Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Tackling Climate Change with Machine Learning: Global Perspectives and Local Challenges

Graph-Based Deep Learning for Sea Surface Temperature Forecasts

Ding Ning · Varvara Vetrova · Karin Bryan

Keywords: [ Time-series analysis ] [ Climate science and climate modeling ] [ Classification, regression, and supervised learning ] [ Other ] [ Oceans and marine systems ] [ Data mining ]


Abstract:

Sea surface temperature (SST) forecasts help with managing the marine ecosystem and the aquaculture impacted by anthropogenic climate change. Numerical dynamical models are resource intensive for SST forecasts; machine learning (ML) models could reduce high computational requirements and have been in the focus of the research community recently. ML models normally require a large amount of data for training; environmental data are collected on regularly-spaced grids, so early work mainly used grid-based deep learning (DL) for prediction. However, both grid data and the corresponding DL approaches have inherent problems. As geometric DL has emerged, graphs as a more generalized data structure and graph neural networks (GNNs) have been introduced to the spatiotemporal domains. In this work, we preliminarily explored graph re-sampling and GNNs for global SST forecasts, and GNNs show better one month ahead SST prediction than the persistence model in most oceans in terms of root mean square errors.

Chat is not available.