ORCAst: Operational High-Resolution Current Forecasts

TL;DR

ORCAst is a multi-stage neural network that accurately forecasts high-resolution ocean surface currents over a week by integrating satellite altimetry and in situ drifter data, outperforming existing methods.

Contribution

It introduces a novel multi-arm encoder-decoder architecture trained on satellite and in situ data for improved ocean current forecasting.

Findings

Achieves superior nowcast and forecast accuracy compared to state-of-the-art methods.

Effectively integrates satellite altimetry and drifter data in a multi-stage learning process.

Training on specific regions enhances model performance.

Abstract

We present ORCAst, a multi-stage, multi-arm network for Operational high-Resolution Current forecAsts over one week. Producing real-time nowcasts and forecasts of ocean surface currents is a challenging problem due to indirect or incomplete information from satellite remote sensing data. Entirely trained on real satellite data and in situ measurements from drifters, our model learns to forecast global ocean surface currents using various sources of ground truth observations in a multi-stage learning procedure. Our multi-arm encoder-decoder model architecture allows us to first predict sea surface height and geostrophic currents from larger quantities of nadir and SWOT altimetry data, before learning to predict ocean surface currents from much more sparse in situ measurements from drifters. Training our model on specific regions improves performance. Our model achieves stronger nowcast and forecast performance in predicting ocean surface currents than various state-of-the-art methods.