The World as a Graph: Improving El Niño Forecasts with Graph Neural Networks
This work addresses the challenge of accurate and interpretable seasonal weather forecasting for climate scientists and policymakers, representing an incremental advance by applying GNNs to a new domain.
The authors tackled the problem of improving El Niño-Southern Oscillation (ENSO) seasonal forecasting by proposing the first application of graph neural networks (GNNs) to this task, resulting in a model that outperforms state-of-the-art deep learning-based models for forecasts up to six months ahead.
Deep learning-based models have recently outperformed state-of-the-art seasonal forecasting models, such as for predicting El Niño-Southern Oscillation (ENSO). However, current deep learning models are based on convolutional neural networks which are difficult to interpret and can fail to model large-scale atmospheric patterns. In comparison, graph neural networks (GNNs) are capable of modeling large-scale spatial dependencies and are more interpretable due to the explicit modeling of information flow through edge connections. We propose the first application of graph neural networks to seasonal forecasting. We design a novel graph connectivity learning module that enables our GNN model to learn large-scale spatial interactions jointly with the actual ENSO forecasting task. Our model, \graphino, outperforms state-of-the-art deep learning-based models for forecasts up to six months ahead. Additionally, we show that our model is more interpretable as it learns sensible connectivity structures that correlate with the ENSO anomaly pattern.