Diving Deep: Forecasting Sea Surface Temperatures and Anomalies

2025-01-10

AI Summary

This study addresses medium- to long-term sea surface temperature anomaly (SSTA) forecasting, specifically targeting global 3-month SSTA prediction and a dedicated 9-month forecast for the Baltic Sea—supporting climate monitoring, ecological management, and fishery adaptation. Methodologically, it systematically evaluates data-driven approaches for multi-scale SSTA predictability within the ECML PKDD Challenge framework, integrating time-series modeling, graph neural networks, Transformers, and multi-task learning into an end-to-end deep learning model trained on ERA5 reanalysis data. Contributions include: (1) establishing a novel AI-augmented climate forecasting paradigm; (2) achieving statistically significant improvements over state-of-the-art physics-based models in global 3-month SSTA prediction; and (3) demonstrating breakthrough performance in the challenging 9-month Baltic Sea forecast—validating AI’s capability to extract persistent, low-signal climate patterns from noisy observations. The results pave the way for high-temporal-resolution, high-accuracy regional climate prediction.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Sea Surface Temperature Prediction
• Baltic Sea
• Climate Change

Innovation

• Machine Learning
• ERA5 Data
• Sea Surface Temperature Prediction