A Transformer-Based Regression Scheme for Forecasting Significant Wave Heights in Oceans

• Published in: IEEE journal of oceanic engineering Vol. 47; no. 4; pp. 1010 - 1023
• Main Authors: Pokhrel, Pujan, Ioup, Elias, Simeonov, Julian, Hoque, Md Tamjidul, Abdelguerfi, Mahdi
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Data assimilation; Forecasting; Machine learning; Mathematical models; Neural networks; Ocean waves; Oceans; Predictive models; Regression analysis; residual correction; Significant wave height; significant wave heights; Statistical analysis; Transformer; Transformers; Wave height
• ISSN: 0364-9059; 1558-1691
• DOI: 10.1109/JOE.2022.3173454

In this article, we present a novel approach for forecasting significant wave heights in oceanic waters. We propose an algorithm based on the WaveWatch III, differencing, and a transformer neural network (Transformer). The data becomes stationary after first-order differencing, performed with the observed significant wave height and the wave height forecasts obtained from WaveWatch III. We perform a case study on a group of 92 buoys using WaveWatch III hindcasts. The Transformer model then provides the statistical forecasts of the residuals. The Transformer-based proposed framework obtains the root mean square error of 0.231 m for two days ahead forecasting. Our proposed method outperforms existing state-of-the-art machine learning and numerical approaches for significant wave heights prediction. Our results suggest that combining numerical and machine learning approaches gives better performance than using either alone.