Update README.md

README.md

@@ -4,16 +4,15 @@ library_name: keras
 
 ## Model description
 
-This model identifies contrails in satellite images. It takes pre-processed .npy files (images) as its inputs, and returns a "mask" image showing only the contrails overlayed on the same area. 
-We used a UNet model architecture ...
+This UNet model identifies contrails in satellite images. It takes pre-processed .npy files (images) from the OpenContrails dataset [here](https://arxiv.org/abs/2304.02122) as its inputs, and returns a "mask" image showing only the contrails overlayed on the same area. 
+We achieve a Mean IOU of 0.6951 on the validation set, which is considered very good.
 
+## Intended uses
 
-
-## Intended uses & limitations
-
-We hope that data scientists and researchers focused on reducing contrails (towards the goal of reducing global warming) will use this model to improve their work. 
-There are current efforts underway to develop software that re-routes planes to avoid contrails. 
-Researchers are building models to predict contrails based on atmospheric conditions and other factors, but they need a way to validate those predictions.
+We hope that data scientists and researchers focused on reducing contrails will use this model to improve their work. 
+There are current efforts underway to develop models that predict contrails, but one major limiting factor for these efforts is that image labeling is still done by humans (labeled images are needed in order to validate contrail prediction models).
+Labeling contrails in images is a difficult and expensive task - our model helps researchers efficiently segment satellite images so they can validate and improve contrail prediction models.
+To learn more about our work, visit [our website](contrailsentinel.com).
 
 ## How to Get Started with the Model