基于经验模态分解-门控循环模型的海表温度预测方法  

*Sea Surface Temperature Prediction Method Based on Empirical Mode Decomposition-Gated Recurrent Unit Model

作　　者：贺琪[1] 胡泽煜 徐慧芳[1,2] 宋巍 杜艳玲 He Qi;Hu Zeyu;Xu Huifang;Song Weil;Du YanLin(College of Information Techmology,Shanghai Oeean University,Shurnghai 201306,Chrina;College of Information Tchnology.Shanghai Jian Qioo Unioersity.Shanghai 201306,China)

机构地区：[1]上海海洋大学信息学院,上海201306 [2]上海建桥学院信息技术学院,上海201306

出　　处：《激光与光电子学进展》2021年第24期334-342,共9页Laser & Optoelectronics Progress

基　　金：上海市教育发展基金(AASH2004);上海市科委地方能力建设项目(20050501900);海洋大数据分析预报技术研发基金(2016YFC1401902)。

摘　　要：海表温度(SST)是平衡地表能量及衡量海水热量的重要指标,SST的高精度预测对全球气候、海洋环境及渔业具有重要意义。极端气候条件下,SST序列呈现明显的非平稳性,传统方法进行海表温度预测(SSTP)时难度大,且精度较低。基于经验模态分解(EMD)算法分解后的SST子序列非平稳性明显降低,且门控循环(GRU)神经网络作为一种常见的机器学习预测模型,参数较少、收敛速度更快,不易在训练过程中出现过拟合现象。结合EMD模型和GRU模型的优势,提出了一种基于EMD-GRU的SST预测模型。为验证所提模型预测效果,对5条不同长度的SST序列进行了多组对比实验。实验结果表明:与直接使用循环神经网络(RNN)、长短期记忆模型(LSTM)、门控循环神经网络(GRU)的模型相比,所提模型预测结果的多尺度复杂度更低;所提模型预测结果的均方差(MSE)和平均绝对误差(MAE)均有不同程度的降低。为验证数据序列长度对预测精度的影响,设计了补充实验。实验结果表明:预测长度越长精度效果越差;通过EMD算法对序列进行处理后,效果均得到了提升,且在预测长度变长的情况下,效果提升较为明显。Sea surface temperature(SST) is an important indicator for balancing the surface energy and measuring the sea heat, the high-precision prediction of SST is of great significance to global climate, marine environment, and fisheries. Under extreme climatic conditions, the SST sequence presents obvious non-stationarity, traditional methods are difficult to predict sea surface temperature(SSTP) and have low accuracy. The non-stationarity of the SST subsequence decomposed based on the empirical mode decomposition(EMD) algorithm is significantly reduced, and the gated recurrent unit(GRU) neural network, as a common machine learning prediction model, has fewer parameters and faster convergence speed, so it is not easy to over fit in the training process. Combining the advantages of the EMD model and the GRU model, a SST prediction model based on EMD-GRU is proposed. In order to verify the prediction effect of the proposed model, several groups of comparative experiments were carried out on five SST sequences with different lengths. Experimental results show that the multi-scale complexity of the prediction results of the proposed model is lower in comparison with directing application of recurrent neural network(RNN), long-short term memory(LSTM), and GRU models, and the mean square error(MSE) and mean absolute error(MAE) of the prediction results of the proposed model have been reduced. In order to verify the influence of data sequence length on prediction accuracy, a supplementary experiment is designed. The longer the prediction length, the worse the accuracy effect;after the sequence is processed by EMD algorithm, the effect is improved, and the effect is improved obviously when the prediction length becomes longer.

关 键 词：机器视觉 海表面温度序列 海表温度预测 经验模态分解算法 门控循环神经网络 

分 类 号：TP302.1[自动化与计算机技术—计算机系统结构]