Diving Deep: Forecasting Sea Surface Temperatures and Anomalies

TL;DR

This paper summarizes the outcomes of a challenge on forecasting sea surface temperatures and anomalies, highlighting machine learning approaches and their effectiveness in climate prediction tasks.

Contribution

It presents a comprehensive overview of methods and results from a competitive challenge focused on SST and SSTA forecasting using historical climate data.

Findings

Machine learning models achieved significant accuracy in SST prediction.

Different approaches showed varying strengths in short-term versus long-term forecasts.

Lessons learned inform future climate modeling and predictive analytics.

Abstract

This overview paper details the findings from the Diving Deep: Forecasting Sea Surface Temperatures and Anomalies Challenge at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 2024. The challenge focused on the data-driven predictability of global sea surface temperatures (SSTs), a key factor in climate forecasting, ecosystem management, fisheries management, and climate change monitoring. The challenge involved forecasting SST anomalies (SSTAs) three months in advance using historical data and included a special task of predicting SSTAs nine months ahead for the Baltic Sea. Participants utilized various machine learning approaches to tackle the task, leveraging data from ERA5. This paper discusses the methodologies employed, the results obtained, and the lessons learned, offering insights into the future of climate-related predictive modeling.