---
license: cdla-permissive-2.0
---
# Model card for granite-geospatial-wxc-downscaling
[>>Try it on Colab<< (Please select the T4 GPU runtime)](https://colab.research.google.com/github/IBM/granite-wxc/blob/main/examples/granitewxc_downscaling/notebooks/granitewxc_downscaling_inference.ipynb)
`granite-geospatial-wxc-downscaling` is a fine-tuned foundation model for the downscaling of weather and climate data. It is based on the [Prithvi WxC foundation model](https://huggingface.co/collections/ibm-nasa-geospatial/prithvi-for-weather-and-climate-6740a9252d5278b1c75b3418). `granite-geospatial-downscaling` has been used to downscale both MERRA-2 data as well as EURO-CORDEX climate simulations. The weights for the former are included here.
6x downscaling of MERRA-2 2m temperature
More information: [Code](https://github.com/IBM/granite-wxc), [base model](https://huggingface.co/collections/ibm-nasa-geospatial/prithvi-for-weather-and-climate-6740a9252d5278b1c75b3418), paper (to appear).
## Architecture
From an architecture point of view, we embed Prithvi WxC's transformer layers into a series of convolutional layers. That is, we typically increase resolution before and after the pre-trained transformer stages.
## Data - MERRA-2
As a reference and baseline how to use Prithvi WxC as well as the downscaling architecture, we have used `granite-geospatial-downscaling` for 6x downscaling of MERRA-2 2m temperature data. That is, we take MERRA-2 data of 0.5 x 0.625 degrees resolution, coarsen it by a factor of six along each axis and then apply an additional smoothing filter via a 3x3 convolution. Subsequently we fine-tune the above architecture to recover the high resolution data. The weights for this are included here.
## Further applications - EURO-CORDEX
In addition, we have used the same architecture with different hyperparameter choices for a 12x downscaling of a subset of EURO-CORDEX climate simulation.