added text and image

app.py

@@ -3,6 +3,7 @@ import numpy as np
 import os
 import pathlib
 from inference import infer, InferenceModel
+from text import intro
 
 # -----------------------------------------------------------------------------
 # class SatvisionDemoApp
@@ -77,6 +78,10 @@ class SatvisionDemoApp:
         with col3:
             st.image(output, use_column_width=True, caption="Reconstruction")
 
+        st.markdown(intro)
+
+        st.image('data/figures/reconstruction.png')
+
     # -------------------------------------------------------------------------
     # load_selected_image
     # -------------------------------------------------------------------------

text.py

@@ -0,0 +1,22 @@
+
+
+intro = '''Remote sensing images from NASA's fleet of Earth-observing satellites are pivotal for applications as broad as land cover mapping,
+disaster monitoring, urban planning, and environmental analysis. The potential of AI-based geospatial foundation models for performing
+visual analysis tasks on these remote sensing images has garnered significant attention. To realize that potential, the crucial first
+step is to develop foundation models – computer models that acquire competence in a broad range of tasks, which can then be specialized
+with further training for specific applications. In this case, the foundation model is based on a large-scale vision transformer model
+trained with satellite imagery.
+
+Vision transformers employ AI/deep learning techniques to fine-tune the model to answer specific science questions. Through training
+on extensive remote sensing datasets, vision transformers can learn general relationships between the spectral data given as inputs,
+as well as capture high-level visual patterns, semantics, and spatial relationships that can be leveraged for a wide range of analysis tasks.
+Trained vision transformers can handle large-scale, high-resolution data; learn global reorientations; extract robust features; and support
+multi-modal data fusion – all with improved performance.
+ 
+The Data Science Group at NASA Goddard Space Flight Center's Computational and Information Sciences and Technology Office (CISTO)
+has implemented an end-to-end workflow to generate a pre-trained vision transformer which could evolve into a foundation model. 
+A training dataset of over 2 million 128x128 pixel “chips” has been created from NASA’s Moderate Resolution Imaging Spectroradiometer (MODIS)
+surface reflectance products (MOD09).  These data were used to train a SwinV2 vision transformer that we call SatVision.
+'''
+
+