# Steady-state Wind Flow Prediction on Wind Flow Prediction Dataset (test)

Source: [Steady-state Wind Flow Prediction on Wind Flow Prediction Dataset (test)](<https://www.sota2.com/research/sota/steady-state-wind-flow-prediction-on-wind-flow-prediction-dataset-test>)

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

Data updated: 2026-03-27T13:35:51.709Z

Evaluation of models performing Steady-state Wind Flow Prediction on the test split of the Wind Flow Prediction Dataset, focusing on resource utilization metrics such as training time, VRAM requirement, and inference speed.

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 | Steady-state Wind Flow Prediction |
| Dataset (including any stated split) | Wind Flow Prediction Dataset (test) |
| Metric | Training Time (Epoch) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [Training Time (Epoch)](<https://www.sota2.com/research/sota/steady-state-wind-flow-prediction-on-wind-flow-prediction-dataset-test.md?metric=Training%20Time%20(Epoch)>): Lower is better; unit: TIME.

- [Training VRAM (GB)](<https://www.sota2.com/research/sota/steady-state-wind-flow-prediction-on-wind-flow-prediction-dataset-test.md?metric=Training%20VRAM%20(GB)>): Lower is better; unit: SIZE.

- [Inference Time (Sample)](<https://www.sota2.com/research/sota/steady-state-wind-flow-prediction-on-wind-flow-prediction-dataset-test.md?metric=Inference%20Time%20(Sample)>): Lower is better; unit: TIME.

## Recorded results

| Method | Training Time (Epoch) | Result date | Report paper |
| --- | --- | --- | --- |
| AB-UPT | 7.5 | Not recorded | 69c60f3e0636e5bf4afc873b |
| AB-SWIFT | 8 | Not recorded | 69c60f3e0636e5bf4afc873b |
| GAOT | 17 | Not recorded | 69c60f3e0636e5bf4afc873b |
| Transolver | 27 | Not recorded | 69c60f3e0636e5bf4afc873b |
| BSMGN | 90 | Not recorded | 69c60f3e0636e5bf4afc873b |

### AB-UPT

Training Time (Epoch): 7.5. Result ID: 69c687a447f34ce924b0b11b.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f3e0636e5bf4afc873b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c231e209131cea8ca68.md>)

Recorded evaluation configuration: {"# of trainable parameters":"6.5M","Hardware":"Nvidia A100 40Gb GPU","Batch size":"1"}. This record does not assert independent reproduction.

### AB-SWIFT

Training Time (Epoch): 8. Result ID: 69c687a447f34ce924b0b11a.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f3e0636e5bf4afc873b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60f3e0636e5bf4afc873b.md>)

Recorded evaluation configuration: {"# of trainable parameters":"6.5M","Hardware":"Nvidia A100 40Gb GPU","Batch size":"1"}. This record does not assert independent reproduction.

### GAOT

Training Time (Epoch): 17. Result ID: 69c687a447f34ce924b0b11c.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f3e0636e5bf4afc873b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78de1e209131cea7ae77.md>)

Recorded evaluation configuration: {"# of trainable parameters":"6.6M","Hardware":"Nvidia A100 40Gb GPU","Batch size":"1"}. This record does not assert independent reproduction.

### Transolver

Training Time (Epoch): 27. Result ID: 69c687a447f34ce924b0b11d.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f3e0636e5bf4afc873b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5bd41e209131ce9cbd98.md>)

Recorded evaluation configuration: {"# of trainable parameters":"6.0M","Hardware":"Nvidia A100 40Gb GPU","Batch size":"1"}. This record does not assert independent reproduction.

### BSMGN

Training Time (Epoch): 90. Result ID: 69c687a447f34ce924b0b11e.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f3e0636e5bf4afc873b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ed11e209131cea42638.md>)

Recorded evaluation configuration: {"# of trainable parameters":"0.4M","Hardware":"Nvidia A100 40Gb GPU","Batch size":"1"}. This record does not assert independent reproduction.

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