El-GNNino
Code associated with the NeurIPS 2020 Climate Change workshop proposal paper "Graph Neural Networks for Improved El Niño Forecasting"
view repo
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, , 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.
READ FULL TEXTCode associated with the NeurIPS 2020 Climate Change workshop proposal paper "Graph Neural Networks for Improved El Niño Forecasting"
Code associated with the paper "The World as a Graph: Improving El Niño Forecasting with Graph Neural Networks". This paper is currently under review.