AWhat changed
Uses spherical-harmonic convolutions rather than planar FFTs for operator learning on spherical geometry, with a differentiable spherical-harmonic implementation and reported stable atmospheric rollouts.
Scientific scope
Uses spherical-harmonic convolutions rather than planar FFTs for operator learning on spherical geometry, with a differentiable spherical-harmonic implementation and reported stable atmospheric rollouts. Seven original authors. SO(3) equivariance pertains to the specified linear spherical layer/continuous construction; discrete nonlinearities are only approximate and the proposed nonlinear frequency variant is not equivariant. Position embeddings and valid transforms constrain grid transfer. Year-long plausible rollouts do not establish climate fidelity or long-horizon trajectory accuracy.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Seven original authors. SO(3) equivariance pertains to the specified linear spherical layer/continuous construction; discrete nonlinearities are only approximate and the proposed nonlinear frequency variant is not equivariant. Position embeddings and valid transforms constrain grid transfer. Year-long plausible rollouts do not establish climate fidelity or long-horizon trajectory accuracy.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction