Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere
By Boris Bonev, Thorsten Kurth, Christian Hundt, Jaideep Pathak, Maximilian Baust, Karthik Kashinath, Anima Anandkumar. International Conference on Machine Learning, 2023
322 citations recorded by the source corpus.
Fourier Neural Operators (FNOs) have proven to be an efficient and effective method for resolution-independent operator learning in a broad variety of application areas across scientific machine learning. A key reason for their success is their ability to accurately model long-range dependencies in spatio-temporal data by learning global convolutions in a computationally efficient manner. To this end, FNOs rely on the discrete Fourier transform (DFT), however, DFTs cause visual and spectral artifacts as well as pronounced dissipation when learning operators in spherical coordinates since they incorrectly assume a flat geometry. To overcome this limitation, we generalize FNOs on the sphere, introducing Spherical FNOs (SFNOs) for learning operators on spherical geometries. We apply SFNOs to forecasting atmospheric dynamics, and demonstrate stable auto\-regressive rollouts for a year of simulated time (1,460 steps), while retaining physically plausible dynamics. The SFNO has important implications for machine learning-based simulation of climate dynamics that could eventually help accelerate our response to climate change.
Subfields: Artificial Intelligence, Atmospheric Science
View Paper: https://www.semanticscholar.org/paper/f3338a66e93b62d60ee01aa00ed798c9cc9582d9
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Alvaro Sanchez-Gonzalez
- Peter W. Battaglia
- Ian Langmore
- Stephan Rasp
- Stephan Hoyer
- Josh Tenenbaum
- Jessica B. Hamrick
- Yoshua Bengio
In Atmospheric Science
Citations in the corpus
- WeatherBench 2: A Benchmark for the Next Generation of Data‐Driven Global Weather Models (2023, methodology): “An updated version using spherical Fourier neural operators was also published recently (Bonev et al., 2023).”
- A foundation model for the Earth system (2025, unknown): “By contrast, current state-of-the-art AI weather prediction models 2,3,16,38,44 can only operate at 0.25° resolution.”