DLWP¶
GlobalS2S202140 GBNVIDIAPyTorch
Deep Learning Weather Prediction (DLWP) is a compact convolutional model from the University of Washington. It maps the globe onto a cubed sphere and applies a U-Net-style convolutional network on the cube faces, which avoids the polar distortion of a lat/lon grid. The version scored here consumes the two most recent ERA5 analysis frames, 6 hours apart. It forecasts seven variables with a 6-hour step: z at 1000, 700, 500, and 300 hPa, 850 hPa temperature, 2 m temperature, and total column water vapour. The cube faces map back to the 0.25° grid for verification.
Skill¶
Pick a metric and variable; hover for exact values at each lead time. Use the Region selector for continental splits, the Month selector for seasonal (DJF/MAM/JJA/SON) and per-month skill against the all-month curve, the Init hour selector for skill by initialization time, the View selector for the skill of every initial condition, and the Baseline selector to overlay persistence and climatology reference forecasts.
Evaluation¶
Deterministic · 48 initial conditions · 14-day horizon · 7 variables
Scores are latitude-weighted (cos φ) and aggregated over the initial conditions. Evaluation is done against ERA5 fetched from ARCO. Initial conditions rotate through the 00Z/06Z/12Z/18Z hours.
| Type | deterministic |
| Initial conditions | 48 (2025) |
| Initial condition source | ERA5 (ARCO) |
| Verification (ground truth) | ERA5 (ARCO) |
| Lead times | 6 h to 14 days |
| Variables scored | 7 |
| Metrics | RMSE, MAE, Log spectral distance |
| Regions | global, tropics, extra tropics, northern hemisphere, southern hemisphere, arctic, antarctica, europe, north america, north atlantic, north pacific, east asia, australia new zealand, south america, africa, asia, oceania |
Variables¶
Scored output variables (7)
| Name | Description | Unit | Group |
|---|---|---|---|
t2m |
Temperature at 2m | K | Surface |
tcwv |
Total column water vapor / precipitable water | kg m⁻² | Surface |
z300 |
Geopotential at 300 hPa | m² s⁻² | Geopotential |
z500 |
Geopotential at 500 hPa | m² s⁻² | Geopotential |
z700 |
Geopotential at 700 hPa | m² s⁻² | Geopotential |
z1000 |
Geopotential at 1000 hPa | m² s⁻² | Geopotential |
t850 |
Temperature at 850 hPa | K | Temperature |
All of the model's output variables that have ERA5 verification are scored.
Data¶
The numbers behind the plot are in eval_scores_dlwp.json, exported by
the eval recipe scorecard
(scorecard/export_scores.py --docs) -- one value per metric, variable
and lead time, in the variable's own units.
Reproducibility¶
Run and environment details
| Date scored | 2026-09-14 |
| Scores written | 2026-09-14 |
| GPUs | 8 x NVIDIA H100 80GB HBM3 (single node) |
| PyTorch | 2.12.0a0+0291f960b6.nv26.04.48445190 |
| CUDA | 13.2 |
| Python | 3.12.3 |
| Repo commit | 6a641cf5184b |
| Provenance source | run |
| Exported | 2026-09-14 |
| Locked dependencies | uv.lock @ 6a641cf5184b |
Reference¶
Weyn, J. A., Durran, D. R., and Caruana, R. (2020). Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere. Journal of Advances in Modeling Earth Systems, 12(9), e2020MS002109. doi:10.1029/2020MS002109.