Benchmarks, datasets & evaluation

Measuring Sharpness of AI-Generated Meteorological Imagery

Imme Ebert‐Uphoff, Lander Ver Hoef, John S. Schreck, Jason Stock, María J. Molina, Amy McGovern, Michael Yu, Bill Petzke, Kyle Hilburn, David Matthew Hall, David John Gagne, William F. Campbell et al.

Artificial Intelligence for the Earth Systems · 09 June 2025 · Colorado State University (incl. CIRA), NSF NCAR / UCAR, NOAA (incl. GFDL, PSL, GSL, NCEP/EMC), NVIDIA, University of Oklahoma (AI2ES)

Paper

In one sentence. Proposes Gaussian Blur Equivalence to interpret sharpness metrics for AI meteorological imagery, demonstrated on the GREMLIN radar emulator and GraphCast outputs.

Labels

Topic

Benchmarks, datasets & evaluation, Explainability, uncertainty & physics

Type

Evaluation or intercomparison of existing models

Domain

Regional

Data

Satellite, Radar

Status

Research

Identifiers

DOI:10.1175/aies-d-24-0083.1 OpenAlex:W4411153558

Added

2026-10-22

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.