Update README.md

README.md

@@ -1,3 +1,49 @@
----
-license: mit
----
+---
+license: mit
+---
+
+## Model Card for UNet-6depth-shuffle: `venkatesh-thiru/s2l8h-UNet-6depth-shuffle`
+
+### Model Description
+
+The UNet-6depth-shuffle model harmonizes Landsat-8 and Sentinel-2 imagery by improving the spatial resolution of Landsat-8 images. This model uses Landsat-8 multispectral and pan-chromatic images to produce outputs that match the Sentinel-2's spectral and spatial characteristics.
+
+### Model Architecture
+
+This UNet model features 6 depth levels and incorporates a shuffling mechanism to enhance image resolution and spectral accuracy. The depth and shuffling operations are tailored to achieve high-quality transformations, ensuring the output images closely resemble Sentinel-2 data.
+
+### Usage
+
+```python
+from transformers import AutoModel
+
+# Load the UNet-6depth-shuffle model
+model = AutoModel.from_pretrained("venkatesh-thiru/s2l8h-UNet-6depth-shuffle", trust_remote_code=True)
+
+# Harmonize Landsat-8 images
+l8up = model(l8MS, l8pan)
+```
+### Where:
+
+l8MS - Landsat Multispectral images (L2 Reflectances)
+
+l8pan - Landsat Pan-Chromatic images (L1 Reflectances)
+
+### Applications
+Water quality assessment
+
+Urban planning
+
+Climate monitoring
+
+Disaster response
+
+Infrastructure oversight
+
+Agricultural surveillance
+
+### Limitations
+Minor limitations may arise in regions with different spectral properties or under extreme environmental conditions.
+
+### Reference
+For more details, refer to the publication: 10.1016/j.isprsjprs.2024.04.026