---
title: README
emoji: 📈
colorFrom: red
colorTo: blue
sdk: static
pinned: false
---
NASA and IBM have teamed up to create an AI Foundation Model for Weather and Climate - [Prithvi WxC](https://huggingface.co/Prithvi-WxC/prithvi.wxc.2300m.v1), using [MERRA-2](https://gmao.gsfc.nasa.gov/reanalysis/MERRA-2/) data.
By embracing the principles of open science, both organizations are actively contributing to the global mission of promoting knowledge sharing and accelerating 
innovations in addressing critical environmental challenges. With Hugging Face’s platform, they simplify model training and deployment, making it accessible for 
open science users, startups, and enterprises on multi-cloud AI platforms like [watsonx](https://www.ibm.com/watsonx). 
Additionally, Hugging Face enables easy sharing of the pipelines of the model family, which our team calls Prithvi WxC, within the community, fostering global 
collaboration and engagement.
Prithvi WxC has been fine-tuned for several tasks including climate downscaling (released as part of the enterprise-grade [IBM granite](https://huggingface.co/ibm-granite) family of models) and 
gravity wave parameterization. More details on Prithvi WxC can be found in the joint [IBM NASA technical paper](https://arxiv.org/abs/2409.13598).

Current downstreams tasks of PrithviWxC are (please feel free to submit a PR if you want to add yours):  
[Downscaling](https://huggingface.co/ibm-granite/granite-geospatial-wxc-downscaling) (IBM Granite Model) <b><i>>>>[Try it on Colab](https://colab.research.google.com/github/IBM/granite-wxc/blob/4d14cd19ec86ae1a5d32c311e6362fb1d42ff693/examples/granitewxc_downscaling/notebooks/granitewxc_downscaling_inference.ipynb)<<<</i></b> (Please select the T4 GPU runtime)  
[Gravity Wave](https://github.com/NASA-IMPACT/gravity-wave-finetuning)  


More information:[Paper](https://arxiv.org/abs/2409.13598), [Code](https://github.com/NASA-IMPACT/Prithvi-WxC), [Model V1](https://huggingface.co/Prithvi-WxC/prithvi.wxc.2300m.v1)
PRs: [prithvi-weather-climate-foundation-model (NASA)](https://www.earthdata.nasa.gov/learn/blog/prithvi-weather-climate-foundation-model-background-benefits), [weather-climate-foundation-model (IBM)](https://research.ibm.com/blog/weather-climate-foundation-model)
[nasa-ibm-weather-climate-foundation-model (NASA)](https://www.earthdata.nasa.gov/learn/blog/nasa-ibm-weather-climate-foundation-model)

<div style="display: flex; justify-content: center;">

<b>Gravity Wave</b>
<img src="https://huggingface.co/Prithvi-WxC/Gravity_wave_Parameterization/resolve/20f8a120752b4e48364a2a606d6d2db26b2aa8b9/prithvi_downstream_gwflux_animation.gif" alt="Gravity Wave" width="512"/>

<b>Hurricane Ida - Zero-Shot Rollout</b>
<img src="https://huggingface.co/datasets/Prithvi-WxC/Hurricane/resolve/6edc7c6838d59c1694755508917dce7a203fb9e8/2021C4Ida_2021082700_ground_truth_prediction.gif" alt="Hurricane Ida" width="475"/>

</div>

<!-- Prithvi WxC is a 2.3 billion parameter model trained on 160 different variables from MERRA-2 data. It has been pretrained on both forecasting and masked
reconstruction objectives. I.e.~the model is capable of reconstructing atmospheric state from partial information as well as propagating state into the
future. The model takes data from two timestamps as input and generates a single, possibly future, timestamp as output. Currently Prithvi WxC comes in two flavors:
- `prithvi.wxc.2300m.v1` has been pretrained with a 50% masking ratio. The time delta between input timestamps is variable as is the forecast lead time.
  During pretraining, the input delta was chosen from [-3, -6, -9, -12] hours while the forecast lead time was chosen from [0, 6, 12, 24] hours. We recommend using
  `prithvi.wxc.2300m.v1` for generic use cases that do not focus on forecasting.
- `prithvi.wxc.rollout.2300m.v1` has been through further training cycles to be optimzed for autoregressive rollout. Here, we restricted the input delta
  as well as the lead time to 6 hours. We recommend using `prithvi.wxc.rollout.2300m.v1` for forecasting applications. -->