# The World as a Graph: Improving El Ni~no Forecasts with Graph Neural Networks

arXiv: https://arxiv.org/abs/2104.05089 · HTML: https://mlsanity.com/paper/2104.05089/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 55 references that are in the map.
- First posted on arXiv 11 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https://mlsanity.com/paper/2005.11650/) (2020)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)

## Built on by (most cited first, 17 of 17)

- [Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey](https://mlsanity.com/paper/2312.03014/) (2023)
- [ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models](https://mlsanity.com/paper/2111.14671/) (2021)
- [Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers](https://mlsanity.com/paper/2207.11417/) (2022)
- [Graph Neural Network for spatiotemporal data: methods and applications](https://mlsanity.com/paper/2306.00012/) (2023)
- [From Graphs to Qubits: A Critical Review of Quantum Graph Neural Networks](https://mlsanity.com/paper/2408.06524/) (2024)
- [AutoML for Climate Change: A Call to Action](https://mlsanity.com/paper/2210.03324/) (2022)
- [Inductive biases in deep learning models for weather prediction](https://mlsanity.com/paper/2304.04664/) (2023)
- [Graph-Based Deep Learning for Sea Surface Temperature Forecasts](https://mlsanity.com/paper/2305.09468/) (2023)
- [Using Deep Learning to Identify Initial Error Sensitivity for Interpretable ENSO Forecasts](https://mlsanity.com/paper/2404.15419/) (2024)
- [Beyond Grid Data: Exploring Graph Neural Networks for Earth Observation](https://mlsanity.com/paper/2411.03223/) (2024)
- [Conservation Tools: The Next Generation of Engineering--Biology Collaborations](https://mlsanity.com/paper/2301.01103/) (2023)
- [A Hybrid Deep-Learning Model for El Ni~no Southern Oscillation in the Low-Data Regime](https://mlsanity.com/paper/2412.03743/) (2024)
- [Statistics and Deep Learning-based Hybrid Model for Interpretable Anomaly Detection](https://mlsanity.com/paper/2202.12720/) (2022)
- [Advancing Marine Heatwave Forecasts: An Integrated Deep Learning Approach](https://mlsanity.com/paper/2412.04475/) (2024)
- [On the use of Graphs for Satellite Image Time Series](https://mlsanity.com/paper/2505.16685/) (2025)
- [MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater](https://mlsanity.com/paper/2512.12142/) (2025)
- [MICA: Multivariate Infini Compressive Attention for Time Series Forecasting](https://mlsanity.com/paper/2604.06473/) (2026)

## Abstract (arXiv)

Deep learning-based models have recently outperformed state-of-the-art seasonal forecasting models, such as for predicting El Ni~no-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.