Deep Learning to Infer Ocean Dynamics
Abstract
Inferring ocean dynamics remains challenging due to the complexity of multiscale nonlinear interactions, sparsity of observations, and limitations of numerical models. Deep learning (DL) has emerged as a powerful data-driven framework that exploits nonlinear dependencies across heterogeneous datasets, complementing traditional approaches. Here, we review recent progress in applying DL to ocean dynamics, including spatiotemporal interpolation of satellite and \emph{in situ} data, estimation of unobserved ocean variables, neural data assimilation, ocean forecasting, and the development of eddy parameterizations for hybrid models. DL methods have excelled at fusing multimodal observations, reconstructing multiscale fields, learning complex distributions, and providing computationally efficient predictions that often match or exceed those of conventional statistical approaches. Despite the rapid methodological progress, opportunities remain in uncertainty quantification, ensuring physical consistency, generalization to unseen conditions, and leveraging DL beyond obtaining operational gains to advance scientific discovery and human-level understanding of ocean dynamics.
Related
- Large-scale bioacoustic detection using semantic segmentation: a deep learning framework applied to fin whale calls in ocean-bottom seismometer recordings
- A deep learning global ocean forecasting model with sub-daily and eddy-resolving resolution
- New Wine in an Old Bottle -- NeuralPOM: A Hybrid Ocean Forecast Model with Differentiable Dynamics and Staged Learning
- Learning native eddy-resolving ocean dynamics outperforms coarse emulation and downscaling
- A deep learning-based pipeline combining UAV imagery and YOLO models for intertidal population dynamics monitoring
BibTeX
@misc{manucharyan2026deep,
title = {{Deep Learning to Infer Ocean Dynamics}},
author = {Georgy Manucharyan and Scott A Martin and Dhruv Balwada and Jinbo Wang},
howpublished = {EarthArXiv},
year = {2026},
month = sep,
doi = {10.1146/annurev-marine-040324-023244},
url = {https://eartharxiv.org/repository/view/15102/},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Deep Learning to Infer Ocean Dynamics
AU - Georgy Manucharyan
AU - Scott A Martin
AU - Dhruv Balwada
AU - Jinbo Wang
PY - 2026
DA - 2026/09/20
PB - EarthArXiv
DO - 10.1146/annurev-marine-040324-023244
UR - https://eartharxiv.org/repository/view/15102/
AB - Inferring ocean dynamics remains challenging due to the complexity of multiscale nonlinear interactions, sparsity of observations, and limitations of numerical models. Deep learning (DL) has emerged as a powerful data-driven framework that exploits nonlinear dependencies across heterogeneous datasets, complementing traditional approaches. Here, we review recent progress in applying DL to ocean dynamics, including spatiotemporal interpolation of satellite and \emph{in situ} data, estimation of unobserved ocean variables, neural data assimilation, ocean forecasting, and the development of eddy parameterizations for hybrid models. DL methods have excelled at fusing multimodal observations, reconstructing multiscale fields, learning complex distributions, and providing computationally efficient predictions that often match or exceed those of conventional statistical approaches. Despite the rapid methodological progress, opportunities remain in uncertainty quantification, ensuring physical consistency, generalization to unseen conditions, and leveraging DL beyond obtaining operational gains to advance scientific discovery and human-level understanding of ocean dynamics.
ER -