Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Mesh
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916368232742912 |
|---|---|
| author | Karlbauer, Matthias Cresswell-Clay, Nathaniel Durran, Dale R. Moreno, Raul A. Kurth, Thorsten Bonev, Boris Brenowitz, Noah Butz, Martin V. |
| author_facet | Karlbauer, Matthias Cresswell-Clay, Nathaniel Durran, Dale R. Moreno, Raul A. Kurth, Thorsten Bonev, Boris Brenowitz, Noah Butz, Martin V. |
| contents | We present a parsimonious deep learning weather prediction model to forecast seven atmospheric variables with 3-h time resolution for up to one-year lead times on a 110-km global mesh using the Hierarchical Equal Area isoLatitude Pixelization (HEALPix). In comparison to state-of-the-art (SOTA) machine learning (ML) weather forecast models, such as Pangu-Weather and GraphCast, our DLWP-HPX model uses coarser resolution and far fewer prognostic variables. Yet, at one-week lead times, its skill is only about one day behind both SOTA ML forecast models and the SOTA numerical weather prediction model from the European Centre for Medium-Range Weather Forecasts. We report several improvements in model design, including switching from the cubed sphere to the HEALPix mesh, inverting the channel depth of the U-Net, and introducing gated recurrent units (GRU) on each level of the U-Net hierarchy. The consistent east-west orientation of all cells on the HEALPix mesh facilitates the development of location-invariant convolution kernels that successfully propagate weather patterns across the globe without requiring separate kernels for the polar and equatorial faces of the cube sphere. Without any loss of spectral power after the first two days, the model can be unrolled autoregressively for hundreds of steps into the future to generate realistic states of the atmosphere that respect seasonal trends, as showcased in one-year simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_06253 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Mesh Karlbauer, Matthias Cresswell-Clay, Nathaniel Durran, Dale R. Moreno, Raul A. Kurth, Thorsten Bonev, Boris Brenowitz, Noah Butz, Martin V. Atmospheric and Oceanic Physics Machine Learning We present a parsimonious deep learning weather prediction model to forecast seven atmospheric variables with 3-h time resolution for up to one-year lead times on a 110-km global mesh using the Hierarchical Equal Area isoLatitude Pixelization (HEALPix). In comparison to state-of-the-art (SOTA) machine learning (ML) weather forecast models, such as Pangu-Weather and GraphCast, our DLWP-HPX model uses coarser resolution and far fewer prognostic variables. Yet, at one-week lead times, its skill is only about one day behind both SOTA ML forecast models and the SOTA numerical weather prediction model from the European Centre for Medium-Range Weather Forecasts. We report several improvements in model design, including switching from the cubed sphere to the HEALPix mesh, inverting the channel depth of the U-Net, and introducing gated recurrent units (GRU) on each level of the U-Net hierarchy. The consistent east-west orientation of all cells on the HEALPix mesh facilitates the development of location-invariant convolution kernels that successfully propagate weather patterns across the globe without requiring separate kernels for the polar and equatorial faces of the cube sphere. Without any loss of spectral power after the first two days, the model can be unrolled autoregressively for hundreds of steps into the future to generate realistic states of the atmosphere that respect seasonal trends, as showcased in one-year simulations. |
| title | Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Mesh |
| topic | Atmospheric and Oceanic Physics Machine Learning |
| url | https://arxiv.org/abs/2311.06253 |