南京信息工程大学学报2026，Vol.18Issue(3)：340-351,12.DOI:10.13878/j.cnki.jnuist.20241018001
基于优化深度学习的有效波高双通道混合预测模型
A dual-channel hybrid prediction model for significant wave height based on optimized deep learning
摘要
Abstract
Significant Wave Height(SWH)exhibits complex nonlinear dynamic properties,posing significant chal-lenges to its accurate prediction.Time-frequency decomposition is an effective approach to deal with such nonlinear-ities.However,existing methods fail to account for the distinct time-frequency characteristics of the SWH's decom-posed components.Here,we employ permutation entropy to categorize SWH components,which are obtained via En-semble Empirical Mode Decomposition(EEMD),into high-and low-frequency groups,and construct an optimized Long Short-Term Memory-Temporal Convolutional Network(LSTM-TCN)based on their respective characteristics,forming a dual-channel temporal feature extraction module.Furthermore,since different component predictions con-tribute unequally to the final SWH prediction result,the Bayesian Model Averaging(BMA)is introduced to assign adaptive weights.Finally,this paper proposes a dual-channel hybrid prediction model for SWH leveraging optimized deep learning.Experimental results show that,compared to state-of-the-art models,the proposed model achieves sig-nificant reductions in RMSE,MAE and MAPE across 1-,3-,6-,and 12-hour SWH predictions,with enhanced accu-racy and stability.关键词
有效波高/双通道预测/深度学习/集成经验模态分解/贝叶斯优化Key words
significant wave height(SWH)/dual-channel prediction/deep learning/ensemble empirical mode de-composition(EEMD)/Bayesian optimization分类
信息技术与安全科学引用本文复制引用
赵芮晗,闫加宁,韩莹..基于优化深度学习的有效波高双通道混合预测模型[J].南京信息工程大学学报,2026,18(3):340-351,12.基金项目
国家自然科学基金(62076136) （62076136）
