SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.03838 · 2023

Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
bernatj/ai-based-attribution pwc_unofficial 2 of 3
FunctionStatusWhere it lives
calculate_trajectory Ran bernatj/ai-based-attribution/3_extreme_events_case_studies/hurricane_florence_2018/tropical_cyclone_functions.py
code served (permissive licence) · get_code("5cd92c0695d2d1e1")
haversine Ran bernatj/ai-based-attribution/3_extreme_events_case_studies/hurricane_florence_2018/tropical_cyclone_functions.py
code served (permissive licence) · get_code("a16c9c0d4c6220e7")
flip_lon_360_2_180 Not yet run bernatj/ai-based-attribution/3_extreme_events_case_studies/shared/utils.py
code served (permissive licence) · get_code("f54ecc0b9a873dce")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2306.03838")
get_code_for_paper("2306.03838")
have("2306.03838")

Connect an agent — have() is free.