# Spatiotemporal Prediction on ERA5 Global Source: [Spatiotemporal Prediction on ERA5 Global]() Collection index: [llms.txt]() Data updated: 2026-03-18T06:51:22.376Z Evaluation of models performing spatiotemporal prediction on the ERA5 Global dataset, assessed using metrics including Root Mean Square Error (RMSE), Structural Similarity Index (SSIM), and Peak Signal-to-Noise Ratio (PSNR). 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 | Spatiotemporal Prediction | | Dataset (including any stated split) | ERA5 Global | | Metric | RMSE | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 14 of 14 | | 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](): Lower is better; unit: SCALAR. - [SSIM](): Higher is better; unit: PERCENT. - [PSNR](): Higher is better; unit: SCALAR. ## Recorded results | Method | RMSE | Result date | Report paper | | --- | --- | --- | --- | | OMNIFLOW | 0.552 | Not recorded | 69ba31730636e5bf4afc0682 | | TAU | 0.602 | Not recorded | 69ba31730636e5bf4afc0682 | | EarthFarseer | 0.615 | Not recorded | 69ba31730636e5bf4afc0682 | | FNO | 0.621 | Not recorded | 69ba31730636e5bf4afc0682 | | PastNet | 0.642 | Not recorded | 69ba31730636e5bf4afc0682 | | Earthformer | 0.654 | Not recorded | 69ba31730636e5bf4afc0682 | | LSM | 0.688 | Not recorded | 69ba31730636e5bf4afc0682 | | SimVP | 0.722 | Not recorded | 69ba31730636e5bf4afc0682 | | PredRNN | 0.845 | Not recorded | 69ba31730636e5bf4afc0682 | | ConvLSTM | 0.921 | Not recorded | 69ba31730636e5bf4afc0682 | | SwinT-Base | 0.982 | Not recorded | 69ba31730636e5bf4afc0682 | | UNet | 1.055 | Not recorded | 69ba31730636e5bf4afc0682 | | ViT-Base | 1.182 | Not recorded | 69ba31730636e5bf4afc0682 | | ResNet | 1.245 | Not recorded | 69ba31730636e5bf4afc0682 | ### OMNIFLOW RMSE: 0.552. Result ID: 69ba4a2947f34ce924a385fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Proposed","Training Strategy":"Training-free"}. This record does not assert independent reproduction. ### TAU RMSE: 0.602. Result ID: 69ba4a2947f34ce924a385f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"S-T Predict","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### EarthFarseer RMSE: 0.615. Result ID: 69ba4a2947f34ce924a385fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Sci-ML","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### FNO RMSE: 0.621. Result ID: 69ba4a2947f34ce924a385f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Sci-ML","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### PastNet RMSE: 0.642. Result ID: 69ba4a2947f34ce924a385fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Sci-ML","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### Earthformer RMSE: 0.654. Result ID: 69ba4a2947f34ce924a385f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"S-T Predict","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### LSM RMSE: 0.688. Result ID: 69ba4a2947f34ce924a385f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Sci-ML","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### SimVP RMSE: 0.722. Result ID: 69ba4a2947f34ce924a385f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"S-T Predict","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### PredRNN RMSE: 0.845. Result ID: 69ba4a2947f34ce924a385f4. [Reporting paper]() Recorded evaluation configuration: {"Category":"S-T Predict","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### ConvLSTM RMSE: 0.921. Result ID: 69ba4a2947f34ce924a385f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"S-T Predict","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### SwinT-Base RMSE: 0.982. Result ID: 69ba4a2947f34ce924a385f2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Vision","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### UNet RMSE: 1.055. Result ID: 69ba4a2947f34ce924a385f0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Vision","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### ViT-Base RMSE: 1.182. Result ID: 69ba4a2947f34ce924a385f1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Vision","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. ### ResNet RMSE: 1.245. Result ID: 69ba4a2947f34ce924a385ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Vision","Training Strategy":"End-to-end"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.