Sea surface temperature prediction and reconstruction using patch-level neural network representations

TL;DR

This paper explores the use of bilinear residual neural networks for predicting and reconstructing sea surface temperature from satellite data, showing significant improvements over existing data-driven models in dynamic ocean regions.

Contribution

It introduces patch-level neural network representations that mimic numerical schemes, enhancing forecasting and data interpolation for complex ocean dynamics.

Findings

Outperforms other data-driven models in forecasting accuracy.

Achieves up to 50% relative gain in dynamic areas.

Effective in missing data interpolation.

Abstract

The forecasting and reconstruction of ocean and atmosphere dynamics from satellite observation time series are key challenges. While model-driven representations remain the classic approaches, data-driven representations become more and more appealing to benefit from available large-scale observation and simulation datasets. In this work we investigate the relevance of recently introduced bilinear residual neural network representations, which mimic numerical integration schemes such as Runge-Kutta, for the forecasting and assimilation of geophysical fields from satellite-derived remote sensing data. As a case-study, we consider satellite-derived Sea Surface Temperature time series off South Africa, which involves intense and complex upper ocean dynamics. Our numerical experiments demonstrate that the proposed patch-level neural-network-based representations outperform other data-driven models, including analog schemes, both in terms of forecasting and missing data interpolation performance with a relative gain up to 50\% for highly dynamic areas.