# Dense-to-dense, medium-range weather forecasting on ERA5 reanalysis 1979–2017

Source: [Dense-to-dense, medium-range weather forecasting on ERA5 reanalysis 1979–2017](<https://www.sota2.com/research/sota/dense-to-dense-medium-range-weather-forecasting-on-era5-reanalysis-1979-2017>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-23T10:14:03.420Z

Evaluation of models performing dense-to-dense, medium-range weather forecasting using the full ERA5 reanalysis dataset (1979–2017), reporting on model size and training time.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Dense-to-dense, medium-range weather forecasting |
| Dataset (including any stated split) | ERA5 reanalysis 1979–2017 |
| Metric | Model Size |
| Unit | SIZE |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Model Size](<https://www.sota2.com/research/sota/dense-to-dense-medium-range-weather-forecasting-on-era5-reanalysis-1979-2017.md?metric=Model%20Size>): Lower is better; unit: SIZE.

- [Training Time](<https://www.sota2.com/research/sota/dense-to-dense-medium-range-weather-forecasting-on-era5-reanalysis-1979-2017.md?metric=Training%20Time>): Lower is better; unit: TIME.

## Recorded results

| Method | Model Size | Result date | Report paper |
| --- | --- | --- | --- |
| GraphCast | 36.7 | Not recorded | 68fa7c501e209131cea8d7fa |
| Pangu-Weather | 64 | Not recorded | 68fa7c501e209131cea8d7fa |

### GraphCast

Model Size: 36.7. Result ID: 69c1123147f34ce924a90f2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d7fa.md>)

Recorded evaluation configuration: {"Grid Resolution":"0.25◦ × 0.25◦ dense grid.","Forecasting Horizon":"10 days (40 steps at 6-hour increments)","Input Variables":"2 time steps of 227 variables","Output Variables":"227 atmospheric states."}. This record does not assert independent reproduction.

### Pangu-Weather

Model Size: 64. Result ID: 69c1123147f34ce924a90f30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d7fa.md>)

Recorded evaluation configuration: {"Grid Resolution":"0.25◦ × 0.25◦ dense grid.","Forecasting Horizon":"≤7 days (28 steps at 6-hour increments)","Input Variables":"69 atmospheric variables","Output Variables":"69 atmospheric states."}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
