Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193062,
        author = {Elakpa Augustine and Kombo Theophilus Johnson},
        title = {Forecasting Floating Offshore Wind Power with Hybrid CNN-LSTM Models: A Case Study in the Gulf of Guinea, Nigeria},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {3850-3862},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193062},
        abstract = {Floating offshore wind turbines represent a critical technology for harnessing deep-water wind resources, yet accurate power forecasting remains challenging due to complex aero-hydro-servo-elastic interactions and stochastic metocean conditions. This study proposes a hybrid deep learning framework combining Convolutional Neural Networks and Long Short-Term Memory networks to forecast power output from a spar-type floating offshore wind turbine in the Gulf of Guinea, offshore Nigeria (4.0°N, 6.5°E). The model is trained on high-fidelity OpenFAST simulation data incorporating realistic wind and wave conditions characteristic of the region, including seasonal variability, swell propagation, and extreme events. The hybrid architecture leverages CNN layers to extract salient spatial features from multivariate input time series while LSTM layers capture long-term temporal dependencies. Model performance is evaluated using root mean square error, mean absolute error, and coefficient of determination, with comparative analysis against standalone LSTM and persistence models. Results demonstrate that the CNN-LSTM model achieves superior forecasting accuracy with RMSE improvements of 18-25% over baseline models, offering a robust tool for grid integration and operational planning in emerging offshore wind markets. A complete MATLAB implementation framework is provided to facilitate reproducibility and further research.},
        keywords = {Floating offshore wind, deep learning, CNN-LSTM, power forecasting, Gulf of Guinea, OpenFAST, Nigeria},
        month = {February},
        }