Stacked Transformer Models for Enhanced Wind Speed Prediction in the Red Sea

• Published in: IEEE International Conference on Industrial Informatics (INDIN) pp. 1 - 7
• Main Authors: Hittawe, Mohamad Mazen, Harrou, Fouzi, Sun, Ying, Knio, Omar
• Format: Conference Proceeding
• Language: English
• Published: IEEE 18.08.2024
• Subjects: Accuracy; Atmospheric modeling; Biological system modeling; Deep Learning; Measurement; Meteorology; Monitoring; Noise reduction; Predictive models; stacked models; Transformers; Wind speed; Wind speed prediction
• ISSN: 2378-363X
• DOI: 10.1109/INDIN58382.2024.10774454

Accurate wind speed (WS) prediction in the Red Sea is essential for enhancing maritime operations, climate analysis, and monitoring ecosystems. Due to the region's complex oceanic and atmospheric patterns, this work introduces new models based on Transformer architectures to improve WS forecasting. Transformers are employed for their strength in handling sequential data and capturing time dependencies. A stacked model called StackedTrans has been developed to boost performance further and integrate multiple Transformer layers. The model's effectiveness is tested with WS data collected from ten locations across the Red Sea and evaluated using five statistical metrics. The results indicate that the StackedTrans model consistently outperforms other methods, such as LSTM, BiLSTM, GRU, BIGRU, and single Transformer models. The StackedTrans architecture performed a notable R2 score of 99.96, demonstrating its high precision in WS prediction