Prithvi WxC: Foundation Model for Weather and Climate

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schmude, Johannes, Roy, Sujit, Trojak, Will, Jakubik, Johannes, Civitarese, Daniel Salles, Singh, Shraddha, Kuehnert, Julian, Ankur, Kumar, Gupta, Aman, Phillips, Christopher E, Kienzler, Romeo, Szwarcman, Daniela, Gaur, Vishal, Shinde, Rajat, Lal, Rohit, Da Silva, Arlindo, Diaz, Jorge Luis Guevara, Jones, Anne, Pfreundschuh, Simon, Lin, Amy, Sheshadri, Aditi, Nair, Udaysankar, Anantharaj, Valentine, Hamann, Hendrik, Watson, Campbell, Maskey, Manil, Lee, Tsengdar J, Moreno, Juan Bernabe, Ramachandran, Rahul
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917780453851136
author Schmude, Johannes
Roy, Sujit
Trojak, Will
Jakubik, Johannes
Civitarese, Daniel Salles
Singh, Shraddha
Kuehnert, Julian
Ankur, Kumar
Gupta, Aman
Phillips, Christopher E
Kienzler, Romeo
Szwarcman, Daniela
Gaur, Vishal
Shinde, Rajat
Lal, Rohit
Da Silva, Arlindo
Diaz, Jorge Luis Guevara
Jones, Anne
Pfreundschuh, Simon
Lin, Amy
Sheshadri, Aditi
Nair, Udaysankar
Anantharaj, Valentine
Hamann, Hendrik
Watson, Campbell
Maskey, Manil
Lee, Tsengdar J
Moreno, Juan Bernabe
Ramachandran, Rahul
author_facet Schmude, Johannes
Roy, Sujit
Trojak, Will
Jakubik, Johannes
Civitarese, Daniel Salles
Singh, Shraddha
Kuehnert, Julian
Ankur, Kumar
Gupta, Aman
Phillips, Christopher E
Kienzler, Romeo
Szwarcman, Daniela
Gaur, Vishal
Shinde, Rajat
Lal, Rohit
Da Silva, Arlindo
Diaz, Jorge Luis Guevara
Jones, Anne
Pfreundschuh, Simon
Lin, Amy
Sheshadri, Aditi
Nair, Udaysankar
Anantharaj, Valentine
Hamann, Hendrik
Watson, Campbell
Maskey, Manil
Lee, Tsengdar J
Moreno, Juan Bernabe
Ramachandran, Rahul
contents Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecasting, downscaling, or nowcasting. While the parallel developments in the AI literature focus on foundation models -- models that can be effectively tuned to address multiple, different use cases -- the developments on the weather and climate side largely focus on single-use cases with particular emphasis on mid-range forecasting. We close this gap by introducing Prithvi WxC, a 2.3 billion parameter foundation model developed using 160 variables from the Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). Prithvi WxC employs an encoder-decoder-based architecture, incorporating concepts from various recent transformer models to effectively capture both regional and global dependencies in the input data. The model has been designed to accommodate large token counts to model weather phenomena in different topologies at fine resolutions. Furthermore, it is trained with a mixed objective that combines the paradigms of masked reconstruction with forecasting. We test the model on a set of challenging downstream tasks namely: Autoregressive rollout forecasting, Downscaling, Gravity wave flux parameterization, and Extreme events estimation. The pretrained model with 2.3 billion parameters, along with the associated fine-tuning workflows, has been publicly released as an open-source contribution via Hugging Face.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13598
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prithvi WxC: Foundation Model for Weather and Climate
Schmude, Johannes
Roy, Sujit
Trojak, Will
Jakubik, Johannes
Civitarese, Daniel Salles
Singh, Shraddha
Kuehnert, Julian
Ankur, Kumar
Gupta, Aman
Phillips, Christopher E
Kienzler, Romeo
Szwarcman, Daniela
Gaur, Vishal
Shinde, Rajat
Lal, Rohit
Da Silva, Arlindo
Diaz, Jorge Luis Guevara
Jones, Anne
Pfreundschuh, Simon
Lin, Amy
Sheshadri, Aditi
Nair, Udaysankar
Anantharaj, Valentine
Hamann, Hendrik
Watson, Campbell
Maskey, Manil
Lee, Tsengdar J
Moreno, Juan Bernabe
Ramachandran, Rahul
Machine Learning
Atmospheric and Oceanic Physics
Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecasting, downscaling, or nowcasting. While the parallel developments in the AI literature focus on foundation models -- models that can be effectively tuned to address multiple, different use cases -- the developments on the weather and climate side largely focus on single-use cases with particular emphasis on mid-range forecasting. We close this gap by introducing Prithvi WxC, a 2.3 billion parameter foundation model developed using 160 variables from the Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). Prithvi WxC employs an encoder-decoder-based architecture, incorporating concepts from various recent transformer models to effectively capture both regional and global dependencies in the input data. The model has been designed to accommodate large token counts to model weather phenomena in different topologies at fine resolutions. Furthermore, it is trained with a mixed objective that combines the paradigms of masked reconstruction with forecasting. We test the model on a set of challenging downstream tasks namely: Autoregressive rollout forecasting, Downscaling, Gravity wave flux parameterization, and Extreme events estimation. The pretrained model with 2.3 billion parameters, along with the associated fine-tuning workflows, has been publicly released as an open-source contribution via Hugging Face.
title Prithvi WxC: Foundation Model for Weather and Climate
topic Machine Learning
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2409.13598