Spaces:
No application file
No application file
Update README.md
Browse files
README.md
CHANGED
@@ -7,28 +7,16 @@ sdk: streamlit
|
|
7 |
pinned: false
|
8 |
license: apache-2.0
|
9 |
---
|
|
|
10 |
|
11 |
-
|
12 |
-
Observations, using large-scale satellite and remote sensing data, including
|
13 |
-
the Harmonized Landsat and Sentinel-2 ([HLS](https://hls.gsfc.nasa.gov/)) data. By embracing the principles of
|
14 |
-
open AI and open science, both organizations are actively contributing to the
|
15 |
-
global mission of promoting knowledge sharing and accelerating innovations in
|
16 |
-
addressing critical environmental challenges. With Hugging Face's platform,
|
17 |
-
they simplify geospatial model training and deployment, making it accessible
|
18 |
-
for open science users, startups, and enterprises on multi-cloud AI platforms
|
19 |
-
like [watsonx](https://www.ibm.com/watsonx). Additionally, Hugging Face enables easy sharing of the pipelines of the model family, which
|
20 |
-
our team calls [Prithvi](https://huggingface.co/ibm-nasa-geospatial/Prithvi-100M), within the community, fostering global collaboration and engagement. More details on Prithvi can be found
|
21 |
-
in the joint IBM NASA [technical paper](https://arxiv.org/abs/2310.18660). For more enterprise-ready finetuned versions of the Prithvi model, please visit the [IBM Granite Hugging Face page](https://huggingface.co/collections/ibm-granite/granite-geospatial-models-667dacfed21bdcf60a8bc982).
|
22 |
|
|
|
|
|
|
|
23 |
|
24 |
-
|
25 |
-
<img class="w-full h-48 object-cover mb-2 bg-gray-300 rounded-md" src="https://img.youtube.com/vi/9bU9eJxFwWc/maxresdefault.jpg" alt="Watch Prithvi end to end demo" width="240" height="180" border="10" />
|
26 |
-
<div class="underline">Watch Prithvi end to end demo</div>
|
27 |
-
</a>
|
28 |
|
29 |
-
|
30 |
-
[](https://youtu.be/9bU9eJxFwWc)
|
31 |
-
-->
|
32 |
|
33 |
-
|
34 |
-
|
|
|
7 |
pinned: false
|
8 |
license: apache-2.0
|
9 |
---
|
10 |
+
IBM and NASA :heart: Open Source AI
|
11 |
|
12 |
+
IBM and NASA have teamed up to create a family of AI foundation models for Earth called Prithvi. These geospatial foundation models make AI accessible for open science users, startups, and enterprises by simplifying model training and deployment.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
+
Three foundation models have been released to date: Prithvi-EO-1.0 [https://huggingface.co/ibm-nasa-geospatial/Prithvi-100M] and Prithvi-EO-2.0 [https://huggingface.co/ibm-nasa-geospatial/Prithvi-EO-2.0-300M] which uses earth observation data from NASA’s Harmonized Landsat and Sentinel-2 (HLS), and Prithvi-WxC-1.0 [https://huggingface.co/Prithvi-WxC] which uses weather and climate data from NASA’s MERRA-2.
|
15 |
+
Technical papers for the Prithvi-EO models can be found here [https://huggingface.co/collections/ibm-nasa-geospatial/prithvi-for-earth-observation-6740a7a81883466bf41d93d6] and the Prithvi-WxC model here [https://huggingface.co/collections/ibm-nasa-geospatial/prithvi-for-weather-and-climate-6740a9252d5278b1c75b3418]. Each foundation model has been finetuned for several tasks using IBM TerraTorch [https://github.com/IBM/terratorch] – model cards, checkpoints and code to get you started with the finetuned models can be found in the links above.
|
16 |
+
IBM has also developed enterprise-ready finetuned versions of the Prithvi models, which are named Granite. Please visit the IBM Granite Hugging Face page [https://huggingface.co/ibm-granite] for more information.
|
17 |
|
18 |
+
The Prithvi models would not have been possible to develop without exceptional collaborators. This includes Forschungszentrum Jülich [https://www.fz-juelich.de/en] who helped co-develop Prithvi-EO-2.0 and Oak Ridge National Lab [https://www.ornl.gov/] who helped co-develop Prithvi-WxC-1.0.
|
|
|
|
|
|
|
19 |
|
20 |
+
By embracing the principles of open AI and open science, IBM and NASA are actively contributing to the global mission of promoting knowledge sharing and accelerating innovations. We hope that the AI community find our efforts useful and that our models help fuel progress in addressing critical environmental challenges.
|
|
|
|
|
21 |
|
22 |
+
If you have any questions, please visit our discussions page.
|
|