Towards Spatio-temporal Sea Surface Temperature Forecasting via Static and Dynamic Learnable Personalized Graph Convolution Network

TL;DR

This paper introduces a novel graph convolution network that models both long-term and short-term spatiotemporal patterns in sea surface temperature data, achieving state-of-the-art forecasting accuracy.

Contribution

It proposes a static and dynamic learnable personalized graph convolution network (SD-LPGC) that effectively captures complex ocean dynamics for SST prediction.

Findings

Achieves superior forecasting accuracy on real SST datasets.

Effectively models both stable and evolving spatiotemporal patterns.

Outperforms existing deep learning methods in SST prediction.

Abstract

Sea surface temperature (SST) is uniquely important to the Earth's atmosphere since its dynamics are a major force in shaping local and global climate and profoundly affect our ecosystems. Accurate forecasting of SST brings significant economic and social implications, for example, better preparation for extreme weather such as severe droughts or tropical cyclones months ahead. However, such a task faces unique challenges due to the intrinsic complexity and uncertainty of ocean systems. Recently, deep learning techniques, such as graphical neural networks (GNN), have been applied to address this task. Even though these methods have some success, they frequently have serious drawbacks when it comes to investigating dynamic spatiotemporal dependencies between signals. To solve this problem, this paper proposes a novel static and dynamic learnable personalized graph convolution network (SD-LPGC). Specifically, two graph learning layers are first constructed to respectively model the stable long-term and short-term evolutionary patterns hidden in the multivariate SST signals. Then, a learnable personalized convolution layer is designed to fuse this information. Our experiments on real SST datasets demonstrate the state-of-the-art performances of the proposed approach on the forecasting task.