A Graph Memory Neural Network for Sea Surface Temperature Prediction

Abstract

Sea surface temperature (SST) is a key factor in the marine environment, and its accurate forecasting is important for climatic research, ecological preservation, and economic progression. Existing methods mostly rely on convolutional networks, which encounter difficulties in encoding irregular data. In this paper, allowing for comprehensive encoding of irregular data containing land and islands, we construct a graph structure to represent SST data and propose a graph memory neural network (GMNN). The GMNN includes a graph encoder built upon the iterative graph neural network (GNN) idea to extract spatial relationships within SST data. It not only considers node but also edge information, thereby adequately characterizing spatial correlations. Then, a long short-term memory (LSTM) network is used to capture temporal dynamics in the SST variation process. We choose the data from the Northwest Pacific Ocean to validate GMNN’s effectiveness for SST prediction in different partitions, time scales, and prediction steps. The results show that our model has better performance for both complete and incomplete sea areas compared to other models.

AI for Marine, Ocean and Climate Change Monitoring

“…These papers can be categorized into several core themes as previously outlined: AI-Enhanced Sea-Surface Temperature Prediction: Researchers have been working on innovative AI/ML techniques to improve SST predictions, which have significant implications for various fields, including climate research, ecological preservation, and economic progress. These advancements include the use of graph memory neural networks (GMNNs) to encode irregular SST data effectively [1] and long-term and short-term memory neural networks (LSTMs) for SST prediction [2]. Satellite-Based AI Monitoring for Environmental Challenges: Satellite-based monitoring is crucial for addressing environmental challenges such as Sargassum aggregations and suspended sediment dynamics.…”