10.1145/2783258.2783275.
He H, Siu W C. 2011. Single image super-resolution using Gaussian process regression. In:Proceedings of CVPR 2011. IEEE, Providence. p.449-456, https://doi.org/10.1109/CVPR.2011.5995713.
He Z K, Liu G B, Zhao X J, Yang J. 2013. Temperature model for FOG zero-bias using Gaussian process regression. In:Du Z Y ed. Intelligence Computation and Evolutionary Computation. Springer, Berlin. p.37-45, https://doi.org/10.1007/978-3-642-31656-2_6.
Hofmann T, Schölkopf B, Smola A J. 2008. Kernel methods in machine learning. The Annals of Statistics, 36(3):1 171-1 220, https://doi.org/10.1214/009053607000000677.
Huang R L, Yu Z, Deng Y C, Zeng X L. 2014. Short-term wind speed forecasting based on SVM under different feature vectors. Acta Energiae Solaris Sinica, 35(5):866-871, https://doi.org/10.3969/j.issn.0254-0096.2014.05.022. (in Chinese with English abstract)
Jia Y N, Ma J W. 2017. What can machine learning do for seismic data processing? An interpolation application. Geophysics, 82(3):V163-V177, https://doi.org/10.1190/geo2016-0300.1.
Katsaros K B, Soloviev A V, Weisberg R H, Luther M E. 2005. Reduced horizontal sea surface temperature gradients under conditions of clear skies and weak winds. BoundaryLayer Meteorology, 116(2):175-185, https://doi.org/10.1007/s10546-004-2421-4.
Kumar A, Hu Z Z. 2012. Uncertainty in the ocean-atmosphere feedbacks associated with ENSO in the reanalysis products. Climate Dynamics, 39(3-4):575-588, https://doi.org/10.1007/s00382-011-1104-3.
Li J, Heap A D, Potter A, Daniell J J. 2011. Application of machine learning methods to spatial interpolation of environmental variables. Environmental Modelling & Software, 26(12):1 647-1 659, https://doi.org/10.1016/j.envsoft.2011.07.004.
Li J, Heap A D. 2008. A Review of Spatial Interpolation Methods for Environmental Scientists. Geoscience Australia, Canberra. 137p.
Nardelli B B, Droghei R, Santoleri R. 2016. Multi-dimensional interpolation of SMOS sea surface salinity with surface temperature and in situ salinity data. Remote Sensing of Environment, 180:392-402, https://doi.org/10.1016/j.rse.2015.12.052.
Paniagua-Tineo A, Salcedo-Sanz S, Casanova-Mateo C, OrtizGarcía E G, Cony M A, Hernández-Martín E. 2011. Prediction of daily maximum temperature using a support vector regression algorithm. Renewable Energy, 36(11):3 054-3 060, https://doi.org/10.1016/j.renene.2011.03.030.
Rasmussen C E, Williams C K I. 2006. Gaussian Processes for Machine Learning. MIT Press, Cambridge. 248p.
Sokolov S, Rintoul S R. 1999. Some Remarks on interpolation of Nonstationary oceanographic fields. Journal of Atmospheric and Oceanic Technology, 16(10):1 434-1 449, https://doi.org/10.1175/1520-0426(1999)016<1434:SROION>2.0.CO;2.
Thompson B, Tkalich P, Malanotte-Rizzoli P. 2017. Regime shift of the South China Sea SST in the late 1990s. Climate Dynamics, 48(5-6):1 873-1 882, https://doi.org/10.1007/s00382-016-3178-4.
Wang H Z, Wang G H, Chen D K, Zhang R. 2012. Reconstruction of three-dimensional pacific temperature with Argo and satellite observations. Atmosphere-Ocean, 50(S1):116-128, https://doi.org/10.1080/07055900.2012.742421.
Wang H Z, Zhang R, Liu W, Wang G H, Jin B G. 2008. Improved interpolation method based on singular spectrum analysis iteration and its application to missing data recovery. Applied Mathematics and Mechanics, 29(10):1 351-1 361, https://doi.org/10.1007/s10483-008-1010-x.
Wang Q J, Zhang X F. 2005. Effective wind speed estimation for variable speed wind turbines based on WLS-SVM. Journal of System Simulation, 17(7):1 590-1 593, https://doi.org/10.3969/j.issn.1004-731X.2005.07.017. (in Chinese with English abstract)
Wang Y L, Chaib-draa B. 2017. An online Bayesian filtering framework for Gaussian process regression:application to global surface temperature analysis. Expert Systems with Applications, 67:285-295, https://doi.org/10.1016/j.eswa.2016.09.018.
Wang Z, Bovik A C, Sheikh H R, Simoncelli E P. 2004. Image quality assessment:from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600-612, https://doi.org/10.1109/TIP.2003.819861.