Statistical and machine learning ensemble modelling to forecast sea surface temperature

TL;DR

This paper develops machine learning models, including deep learning, to forecast sea surface temperatures using satellite and atmospheric data, achieving accuracy comparable to physics-based models with low computational cost, suitable for deployment on low-power devices.

Contribution

It demonstrates that combining automated feature engineering with machine learning can produce accurate SST forecasts comparable to state-of-the-art models, with advantages in computational efficiency and deployment flexibility.

Findings

Machine learning models achieved accuracy comparable to physics-based models.

Models effectively captured seasonal and short-term atmospheric-driven variations.

Low computational cost enables deployment on edge devices in marine environments.

Abstract

In situ and remotely sensed observations have potential to facilitate data-driven predictive models for oceanography. A suite of machine learning models, including regression, decision tree and deep learning approaches were developed to estimate sea surface temperatures (SST). Training data consisted of satellite-derived SST and atmospheric data from The Weather Company. Models were evaluated in terms of accuracy and computational complexity. Predictive skill were assessed against observations and a state-of-the-art, physics-based model from the European Centre for Medium Weather Forecasting. Results demonstrated that by combining automated feature engineering with machine-learning approaches, accuracy comparable to existing state-of-the-art can be achieved. Models captured seasonal patterns in the data and qualitatively reproduce short-term variations driven by atmospheric forcing. Further, it demonstrated that machine-learning-based approaches can be used as transportable prediction tools for ocean variables -- the data-driven nature of the approach naturally integrates with automatic deployment frameworks, where model deployments are guided by data rather than user-parametrisation and expertise. The low computational cost of inference makes the approach particularly attractive for edge-based computing where predictive models could be deployed on low-power devices in the marine environment.