# S2S Forecasting on S2S forecasting dataset T2m variable

Source: [S2S Forecasting on S2S forecasting dataset T2m variable](<https://www.sota2.com/research/sota/s2s-forecasting-on-s2s-forecasting-dataset-t2m-variable>)

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

Data updated: 2026-03-06T06:58:48.427Z

Evaluation of Sequence-to-Sequence (S2S) forecasting models on the T2m variable dataset, measured using Root Mean Square Error (RMSE) across specific forecasting horizons (15 to 45 days).

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 | S2S forecasting |
| Dataset (including any stated split) | S2S forecasting dataset T2m variable |
| Metric | RMSE (15 days) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [RMSE (15 days)](<https://www.sota2.com/research/sota/s2s-forecasting-on-s2s-forecasting-dataset-t2m-variable.md?metric=RMSE%20(15%20days)>): Lower is better; unit: SCALAR.

- [RMSE (20 days)](<https://www.sota2.com/research/sota/s2s-forecasting-on-s2s-forecasting-dataset-t2m-variable.md?metric=RMSE%20(20%20days)>): Lower is better; unit: SCALAR.

- [RMSE (25 days)](<https://www.sota2.com/research/sota/s2s-forecasting-on-s2s-forecasting-dataset-t2m-variable.md?metric=RMSE%20(25%20days)>): Lower is better; unit: SCALAR.

- [RMSE (30 days)](<https://www.sota2.com/research/sota/s2s-forecasting-on-s2s-forecasting-dataset-t2m-variable.md?metric=RMSE%20(30%20days)>): Lower is better; unit: SCALAR.

- [RMSE (35 days)](<https://www.sota2.com/research/sota/s2s-forecasting-on-s2s-forecasting-dataset-t2m-variable.md?metric=RMSE%20(35%20days)>): Lower is better; unit: SCALAR.

- [RMSE (40 days)](<https://www.sota2.com/research/sota/s2s-forecasting-on-s2s-forecasting-dataset-t2m-variable.md?metric=RMSE%20(40%20days)>): Lower is better; unit: SCALAR.

- [RMSE (45 days)](<https://www.sota2.com/research/sota/s2s-forecasting-on-s2s-forecasting-dataset-t2m-variable.md?metric=RMSE%20(45%20days)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | RMSE (15 days) | Result date | Report paper |
| --- | --- | --- | --- |
| TianQuan-S2S | 2.64 | Not recorded | 68fa78361e209131cea773e0 |
| XGBoost | 2.82 | Not recorded | 68fa78361e209131cea773e0 |
| Lasso | 3.05 | Not recorded | 68fa78361e209131cea773e0 |

### TianQuan-S2S

RMSE (15 days): 2.64. Result ID: 69aa7b0d6dbb7075b953b137.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78361e209131cea773e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78361e209131cea773e0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### XGBoost

RMSE (15 days): 2.82. Result ID: 69aa7b0d6dbb7075b953b138.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78361e209131cea773e0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Lasso

RMSE (15 days): 3.05. Result ID: 69aa7b0d6dbb7075b953b139.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78361e209131cea773e0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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