AI model improves global ocean forecasts for up to 60 days
Neptune: An AI model for Global Ocean Subseasonal Prediction
Artificial Intelligence
Summary
Predicting ocean conditions weeks in advance is important for many areas like farming and disaster planning but is hard because traditional methods are slow and complex. The authors created Neptune, an AI system that uses smart computer techniques to quickly mimic ocean behavior and changes over time. Neptune looks at many ocean features such as temperature, currents, and sea ice, providing daily updates up to two months ahead. Their tests show Neptune matches real ocean patterns well and stays reliable even over longer periods. This approach could help make more timely and detailed ocean forecasts in the future.
Subseasonal-to-seasonal forecastingOcean General Circulation ModelsConvolutional Neural NetworksSpherical Fourier Neural OperatorsOcean heat contentSea surface heightSea ice concentrationENSO (El Niño Southern Oscillation)Ocean currentsData-driven modeling
Authors
Davide Donno, Italo Epicoco, Massimo Cafaro, Gabriele Accarino, Mohammad M. Amirian, Viviana Acquaviva, Paola Nassisi, Doroteaciro Iovino, Annalisa Bracco, Simona Masina, Pierre Gentine
Abstract
Subseasonal-to-seasonal (S2S) forecasting is societally critical, supporting decision-making in sectors ranging from water and agricultural management to disaster risk reduction, energy planning, and insurance. Achieving reliable predictions at these timescales requires representing the ocean and its dynamics, but traditional physics-based Ocean General Circulation Models (OGCMs), are computationally expensive and difficult to develop and improve because of the code complexity. In this work, we propose Neptune, an end-to-end data-driven framework for global ocean and sea-ice components emulation tailored for S2S timescales, up to 60 days. Neptune combines Convolutional Neural Networks (CNNs) and Spherical Fourier Neural Operators (SFNOs) to effectively capture local features and global cross-scale interactions, thereby obtaining a coherent representation of the ocean state. Forced by prescribed daily atmospheric fields, Neptune emulates ocean state variables, from temperature and salinity, to zonal and meridional currents, from sea surface height to sea ice thickness and concentration, with daily outputs at the ocean surface and through the water column. Specifically, we propose two variants of Neptune, Neptune-1 and Neptune-025, capable of emulating the ocean state at 1° and 0.25° resolution, respectively. Evaluated against a suite of metrics, including statistics (RMSE, CRPS and ACC), physical coherency (Ocean Heat Content, Eddy Kinetic Energy and Ice Brier Score) and climate indices (ENSO and Z20 metric, IOD), Neptune successfully reproduces the spatio-temporal evolution of the oceanic fields up to 60 days, and is stable over long timescales. Neptune provides compelling evidence that end-to-end data-driven ocean emulators can become a powerful component of next-generation S2S forecasting systems, emulating ocean state at high spatio-temporal resolution.