# Temperature Forecasting on set 2023 (test)

Source: [Temperature Forecasting on set 2023 (test)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test>)

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

Data updated: 2026-04-28T06:39:59.968Z

Evaluation of Temperature Forecasting performance on the test split of the set 2023 dataset, measured using various error metrics indexed by forecast horizon (1 to 48 hours) and overall Mean Error.

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 | Temperature Forecasting |
| Dataset (including any stated split) | set 2023 (test) |
| Metric | Error (1h) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 16 of 16 |
| 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

- [Error (1h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(1h)>): Lower is better; unit: SCALAR.

- [Error (2h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(2h)>): Lower is better; unit: SCALAR.

- [Error (4h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(4h)>): Lower is better; unit: SCALAR.

- [Error (8h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(8h)>): Lower is better; unit: SCALAR.

- [Error (12h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(12h)>): Lower is better; unit: SCALAR.

- [Error (18h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(18h)>): Lower is better; unit: SCALAR.

- [Error (24h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(24h)>): Lower is better; unit: SCALAR.

- [Error (36h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(36h)>): Lower is better; unit: SCALAR.

- [Error (48h)](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Error%20(48h)>): Lower is better; unit: SCALAR.

- [Mean Error](<https://www.sota2.com/research/sota/temperature-forecasting-on-set-2023-test.md?metric=Mean%20Error>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Error (1h) | Result date | Report paper |
| --- | --- | --- | --- |
| Multi-modal Transformer | 0.7709 | Not recorded | 68fa4b761e209131ce9462ec |
| Multi-modal Transformer | 0.785 | Not recorded | 68fa4b761e209131ce9462ec |
| Multi-modal Transformer | 0.789 | Not recorded | 68fa4b761e209131ce9462ec |
| Multi-modal Transformer | 0.8453 | Not recorded | 68fa4b761e209131ce9462ec |
| MLP | 0.8586 | Not recorded | 68fa4b761e209131ce9462ec |
| Persistence | 1.1285 | Not recorded | 68fa4b761e209131ce9462ec |
| MLP | 1.5194 | Not recorded | 68fa4b761e209131ce9462ec |
| MLP | 1.5682 | Not recorded | 68fa4b761e209131ce9462ec |
| GNN | 1.6763 | Not recorded | 68fa4b761e209131ce9462ec |
| Interpolation | 1.6824 | Not recorded | 68fa4b761e209131ce9462ec |
| MLP | 1.6848 | Not recorded | 68fa4b761e209131ce9462ec |
| GNN | 1.7077 | Not recorded | 68fa4b761e209131ce9462ec |
| GNN | 1.7567 | Not recorded | 68fa4b761e209131ce9462ec |
| Interpolation | 1.7706 | Not recorded | 68fa4b761e209131ce9462ec |
| GNN | 1.7773 | Not recorded | 68fa4b761e209131ce9462ec |
| Interpolation | 2.0285 | Not recorded | 68fa4b761e209131ce9462ec |

### Multi-modal Transformer

Error (1h): 0.7709. Result ID: 69f0551e47f34ce924d5830a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"HRRR-A"}. This record does not assert independent reproduction.

### Multi-modal Transformer

Error (1h): 0.785. Result ID: 69f0551e47f34ce924d58308.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"ERA5"}. This record does not assert independent reproduction.

### Multi-modal Transformer

Error (1h): 0.789. Result ID: 69f0551e47f34ce924d58309.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"HRRR-F"}. This record does not assert independent reproduction.

### Multi-modal Transformer

Error (1h): 0.8453. Result ID: 69f0551e47f34ce924d58307.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"-"}. This record does not assert independent reproduction.

### MLP

Error (1h): 0.8586. Result ID: 69f0551e47f34ce924d582ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"-"}. This record does not assert independent reproduction.

### Persistence

Error (1h): 1.1285. Result ID: 69f0551e47f34ce924d582fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"-"}. This record does not assert independent reproduction.

### MLP

Error (1h): 1.5194. Result ID: 69f0551e47f34ce924d58302.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"HRRR-A"}. This record does not assert independent reproduction.

### MLP

Error (1h): 1.5682. Result ID: 69f0551e47f34ce924d58301.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"HRRR-F"}. This record does not assert independent reproduction.

### GNN

Error (1h): 1.6763. Result ID: 69f0551e47f34ce924d58303.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5a301e209131ce9bdc8e.md>)

Recorded evaluation configuration: {"ExternalDataset":"-"}. This record does not assert independent reproduction.

### Interpolation

Error (1h): 1.6824. Result ID: 69f0551e47f34ce924d582fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"HRRR-A"}. This record does not assert independent reproduction.

### MLP

Error (1h): 1.6848. Result ID: 69f0551e47f34ce924d58300.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"ERA5"}. This record does not assert independent reproduction.

### GNN

Error (1h): 1.7077. Result ID: 69f0551e47f34ce924d58306.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5a301e209131ce9bdc8e.md>)

Recorded evaluation configuration: {"ExternalDataset":"HRRR-A"}. This record does not assert independent reproduction.

### GNN

Error (1h): 1.7567. Result ID: 69f0551e47f34ce924d58304.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5a301e209131ce9bdc8e.md>)

Recorded evaluation configuration: {"ExternalDataset":"ERA5"}. This record does not assert independent reproduction.

### Interpolation

Error (1h): 1.7706. Result ID: 69f0551e47f34ce924d582fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"HRRR-F"}. This record does not assert independent reproduction.

### GNN

Error (1h): 1.7773. Result ID: 69f0551e47f34ce924d58305.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5a301e209131ce9bdc8e.md>)

Recorded evaluation configuration: {"ExternalDataset":"HRRR-F"}. This record does not assert independent reproduction.

### Interpolation

Error (1h): 2.0285. Result ID: 69f0551e47f34ce924d582fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa4b761e209131ce9462ec.md>)

Recorded evaluation configuration: {"ExternalDataset":"ERA5"}. This record does not assert independent reproduction.

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