REVIEW 7 cited by
Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 7 Pith papers
-
FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
A purely convolutional, spherical-geometry weather model trained with a combined spatial and spectral CRPS loss delivers GenCast-level skill, IFS-beating accuracy, and stable spectra out to 60 days.
-
Anomalous Diffusion of Tropical Cyclones Observed in Huge Ensembles of Hindcasts
Tropical cyclone track variance in a 7,424-member ML hindcast ensemble grows as a power law with exponents e≈1.1–2.0, but the ballistic values largely reflect straight-line storm motion rather than anomalous diffusion.
-
Modeling turbulent and self-gravitating fluids with Fourier neural operators
Fourier neural operators trained on 2D projected views of 3D astrophysical simulations can forecast subsequent projected density and velocity snapshots with 5-25% RMS error, though a constant hidden magnetic field mea...
-
Forecast error diagnostics in neural weather models
Correcting the stratosphere or boundary layer toward reanalysis truth substantially improves mid-latitude medium-range forecasts in a neural weather model; correcting the tropics does not.
-
DEF: Diffusion-augmented Ensemble Forecasting
A conditional diffusion model that generates perturbed initial states can turn any deterministic neural weather forecast model into an ensemble, with measured error reduction on a single ERA5 case study.
-
TCBench: A Benchmark for Tropical Cyclone Track and Intensity Forecasting at the Global Scale
TCBench benchmarks eight global models on 2023 tropical cyclones: AI models match physics models at track forecasting, but intensity and rapid-intensification skill requires post-processing.
-
Extreme Solar Storm Reveals Causal Interactions in Space Weather
A causality-informed neural network, SolarAurora, claims improved space weather forecasts for 2024 extreme storms by using synergy-flux constraints derived from 1980-2024 data.
Discussion (0). Sign in to comment.