AUTHOR=Oke Peter R. , Rykova Tatiana 

TITLE=A data-driven approach to mesoscale ocean forecasting

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 12 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2025.1729116

DOI=10.3389/fmars.2025.1729116

ISSN=2296-7745

ABSTRACT=Accurate ocean forecasting is essential for many marine industries, including oil and gas, search and rescue, and Defence. Traditional forecasting systems typically produce analyses that are not dynamically consistent – leading to initialisation shock that degrades forecasts. These systems are computationally intensive and generate vast amounts of data, making it difficult for end users to interpret and exploit. Here, we develop a data-driven alternative using analog forecasting. We use along-track sea-level anomaly observations to identify past ocean states that most closely match present conditions in a large archive of model simulations. These historical cases serve as analogs to the present state. The subsequent evolution of each analog is then assembled into an ensemble forecast. We generate 15-day sea-level anomaly forecasts for twelve 5°x5° regions around Australia and demonstrate that our system outperforms traditional operational forecasts in 40-60% of cases, performs equally well (no statistical difference) in about 30% of cases, and is outperformed in about 10-25% of cases. By offering a computationally efficient approach to predicting mesoscale ocean circulation, analog forecasting presents a viable and practical alternative or compliment for ocean prediction.