Study on time series prediction model of sea surface temperature based on Ensemble Empirical Mode Decomposition and Autoregressive Integrated Moving Average

ZHANG Ying; TAN Yan-chun; PENG Fa-ding; LIAO Xing-jie; YU Yu-xin

doi:10.3969/j.issn.1001-909X.2019.01.002

PDF(1566 KB)

Journal of Marine Sciences ›› 2019, Vol. 37 ›› Issue (1) : 9-14. DOI: 10.3969/j.issn.1001-909X.2019.01.002

Study on time series prediction model of sea surface temperature based on Ensemble Empirical Mode Decomposition and Autoregressive Integrated Moving Average

ZHANG Ying¹, TAN Yan-chun^*2, PENG Fa-ding¹, LIAO Xing-jie¹, YU Yu-xin²

Author information +

History +

Abstract

Various types of ocean detection data with high spatial and temporal resolution provides possibilities for the application of signal decomposition and machine learning algorithms. In order to establish an effective sea surface temperature (SST) prediction model, the high time resolution of the SST and the fusion of products were used in this study, introducing the ensemble empirical mode decomposition (EEMD) in the field of signal processing and autoregressive integrated moving average model (ARIMA) in the field of machine learning. Firstly, the SST data were decomposed into several frequency sequences by EEMD method, which was the most suitable for decomposing natural signals. After that the ARIMA was used to predict the sequence of frequencies, and then the predicted results of each sequence were combined. Compared with the previous method of directly using SST data to build prediction model, this method achieves higher accuracy because of its abundant data, and provides a new way for better SST prediction.

Key words

Ensemble Empirical Mode Decomposition / machine learning / Autoregressive Integrated Moving Average Model / sea surface temperatures

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

ZHANG Ying, TAN Yan-chun, PENG Fa-ding, LIAO Xing-jie, YU Yu-xin. Study on time series prediction model of sea surface temperature based on Ensemble Empirical Mode Decomposition and Autoregressive Integrated Moving Average[J]. Journal of Marine Sciences. 2019, 37(1): 9-14 https://doi.org/10.3969/j.issn.1001-909X.2019.01.002

References

[1] JI Jin-xi, ZHANG Li-feng. Prediction of sea surface temperature by Kalman filtering[J]. Marine Forecasts,2010,27(3):59-65.
吉进喜,张立凤,郭渊. Kalman滤波技术在海表温度预测中的应用[J].海洋预报,2010,27(3):59-65.
[2] XU Shu-wen, XIA Min-hui, WANG Xiao-chun, et al. Relationship between MJO and tropical wind diurnal cycle with SST diurnal warming[J]. Marine Forecasts,2018,35(1):80-94.
徐淑雯,夏旻慧,王晓春,等.MJO与热带风场、海温日变化的关系[J].海洋预报,2018,35(1):80-94.
[3] CHEN Jian, JIANG Zhu-hui, SU Xing-tao, et al. Prescribed error estimation and diagnostic analysis in reconstruction of 3-D ocean temperature field from multi-source data[J]. Haiyang Xuebao,2018,40(4):15-29.
陈建,姜祝辉,宿兴涛,等.多源资料重构三维海温场的先验误差估计和诊断分析[J].海洋学报,2018,40(4):15-29.
[4] FANG Yue-wei, TANG You-min, LI Jun-de, et al. Several statistical models to predict tropical Indian Ocean sea surface temperature anomaly[J]. Journal of Marine Sciences,2018,36(1):1-15.
方玥炜,唐佑民,李俊德,刘婷.几种统计模型对热带印度洋海温异常的预报[J].海洋学研究,2018,36(1):1-15.
[5] CHEN Si-si, ZHANG Jing-yong, HUANG Gang. Application of time-scale decomposition statistical method in climatic prediction of summer extreme high-temperature events in South China[J]. Climatic and Environmental Research,2018,23(2):185-198.
陈思思,张井勇,黄刚.时间尺度分离在华南夏季极端高温预测中的应用[J].气候与环境研究,2018,23(2):185-198.
[6] ZHAO Yu-heng, FENG Guo-lin, ZHENG Zhi-hai. Classification of winter typical sea surface temperature variabilities based on statistical method[J]. Plateau Meteorology,2017,36(5):1 357-1 367.
赵玉衡,封国林,郑志海.基于统计方法的典型冬季海温变率分类研究[J].高原气象,2017,36(5):1 357-1 367.
[7] MAO Wen-shu, WANG Qian-qian, PENG Jun, et al. Characteristics of meiyu precipitation and SVD analysis of precipitation over the Changjiang-Huaihe River valley and the sea surface temperature in the northern Pacific Ocean[J]. Journal of Tropical Meteorology,2008,24(3):259-264.
毛文书,王谦谦,彭骏,等.江淮梅雨特征及其与北太平洋海温的SVD分析[J].热带气象学报,2008,24(3):259-264.
[8] REYNOLDS R W, RAYNER N A, SMITH T M, et al. An improved in situ and satellite SST analysis for climate[J]. Journal of Climate, 2002, 15(13):1 609-1 625.
[9] O'CARROLL A G, SAUNDERS R W, WATTS J G. The measurement of the sea surface temperature by satellites from 1991 to 2005[J]. Journal of Atmospheric & Oceanic Technology, 2005, 23(11):1 573-1 582.
[10] WU Zhao-hua, HUANG N E. Ensemble empirical mode decomposition: A noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1):1-41.
[11] HUANG N E, WU Zhao-hua. A Review on Hilbert-Hung transform method and its applications to geophysical studies[J]. Reviews of Geophysics, 2008, 46(2):1-23.
[12] HUANG N E., SHEN Zheng, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings A, 1998, 454:903-995.
[13] DILLING S, MACVICAR B J. Cleaning high-frequency velocity profile data with autoregressive moving average (ARMA) models[J]. Flow Measurement & Instrumentation, 2017, 54:68-81.
[14] DONG Yin-feng, LI Y, LAI M. Structural damage detection using empirical-mode decomposition and vector autoregressive moving average model[J]. Soil Dynamics & Earthquake Engineering, 2010, 30(3):133-145.
[15] PORPORATO A, RIDOLFI L. Multivariate nonlinear prediction of river flows[J]. Journal of Hydrology, 2001, 248(1-4):109-122.
[16] BROCKWELL P J. Time series: Theory and methods[M]. Springer-Verlag, 2015.