Update README.md

Updated for latex syntax

README.md

@@ -9,7 +9,7 @@ license: apache-2.0
 
 [<b><i>>>Try it on Colab<<</i></b>](https://colab.research.google.com/github/ibm-granite/granite-geospatial-land-surface-temperature/blob/main/notebooks/1_getting_started.ipynb)
 
-The granite-geospatial-land-surface-temperature model is a fine-tuned geospatial foundation model for predicting the land surface temperature (LST) using satellite imagery along with climate statistics. Excessive urban heat has been shown to have adverse effects across a range of dimensions, including increased energy demand, severe heat stress on human and non-human populations, and worse air and water quality. As global cities become more populous with increasing rates of urbanization, it is crucial to model and understand urban temperature dynamics and its impacts. Characterizing and mitigating Urban Heat Island (UHI) effects is dependent on the availability of high-resolution (spatial and temporal) LST data. This model is fine-tuned using a combination of Harmonised Landsat Sentinel-2 [(HLS L30)](https://hls.gsfc.nasa.gov/products-description/l30/) and ECMWF Reanalysis v5 [(ERA5-Land)](https://cds.climate.copernicus.eu/datasets/reanalysis-era5-land?tab=overview) $2 m$ near-surface air temperature ($T_{2m}$) datasets across 28 global cities from varying hydroclimatic zones for the period 2013-2023. 
+The granite-geospatial-land-surface-temperature model is a fine-tuned geospatial foundation model for predicting the land surface temperature (LST) using satellite imagery along with climate statistics. Excessive urban heat has been shown to have adverse effects across a range of dimensions, including increased energy demand, severe heat stress on human and non-human populations, and worse air and water quality. As global cities become more populous with increasing rates of urbanization, it is crucial to model and understand urban temperature dynamics and its impacts. Characterizing and mitigating Urban Heat Island (UHI) effects is dependent on the availability of high-resolution (spatial and temporal) LST data. This model is fine-tuned using a combination of Harmonised Landsat Sentinel-2 [(HLS L30)](https://hls.gsfc.nasa.gov/products-description/l30/) and ECMWF Reanalysis v5 [(ERA5-Land)](https://cds.climate.copernicus.eu/datasets/reanalysis-era5-land?tab=overview) 2m near-surface air temperature (T2m) datasets across 28 global cities from varying hydroclimatic zones for the period 2013-2023. 
 
 <p align="center" width="100%">
 <img src="cities_map2.png" width="800">
@@ -45,7 +45,7 @@ For more details, check out the tutorials below which guide the user through the
 
 ## Model Description
 
-The granite-geospatial-land-surface-temperature model is a geospatial foundation model that has been fine-tuned using HLS L30 and ERA5-Land data to predict LST at a high spatial resolution ($30 m$) and high temporal frequency (hourly). The fine-tuned granite-geospatial-land-surface-temperature model incorporates a Shifted Windowing (SWIN) Transformer architecture and leverages the IBM Earth Observation Foundation Model, “Prithvi-SWIN-L” as the base foundation model. For fine-tuning, we used a SWIN backbone with unfrozen pre-trained weights for the encoder and a decoder that comprised of a Unified Perceptual Parsing for Scene Understanding (UperNet) regression head with an auxiliary 1-layer Convolution regression head and a Linear final activation layer. 
+The granite-geospatial-land-surface-temperature model is a geospatial foundation model that has been fine-tuned using HLS L30 and ERA5-Land data to predict LST at a high spatial resolution (30m) and high temporal frequency (hourly). The fine-tuned granite-geospatial-land-surface-temperature model incorporates a Shifted Windowing (SWIN) Transformer architecture and leverages the IBM Earth Observation Foundation Model, “Prithvi-SWIN-L” as the base foundation model. For fine-tuning, we used a SWIN backbone with unfrozen pre-trained weights for the encoder and a decoder that comprised of a Unified Perceptual Parsing for Scene Understanding (UperNet) regression head with an auxiliary 1-layer Convolution regression head and a Linear final activation layer. 
 
 More details on the base foundation model can be found in this [paper](https://arxiv.org/abs/2310.18660)
 
@@ -59,14 +59,14 @@ For more details on this approach, refer to:
 
 ## Model Releases (along with the branch name where the models are stored):
 
-- **tag v1 —** - 05/11/2024
+- **tag v1 —** 05/11/2024
 
 - Stay tuned for more models!
  
 ### Model Sources
 
 - **Repository:** https://github.com/ibm-granite/granite-geospatial-land-surface-temperature
-- **Paper (UHI):** https://ieeexplore.ieee.org/document/10641750 - we have since extended on this approach by training on multiple cites to downscale to $30 m$ resolution LST. We have also included functionality for temporal gap filling, "Tweening". 
+- **Paper (UHI):** https://ieeexplore.ieee.org/document/10641750 - we have since extended on this approach by training on multiple cites to downscale to 30m resolution LST. We have also included functionality for temporal gap filling, "Tweening". 
 - **Paper (foundation model):** https://arxiv.org/abs/2310.18660 
 
 ### External Blogs