基于主成分分析和LSTM神经网络的海温预报模型

作者：李竞时1 2  匡晓迪1 2  李琼3  何恩业1 2  张聿柏3  袁承仪4  张延琳5

单位：1. 国家海洋环境预报中心, 北京 100081; 2. 国家海洋环境预报中心 自然资源部海洋灾害预报技术重点实验室, 北京 100081; 3. 山东省海洋预报减灾中心, 青岛 266104; 4. 天津科技大学, 天津 300222; 5. 辽宁省自然资源事务服务中心, 辽宁 沈阳 110033

关键词：主成分分析 长短时记忆神经网络 海温预报

分类号：P731.31

出版年·卷·期（页码）：2023·40·第二期（1-10）

摘要：

利用荣成、海阳两站的自建浮标海温观测数据以及区域大气模式WRF（Weather Researchand Forecasting）的气象数值预报数据，基于主成分分析（Principal Component Analysis，PCA）法和长短时记忆（Long Short-Term Memory，LSTM）神经网络，提出了适用于单站海表温度预报的PCALSTM海温预报模型。该模型可以提供24～120 h预报时效的海温预报，预测效果比数值模型和统计模型明显提高。

Using the sea temperature observation data of buoys at Rongcheng and Haiyang marine stations and the numerical forecast meteorology data of the regional atmospheric model Weather Research and Forecasting (WRF), and based on the Principal Component Analysis (PCA) and Long Short-Term Memory (LSTM) neural network, a PCA-LSTM sea temperature forecasting model suitable for the Sea Surface Temperature (SST) forecasting is proposed in this paper. This model can provide SST forecast for the following 24～120 hours, and its forecasting accuracy is significantly improved compared with the numerical model and statistical model.

参考文献：

[1] WEBSTER P J, CLAYSON C A, CURRY J A. Clouds, radiation, and the diurnal cycle of sea surface temperature in the tropical western Pacific[J]. Journal of Climate, 1996, 9(8): 1712-1730. [2] CASEY K S, CORNILLON P. Global and regional sea surface temperature trends[J]. Journal of Climate, 2001, 14(18): 3801- 3818. [3] 刘伯胜, 雷家煜. 水声学原理[M]. 哈尔滨: 哈尔滨工程大学出版社, 1993. LIU B S, LEI J Y. Principles of underwater acoustics[M]. Harbin: Harbin Engineering University Press, 1993. [4] 陈新军. 渔业资源与渔场学[M]. 北京: 海洋出版社, 2004: 289- 306. CHEN X J. Fishery resources and fishery field studies[M]. Beijing: China Ocean Press, 2004: 289-306. [5] 张建华. 海温预报知识讲座: 第一讲海水温度预报概况[J]. 海洋预报, 2003, 20(4): 81-85. ZHANG J H. Sea temperature forecast knowledge lecture: the first lecture seawater temperature forecast[J]. Marine Forecasts, 2003, 20(4): 81-85. [6] 李燕, 张建华, 刘钦政, 等. 单站海温短期预报自动化[J]. 海洋预报, 2007, 24(4): 33-41. LI Y, ZHANG J H, LIU Q Z, et al. The automation of single sea station's surface sea temperature short term forecasting[J]. Marine Forecasts, 2007, 24(4): 33-41. [7] 刘娜, 王辉, 凌铁军, 等. 全球业务化海洋预报进展与展望[J]. 地球科学进展, 2018, 33(2): 131-140. LIU N, WANG H, LING T J, et al. Review and prospect of global operational ocean forecasting[J]. Advances in Earth Science, 2018, 33(2): 131-140. [8] 匡晓迪, 王兆毅, 张苗茵, 等. 基于BP神经网络方法的近岸数值海温预报释用技术[J]. 海洋与湖沼, 2016, 47(6): 1107-1115. KUANG X D, WANG Z Y, ZHANG M Y, et al. An interpretation scheme of numerical near-shore sea-water temperature forecast based on BPNN [J]. Oceanologia et Limnologia Sinica, 2016, 47(6): 1107-1115. [9] 王兆毅, 李云, 王旭. 中国近岸海域基础预报单元海温预报指导产品研制[J]. 海洋预报, 2020, 37(4): 59-65. WANG Z Y, LI Y, WANG X. Development of forecast guidance product for sea temperature of basic forecast units in the Chinese coastal waters[J]. Marine Forecasts, 2020, 37(4): 59-65. [10] 李启华, 吉海鹏, 张高. 基于神经网络的港口潮汐预报研究[J]. 广州航海高等专科学校学报, 2007, 15(1): 1-4. LI Q H, JI H P, ZHANG G. Study on tidal prediction of harbor bared on neural network[J]. Journal of Guangzhou Maritime College, 2007, 15(1): 1-4. [11] 秦思远, 李进军, 龙冰心, 等. 基于GPOS-BP神经网络模型的潮汐预报[J]. 海洋信息, 2020, 35(2): 1-5. QIN S Y, LI J J, LONG B X, et al. Tide forecast model based on GPOS-BP neural network[J]. Marine Information, 2020, 35(2): 1- 5. [12] KUMAR N K, SAVITHA R, AL MAMUN A. Regional ocean wave height prediction using sequential learning neural networks [J]. Ocean Engineering, 2017, 129: 605-612. [13] 朱智慧, 曹庆, 徐杰. 神经网络方法在上海沿海海浪预报中的应用[J]. 海洋预报, 2018, 35(5): 25-33. ZHU Z H, CAO Q, XU J. Application of neural networks to wave prediction in coastal areas of Shanghai[J]. Marine Forecasts, 2018, 35(5): 25-33. [14] 朱浩朋, 伍玉梅, 唐峰华, 等. 采用卷积神经网络构建西北太平洋柔鱼渔场预报模型[J]. 农业工程学报, 2020, 36(24): 153- 160. ZHU H P, WU Y M, TANG F H, et al. Construction of fishing ground forecast model of Ommastrephes bartramii using convolutional neural network in the Northwest Pacific[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(24): 153-160. [15] WU A M, HSIEH W W, TANG B Y. Neural network forecasts of the tropical Pacific sea surface temperatures[J]. Neural Networks, 2006, 19(2): 145-154. [16] JIA X Y, JI Q Y, HAN L, et al. Prediction of sea surface temperature in the East China Sea based on LSTM neural network [J]. Remote Sensing, 2022, 14(14): 3300. [17] 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. HE Q, ZHA C, SONG W, et al. Sea surface temperature prediction algorithm based on STL model[J]. Marine Environmental Science, 2020, 39(6): 918-925. [18] 李艳双, 曾珍香, 张闽, 等. 主成分分析法在多指标综合评价方法中的应用[J]. 河北工业大学学报, 1999, 28(1): 94-97. LI Y S, ZENG Z X, ZHANG M, et al. Application of primary component analysis in the methods of comprehensive evaluation for many indexes[J]. Journal of Hebei University of Technology, 1999, 28(1): 94-97. [19] SCHMIDHUBER J. Deep learning in neural networks: an overview[J]. Neural Networks, 2015, 61: 85-117. [20] HOCHREITER S, SCHMIDHUBER J. Long short-term memory [J]. Neural Computation, 1997, 9(8): 1735-1780.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】