• 中文核心期刊
  • 中国科技核心期刊
  • ISSN 1007-6336
  • CN 21-1168/X
YANG Leqing, WANG Lina, ZHANG Hongchun, DONG Changming. Combining forecasting model for sea surface temperature in the South China Sea based on STL[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2024, 43(1): 109-118. DOI: 10.12111/j.mes.2023-x-0167
Citation: YANG Leqing, WANG Lina, ZHANG Hongchun, DONG Changming. Combining forecasting model for sea surface temperature in the South China Sea based on STL[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2024, 43(1): 109-118. DOI: 10.12111/j.mes.2023-x-0167

Combining forecasting model for sea surface temperature in the South China Sea based on STL

More Information
  • Received Date: July 01, 2023
  • Revised Date: September 26, 2023
  • Accepted Date: September 26, 2023
  • Sea surface temperature (SST) is one of the important contents of marine scientific research. Abnormal fluctuations of SST lead to marine and meteorological disasters. Accurate prediction is of great significance for the study of the marine environmental protection and the development of marine economy. For the seasonality and non-stationarity of the SST sequence, firstly, the data are preprocessed through Seasonal and Trend decomposition using loess (STL), and the decomposition obtains the seasonal component, trend component and residual component. Next, select the corresponding prediction method to build a combining model. Seasonal components are predicted using the Transformer with time embedding encoding module, which fully exploits the global information of the sequence, and solve the problem of capturing long-range dependency; trend components are predicted using linear regression; residual components are predicted using auto regression model. Select the single-point SST data of the South China Sea, and apply the combination prediction model based on STL for modeling to predict the SST value of 5 days. The experimental results show that the model of this paper can effectively capture the variation pattern of SST and improve the prediction accuracy in a single-point SST prediction task.

  • [1]
    APARNA S G, D’SOUZA S, ARJUN N B. Prediction of daily sea surface temperature using artificial neural networks[J]. International Journal of Remote Sensing, 2018, 39(12): 4214-4231. doi: 10.1080/01431161.2018.1454623
    [2]
    MENDOZA V M, VILLANUEVA E E, ADEN J. Numerical experiments on the prediction of sea surface temperature anomalies in the Gulf of Mexico[J]. Journal of Marine Systems, 1997, 13(1): 83-99.
    [3]
    NOORI R, ABBASI M R, ADAMOWSKI J F, et al. A simple mathematical model to predict sea surface temperature over the northwest Indian Ocean[J]. Estuarine Coastal and Shelf Science, 2017, 197(15): 236-243.
    [4]
    STOCKDALE T N, BALMASEDA M A, VIDARD A. Tropical Atlantic SST prediction with coupled ocean–atmosphere GCMs[J]. Journal of Climate, 2006, 19(23): 6047-6061. doi: 10.1175/JCLI3947.1
    [5]
    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): 1357-1367.
    [6]
    张 莹, 谭艳春, 彭发定, 等. 基于 EEMD 和 ARIMA 的海温预测模型研究[J]. 海洋学研究, 2019, 37(1): 9-14.
    [7]
    ZHANG X, LI Y, FRERY A C, et al. Sea surface temperature prediction with memory graph convolutional networks[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 8017105.
    [8]
    BAI S J, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling [J]. arXiv preprint arXiv: 1803.01271, 2018.
    [9]
    HEWAMALAGE H, BERGMEIR C, BANDARA K. Recurrent neural networks for time series forecasting: current status and future directions[J]. International Journal of Forecasting, 2021, 37(1): 388-427. doi: 10.1016/j.ijforecast.2020.06.008
    [10]
    张雪薇, 韩 震. 基于ConvGRU深度学习网络模型的海表面温度预测[J]. 大连海洋大学学报, 2022, 37(3): 531-538.
    [11]
    谢昌辉. 基于时间序列分解的组合模型预测方法研究[D]. 西安: 西安电子科技大学, 2020.
    [12]
    BROWN T B, MANN B, RYDER N, et al. Language models are few-shot learners[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. Vancouver: Curran Associates Inc. , 2020: 159.
    [13]
    ADJEI-MENSAH I, ZHANG X L, BAFFOUR A A, et al. Investigating vision transformer models for low-resolution medical image recognition[C]//2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). Chengdu: IEEE, 2021: 179-183.
    [14]
    HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770-778.
    [15]
    ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: beyond efficient transformer for long sequence time-series forecasting [J]. arXiv preprint arXiv: 2012. 07436v3, 2021.
    [16]
    冯振鲁. 基于线性回归方法的Peck公式适应性研究[J]. 公路, 2023, 68(5): 418-422.
    [17]
    王 琰, 吕 航, 谷复光. 多元线性回归方法在地面沉降量预测中的解析及应用[J]. 安全与环境工程, 2021, 28(3): 156-161. doi: 10.13578/j.cnki.issn.1671-1556.20201148
    [18]
    夏婉玉. 基于多元线性回归方法的疫情监测系统研究[D]. 武汉: 武汉工程大学, 2022.
    [19]
    周 柯, 王晓明, 李肖博, 等. 基于ARIMA-BP组合模型的智能变电站遥测数据趋势性分析预警技术研究[J]. 哈尔滨理工大学学报, 2023, 28(01): 97-104. doi: 10.15938/j.jhust.2023.01.012
    [20]
    朱周帆, 郝 鸿, 张立文. 基于机器学习与时间序列组合模型的中国汽车市场预测[J]. 统计与决策, 2020, 36(08): 177-180. doi: 10.13546/j.cnki.tjyjc.2020.08.038
    [21]
    ZHANG Q, WANG H, DONG J Y, et al. Prediction of sea surface temperature using long short-term memory[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(10): 1745-1749. doi: 10.1109/LGRS.2017.2733548
    [22]
    贺 琪, 查 铖, 宋 巍, 等. 基于 STL 的海表面温度预测算法[J]. 海洋环境科学, 2020, 39(6): 918-925.
  • Related Articles

    [1]ZHOU Guoliang, ZHOU Feng. Sea surface temperature prediction method based on an IWOA optimized Res-BiGRU deep learning model[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2024, 43(5): 806-816. DOI: 10.12111/j.mes.2023-x-0126
    [2]WANG Lina, QI Zhiyuan, ZHANG Hongchun, DONG Changming. Prediction of significant wave height based on CNN-STLSTM-CNN model[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2024, 43(3): 417-429. DOI: 10.12111/j.mes.2023-x-0127
    [3]FANG Cao, NING Zhi-ming, WEI Fen, XIA Rong-lin, YANG Bin. Key factors affecting the concentrations and structures of nutrients around Weizhou island based on the LOICZ model[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2022, 41(5): 689-696. DOI: 10.12111/j.mes.20210040
    [4]ZHANG Xue-wei, HAN Zhen. Prediction and analysis of Argo temperature data by ConvGRU model[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2022, 41(4): 628-635. DOI: 10.12111/j.mes.20210054
    [5]XU Yang-feng, LI Lian-wei, XUE Cun-jin, YUE Zeng-you, LIU Jing-yi. Sea surface temperature consistency analysis based on AVHRR and MODIS[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2021, 40(1): 122-132. DOI: 10.12111/j.mes.20190294
    [6]LIU Xiao-xing, WEI Qi-gong, WANG Si-tong, FU Chong-yao, HUANG Yi, ZHANG Ting-ting, GONG Wei-min. Study on identification of marine oil spill using logistic regression based on petroleum fluorescence characteristics[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2017, 36(5): 760-764, 773. DOI: 10.13634/j.cnki.mes20170519
    [7]JING Xiao-li, MI Tie-zhu, ZHEN Yu, FU Bao-zhong, LI Cheng-feng, YU Zhi-gang. Description of nitrogen metabolism pathway based on Skeletonema marinoi transcriptome[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2016, 35(5): 703-711. DOI: 10.13634/j.cnki.mes20160511
    [8]ZHENG Wen-jing, HAN Yu, QIN Chuan, ZHANG Gui-ling. Continuous underway measurements of sea surface O2/Ar and pCO2 by membrane inlet mass spectrometry[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2016, 35(4): 611-617. DOI: 10.13634/j.cnki.mes20160421
    [9]QIAO Ling, ZHEN Yu, MI Tie-Zhu. Review of the brown tides caused by Aureococcus anophagefferens[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2016, 35(3): 473-480. DOI: 10.13634/j.cnki.mes20160324
    [10]SONG Wan-jiao, DONG Qing, XUE Cun-jin, WU Shu-chao. Relationships between two types El Niño events and sea surface temperature of tropical and North Pacific[J]. Chinese Journal of MARINE ENVIRONMENTAL SCIENCE, 2016, 35(3): 410-416,433. DOI: 10.13634/j.cnki.mes20160314
  • Cited by

    Periodical cited type(2)

    1. 池瑜. 基于STL的水下盾构隧道收敛组合预测模型. 上海建设科技. 2024(04): 40-45 .
    2. 赖启祥,周为峰,崔雪森,石永闯. 近40 a远洋渔业主要作业海域海表温度异常年际变化分析. 海洋科学. 2024(10): 33-47 .

    Other cited types(3)

Catalog

    Article Metrics

    Article views (162) PDF downloads (11) Cited by(5)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return