Neptune: An AI model for Global Ocean Subseasonal Prediction
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.
Related
- From objective discovery to prediction of global ocean eco-provinces: A pathway for trustworthy learning
- Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction
- Dynamical-Model-Informed Stochastic Flow Matching for Global Probabilistic Subseasonal Forecasting of Means and Extremes
- EastAsiaClimateExtremes: An AI-Ready Dataset of Weekly Atmospheric and Oceanic Extremes over East Asia for Subseasonal Prediction Research
- Biases and predictability limits of Northern Hemisphere extratropical cyclones in subseasonal prediction systems
BibTeX
@misc{donno2026neptune,
title = {{Neptune: An AI model for Global Ocean Subseasonal Prediction}},
author = {Davide Donno and Italo Epicoco and Massimo Cafaro and Gabriele Accarino and Mohammad M. Amirian and Viviana Acquaviva and Paola Nassisi and Doroteaciro Iovino and Annalisa Bracco and Simona Masina and Pierre Gentine},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.08606},
eprint = {2609.08606},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.08606},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Neptune: An AI model for Global Ocean Subseasonal Prediction
AU - Davide Donno
AU - Italo Epicoco
AU - Massimo Cafaro
AU - Gabriele Accarino
AU - Mohammad M. Amirian
AU - Viviana Acquaviva
AU - Paola Nassisi
AU - Doroteaciro Iovino
AU - Annalisa Bracco
AU - Simona Masina
AU - Pierre Gentine
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2609.08606
UR - https://arxiv.org/abs/2609.08606
AB - 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.
ER -