| 基于改进EMD算法和BP神经网络的SST预测研究 |
| |
| 引用本文： | 李嘉康,赵颖,廖洪林,李其杰.基于改进EMD算法和BP神经网络的SST预测研究[J].气候与环境研究,2017,22(5):587-600. |
| |
| 作者姓名： | 李嘉康 赵颖 廖洪林 李其杰 |
| |
| 作者单位： | 中国人民解放军理工大学理学院, 南京 211101,中国人民解放军理工大学理学院, 南京 211101,中国人民解放军理工大学理学院, 南京 211101,中国人民解放军理工大学理学院, 南京 211101 |
| |
| 基金项目： | 国家自然科学基金项目91530204、41430426。 |
| |
| 摘 要： | 海洋表面温度(Sea Surface Temperature,SST)具有非平稳、非线性的特征,直接将处理平稳数据序列的方法应用到非平稳非线性特征明显的序列上显然是不合适的,预测的误差将会很大。为了提高预测精度,更好地解决非平稳非线性序列预测的问题,本文以东北部太平洋(40°N~50°N、150°W~135°W)区域的月平均海洋表面距平温度为例,首先分别应用集合经验模态分解(EEMD)和互补集合经验模态分解(CEEMD)方法将SST分解为不同尺度的一系列模态分量(IMF),再运用BP(Back Propagation)神经网络模型对每一个模态分量进行分析预测,最后将各IMF预测结果进行重构得到SST的预测值。数值试验的结果表明,CEEMD分解精度比EEMD分解精度高,CEEMD提高了基于BP神经网络的预测精度。系列试验统计分析说明应用这种方法对SST的1年预测是有效的。
|
| 关 键 词： | 集合经验模态分解 互补集合经验模态分解 BP神经网络 海洋表面月平均温度 预测 |
| 收稿时间： | 2016/9/27 0:00:00 |
| 修稿时间： | 2017/4/8 0:00:00 |
SST Forecast Based on BP Neural Network and Improved EMD Algorithm |
| |
| LI Jiakang,ZHAO Ying,LIAO Honglin and LI Qijie.SST Forecast Based on BP Neural Network and Improved EMD Algorithm[J].Climatic and Environmental Research,2017,22(5):587-600. |
| |
| Authors: | LI Jiakang ZHAO Ying LIAO Honglin and LI Qijie |
| |
| Institution: | Institute of Science, PLA University of Science and Technology, Nanjing 211101,Institute of Science, PLA University of Science and Technology, Nanjing 211101,Institute of Science, PLA University of Science and Technology, Nanjing 211101 and Institute of Science, PLA University of Science and Technology, Nanjing 211101 |
| |
| Abstract: | Monthly mean sea surface temperature (SST) is characterized by non-stationary and nonlinear feature. It is obviously unreasonable to apply linear data processing methods directly to non-stationary and nonlinear time series, which would produce large prediction errors. In order to improve the prediction accuracy and better address the non-stationary and nonlinear sequence prediction problem, in this paper, we present an example based on monthly mean SST anomalies (SSTA) of the Northeast Pacific (40°N-50°N, 150°W-135°W). We first use ensemble empirical mode decompose (EEMD) and complementary ensemble empirical mode decomposition (CEEMD) to decompose monthly mean SST into a series of Intrinsic Mode Function (IMF). BP (Back Propagation) neural network model is then utilized to predict each IMF. Finally, the forecast results of each IMF are reconstructed to obtain the predicted value of monthly mean SST. Results of the experiment indicate that the accuracy of CEEMD is better than that of EEMD, and CEEMD has improved the forecast accuracy based on BP neural network. Statistical analysis of the results of a series of experiments shows that this method is effective for SST prediction at the 1-year scale. |
| |
| Keywords: | Ensemble empirical mode decomposition Complementary Ensemble Empirical Mode Decomposition BP neural network model Monthly mean sea surface temperature Prediction |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《气候与环境研究》浏览原始摘要信息 |
| 点击此处可从《气候与环境研究》下载免费的PDF全文 |
|
