检索
E-mail
RSS

作者投稿 主编审稿 专家审稿 远程编辑

热带海洋学报

• • 上一篇    

基于SMOTE-LSTM的超短期极端风速事件预测

马林涛1, 汪致君2, 韦骏1   

  1. 1.中山大学大气科学学院, 南方海洋科学与工程广东省实验室(珠海), 广东 珠海 519082;

    2.珠海科技学院, 广东 珠海 519041



  • 收稿日期:2025-10-10 修回日期:2025-12-02 接受日期:2025-12-15
  • 通讯作者: 韦骏
  • 基金资助:

    南方海洋科学与工程广东省实验室(珠海)自主科研项目(SML2020SP009)

Ultra-Short-Term extreme wind speed event prediction based on SMOTE-LSTM

MA Lintao1, WANG Zhijun2, WEI Jun1   

  1. 1. School of Atmospheric Sciences, Sun Yat-sen University, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, China;

    2. Zhuhai College of Science and Technology, Zhuhai 519041, China



  • Received:2025-10-10 Revised:2025-12-02 Accepted:2025-12-15
  • Supported by:

    The Project of Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) (SML2020SP009)

PDF (PC)

赞

摘要： 香港位于西北太平洋台风多发区, 极端风速事件频发, 对海上风电建设与电网稳定性构成严重挑战。然而, 由于极端风速在观测数据中相对稀少, 样本分布高度不平衡, 传统的数据驱动方法往往难以准确预测此类事件。针对这一问题, 本文提出了一种基于合成少数类过采样技术(synthetic minority over-sampling technique, SMOTE)与长短期记忆网络(long short-term memory, LSTM)的超短期极端风速预测方法。首先利用SMOTE生成一定数量的极端风速样本, 从而缓解数据不平衡问题, 提升模型对稀有事件的敏感性。随后, 结合历史风速, 构建LSTM模型以捕捉时间序列的依赖关系和非线性特征。实验结果表明, 与传统LSTM模型相比, 在超短期极端风速事件预测中, 所提出的SMOTE-LSTM方法在回归任务的精度以及分类任务的综合性能均有显著提升。当极端风速样本扩增至总体的10%时, 模型表现最佳：整体均方根误差(root mean square error, RMSE)从 1.58m·s-1 降至 1.55m·s-1 ;平均绝对误差(mean absolute error, MAE)由1.05m·s-1降低至0.99m·s-1 ;F1分数由0.61提升至0.78。在20~24m·s-1的极端风速区间, 改进模型的MAE由2.29m·s-1降低至1.52m·s-1。该方法为南海及其他台风多发地区的海上风电系统在极端天气下的可靠运行提供了可行途径。

关键词: 极端大风, 风速预测, 数据增强, 长短期记忆神经网络

Abstract: Hong Kong is located in the Northwest Pacific, a region frequently affected by typhoons, where extreme wind events pose significant challenges to offshore wind power development and grid stability. However, due to the relative scarcity of extreme wind speed events in observational data, the sample distribution is highly imbalanced, and traditional data-driven methods often struggle to accurately predict such events. To address this issue, this study proposes an ultra-short-term extreme wind speed forecasting method based on the synthetic minority over-sampling technique (SMOTE) combined with long short-term memory (LSTM) networks. First, SMOTE is used to generate a certain number of extreme wind speed samples, thereby alleviating the data imbalance problem and enhancing the model's sensitivity to rare events. Then, historical wind speed data are used to construct an LSTM model to capture temporal dependencies and nonlinear features. Experimental results demonstrate that, compared with the conventional LSTM model, the proposed SMOTE-LSTM approach significantly improves both regression accuracy and classification performance in ultra-short-term extreme wind speed prediction. When the number of synthetic extreme wind samples reaches 10% of the total dataset, the model achieves optimal performance: the root mean square error (RMSE) decreases from 1.58m·s-1 to 1.55m·s-1, the mean absolute error (MAE) drops from 1.05m·s-1to 0.99m·s-1, and the F1-score rises from 0.61 to 0.78. In the extreme wind speed range of 20~24 m·s-1, the MAE is reduced from 2.29m·s-1 to 1.52m·s-1. This method provides a feasible approach for ensuring the reliable operation of offshore wind power systems under extreme weather conditions in the South China Sea and other typhoon-prone regions.

Key words: extreme wind, wind speed prediction, data augmentation, long short-term memory neural network