Predicting wind speed over the ocean is difficult due to the unequal distribution of buoy stations and the occasional fluctuations in the wind field. This study proposes a dynamic graph embedding-based graph neural network—long short-term memory joint framework (DGE-GAT-LSTM) to estimate wind speed at numerous stations by considering their spatio-temporal information properties. To begin, the buoys that are pertinent to the target station are chosen based on their geographic position. Then, the local graph structures connecting the stations are represented using cosine similarity at each time interval. Subsequently, the graph neural network captures intricate spatial characteristics, while the LSTM module acquires knowledge of temporal interdependence. The graph neural network and LSTM module are sequentially interconnected to collectively capture spatio-temporal correlations. Ultimately, the multi-step prediction outcomes are produced in a sequential way, where each step relies on the previous predictions. The empirical data are derived from direct measurements made by NDBC buoys. The results indicate that the suggested method achieves a mean absolute error reduction ranging from 1% to 36% when compared to other benchmark methods. This improvement in accuracy is statistically significant. This approach effectively addresses the challenges of inadequate information integration and the complexity of modeling temporal correlations in the forecast of ocean wind speed. It offers valuable insights for optimizing the selection of offshore wind farm locations and enhancing operational and management capabilities.

Accurately predicting wind speed is crucial for the generation efficiency of offshore wind energy. This paper proposes an ultra-short-term wind speed prediction method using a graph neural network with a multi-head attention mechanism. The methodology aims to effectively explore the spatio-temporal correlations present in offshore wind speed data to enhance the accuracy of wind speed predictions. Initially, the offshore buoys are organized into a graphical network. Subsequently, in order to cluster the nodes with comparable spatio-temporal features, it clusters the nearby nodes around the target node. Then, a multi-head attention mechanism is incorporated to prioritize the interconnections among distinct regions. In the construction of the graph neural network, a star topology structure is formed by connecting additional nodes to the target node at the center. The effectiveness of this methodology is validated and compared to other time series-based approaches through comparative testing. Metrics such as Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, and R yielded values of 0.364, 0.239, 0.489, and 0.985, respectively. The empirical findings indicate that graph neural networks utilizing a multi-head attention mechanism exhibit notable benefits in the prediction of offshore wind speed, particularly when confronted with intricate marine meteorological circumstances.

The increasing congestion in major global maritime routes poses significant threats to international maritime safety, exacerbated by the proliferation of large, high-speed vessels. To improve the detection of abnormal ship behavior, this research employed automatic identification system (AIS) data for ship trajectory forecasting. Traditional methods primarily focus on spatial and temporal correlations but often lack accuracy and reliability. In this study, ship path predictions were enhanced using the WTG model, which combines wavelet transform, temporal convolutional networks (TCN), and gated recurrent units (GRU). Initially, wavelet decomposition was applied to deconstruct the input trajectory time series. The TCN and GRU modules then extracted features from both the time series and the decomposed data. The predicted elements were reassembled using a multi-head attention mechanism and a pooling layer to produce the final predictions. Comparative experiments demonstrated that the WTG model surpasses other models in the accuracy of ship trajectory prediction. The model proposed in this study proves to be reliable for forecasting ship paths, which is crucial for marine traffic management and ensuring safe navigation.

Continuous and reliable offshore wind speed time series are essential for offshore wind resource assessment, power forecasting, and long-term wind energy analysis. However, ERA5 reanalysis data may contain site-scale biases over offshore areas, and missing records in offshore wind-tower observations limit their practical use. To improve the reliability of offshore wind speed series, this study proposes a residual learning framework for ERA5 bias correction and continuous gap reconstruction by integrating ERA5 background fields with target- and neighboring-station information. Using FINO1 and FINO3 observations in the North Sea from 2018 to 2025, ERA5 wind-vector components were matched with tower observations, and residuals of the east–west and north–south wind components were used as prediction targets. Statistical methods, linear models, tree-based ensemble models, and GRU models were evaluated under a cross-year framework, with additional analyses of historical residuals, neighboring-station information, and wind-direction-related features. Results show that target-station historical residuals dominate site-scale correction, reducing RMSE by 50.77% and 32.69% for FINO1 and FINO3, respectively, under a 1 h observation lag. Neighboring-station information provides useful constraints when local observations are limited or missing. The framework maintains stable improvements across years and strong-wind conditions and supports reliable offshore wind speed reconstruction for wind energy applications.

This study addresses the critical need for accurate sea wind speed predictions to support ocean wind farm operations, equipment maintenance, and maritime navigation safety. To enhance prediction accuracy for any location within target sea areas, we propose a short-to-medium-term wind speed prediction method that effectively explores spatiotemporal correlations in ocean reanalysis grid data. The method involves collecting and reanalyzing data, as well as spatial processing, to reconstruct the historical wind speed sequence at the target point. Finally, a future wind speed time series is generated using an LSTM network and a Transformer encoder. Test results validated against NOAA buoy data demonstrate the effectiveness of our spatiotemporal prediction model, achieving RMSE values of 1.161 m/s, 1.500 m/s, and 1.854 m/s for 1 h, 6 h, and 12 h predictions, respectively, outperforming comparative methods. The conclusions are threefold: (1) The proposed hybrid model effectively captures spatiotemporal dependencies and achieves more accurate spatiotemporal predictions compared to the benchmark model; (2) taking into account seasonal factors and forecasting time periods, the method proposed in this paper maintains good stability; (3) this framework provides a reliable technical approach for generating operational references in maritime navigation and wind power maintenance, with potential applications in wind farm siting and resource assessment.