文献类型：期刊文献

英文题名：A novel depthwise separable U-Net for large-scale wave field prediction

作者：Zhang, Zeguo[1,2];Yin, Jianchuan[1,2]

机构：[1]Guangdong Ocean Univ, Naval Architecture & Shipping Coll, Zhanjiang 524088, Peoples R China;[2]Guangdong Ocean Univ, Guangdong Prov Key Lab Intelligent Equipment South, Zhanjiang 524088, Peoples R China

年份：2025

卷号：254

外文期刊名：RENEWABLE ENERGY

收录：SCI-EXPANDED(收录号：WOS:001514544700001)、、EI(收录号：20252418576449)、Scopus(收录号：2-s2.0-105007540193)、WOS

基金：This work was supported by the National Natural Science Foundation of China under Grants 52271361 and 52231014, the Natural Science Foundation of Guangdong Province of China under Grant 2023A1515010684, the Special Projects of Key Areas for Colleges and Universities in Guangdong Province under Grant 2021ZDZX1008, the Technology breakthrough plan project of Zhanjiang under Grant 2023B01024 and the program for scientific research start-up funds of Guangdong Ocean University (060302132310) .

语种：英文

外文关键词：Wave field prediction; Wave energy; Attention strategy; Depthwise separable convolution; 2D convolutional neural network

外文摘要：Accurate spatial-temporal ocean wave energy forecasting is critical for advancing global carbon neutrality and clean energy sustainability. While deep neural networks alleviate computational burdens of numerical weather models, prior approaches relying on location-specific or grid-cell samples neglect spatial-temporal correlation and nonlinear dynamics in large 2D wave fields. Recurrent Neural Networks (RNNs) further suffer from poor convergence. To address these gaps, this work proposes a spatial-temporal depthwise separable U-Net model integrating attention mechanisms, residual learning blocks, and depthwise separable convolutions. The U-Net architecture captures multi-scale spatial patterns and propagates energy dynamics across 2D fields, while attention modules prioritize regions of nonlinear interactions (storm zones). Residual blocks stabilize temporal modeling, learning long-term dependencies and abrupt shifts (weather changes), and depthwise separable convolutions efficiently fuse spatial-temporal features, reducing redundancy while preserving variability. The model achieves an RMSE of 0.09 m (1-h) and 0.43 m (12-h) for significant wave height predictions, with PCC of 0.97 and 0.83, respectively. Spatial-averaged RMSEs are 0.01 m (1-h) and 0.09 m (12-h). Experiments demonstrated that the novel model can provide great potential and guidance for operational marine monitoring and renewable energy-based marine constructions.