Update README.md

README.md

@@ -2,7 +2,6 @@
 license: openrail
 datasets:
 - DarthReca/hydro-chronos
-pipeline_tag: image-segmentation
 tags:
 - climate
 - geospatial
@@ -15,16 +14,16 @@ tags:
 library_name: transformers
 ---
 
-# ACTU for Magnitude Regression
+# ACTU for Change Detection
 
 <!-- Provide a quick summary of what the model is/does. -->
-This is ACTU for pixelwise regression of MNDWI.
+This is ACTU for change detection of thresholded absolute MNDWI difference.
 
 ## Model Details
 
 <!-- Provide a longer summary of what this model is. -->
 This architecture is a temporal UNet (with ConvLSTMs), featuring an LSTM branch to process climate timeseries and a gating mechanism. 
-It is designed to receive a timeseries of Sentinel-2 images, DEM, and timeseries of climate variables and output a single real mask of future MNDWI.
+It is designed to receive a timeseries of Sentinel-2 images, DEM, and timeseries of climate variables and output a binary mask.
 
 - **Developed by:** Daniele Rege Cambrin
 - **Model type:** ACTU
@@ -37,7 +36,7 @@ It is designed to receive a timeseries of Sentinel-2 images, DEM, and timeseries
 The model is integrated into Transformers, so you can easily load it with the following code:
 
 ```python
-AutoModel.from_pretrained("DarthReca/actu-magnitude-regression", trust_remote_code=True, revision=<model_type>)
+AutoModel.from_pretrained("DarthReca/actu-change-detection", trust_remote_code=True, revision=<model_type>)
 ```
 
 Load the model with the desired configuration with the *revision* parameter (the branches of this repo). These configurations are available:
@@ -65,4 +64,4 @@ The model is pre-trained on Landsat-5 images and fine-tuned on Sentinel-2 of Hyd
 ```
 
 ## Licensing
-The project uses third-party software. For detailed information on the licensing of each component, please see the [**NOTICE.md**](NOTICE.md) file.
+The project uses third-party software. For detailed information on the licensing of each component, please see the [**NOTICE.md**](NOTICE.md) file.