ML4WX

Benchmarks, datasets & evaluation

Boosting Weather Prediction with Machine Learning

Sarah Stanley

Eos ·

Paper

In one sentence. Eos article introducing WeatherBench, an ERA5-based benchmark dataset for evaluating data-driven AI weather forecasting against standard baselines.

Abstract

WeatherBench is a data set compiled to serve as a standard for evaluating new approaches to artificial intelligence–driven weather forecasting.

Labels

Topic
Benchmarks, datasets & evaluation
Type
Benchmark or dataset
Time scale
3–15 days
Domain
Global
Data
ERA5 / reanalysis
Status
Research
Identifiers
DOI:10.1029/2020eo149637 OpenAlex:W3109880999
Added
2026-10-22

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