diff --git a/notebook.ipynb b/notebook.ipynb
index 7968d88..d39817a 100644
--- a/notebook.ipynb
+++ b/notebook.ipynb
@@ -16,9 +16,9 @@
     "This notebook demonstrates the use of the python library api for forecasting sea ice for a reduced dataset to demonstrate its capabilities. The final output of interest are maps of sea ice concentration.\n",
     "\n",
     "### Modelling approach\n",
-    "IceNet is a probabilistic, deep learning sea ice forecasting system. It utilises ensemble modelling of U-Net networks to generate daily forecasts of sea ice condition, trained on climate reanalysis and sea ice observational data (the built-in downloaders within IceNet are extensible). The original IceNet research model, published in Nature Communications ([Seasonal Arctic sea ice forecasting with probabilistic deep learning](https://www.nature.com/articles/s41467-021-25257-4)) was trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps.\n",
+    "IceNet is a probabilistic, deep learning sea ice forecasting system. It utilises ensemble modelling of [U-Net](https://link.springer.com/chapter/10.1007/978-3-319-24574-4_28) networks to generate daily forecasts of sea ice condition, trained on climate reanalysis and sea ice observational data (the built-in downloaders within IceNet are extensible). The original IceNet research model, published in Nature Communications ([Seasonal Arctic sea ice forecasting with probabilistic deep learning](https://www.nature.com/articles/s41467-021-25257-4)) was trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps.\n",
     "\n",
-    "The python library ([IceNet](https://github.com/icenet-ai/icenet/)) showcased in this notebook is a heavily refactored version of the original research code from the original publication that has been developed for operational forecasting that utilises daily inputs and is able to generate daily forecast outputs for a variable forecast time period. The core UNet architecture is implemented using Tensorflow, however, the library architecture allows other backend libraries to be utilised and wrapped around the IceNet library ecosystem.\n",
+    "The python library ([IceNet](https://github.com/icenet-ai/icenet/)) showcased in this notebook is a heavily refactored version of the original research code from the original publication that has been developed for operational forecasting that utilises daily inputs and is able to generate daily forecast outputs for a variable forecast time period. The core U-Net architecture is implemented using Tensorflow, however, the library architecture allows other backend libraries to be utilised and wrapped around the IceNet library ecosystem.\n",
     "\n",
     "### Highlights\n",
     " * [1. Setup](#Setup) the environment and project structure.\n",
@@ -31,7 +31,7 @@
     "### Compatible platforms\n",
     "\n",
     "The `IceNet` library is designed to be run within a Unix environment, and, as such, this notebook has been tested on the following OS platforms:\n",
-    "* Linux x64\n",
+    "* Linux\n",
     "* macOS (Intel and Apple Silicon)\n",
     "\n",
     "Windows is not supported, however, [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install) should work, but is untested.\n",
@@ -880,7 +880,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We can now use `train_model` function to train the UNet model based on the above downloaded and processed data."
+    "We can now use `train_model` function to train the U-Net model based on the above downloaded and processed data."
    ]
   },
   {
@@ -7832,7 +7832,7 @@
     "\n",
     "* Showing usage of the IceNet library to download different climate data variables ([ERA5](https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-single-levels?tab=overview)) and sea ice concentration maps ([OSI SAF](https://osi-saf.eumetsat.int/)) from different data sources via a similar api interface. (The ERA5 code was shown, but not run due to need for a free personal API key having been setup by the user)\n",
     "* Processing of downloaded data to include normalisation and data caching to speed up the training.\n",
-    "* Showing the use of a high-level interface to the IceNet UNet model to train on different data sources and generate predictions of binary sea ice concentration.\n",
+    "* Showing the use of a high-level interface to the IceNet U-Net model to train on different data sources and generate predictions of binary sea ice concentration.\n",
     "* Visualising the predictions using the plotting tools within the IceNet library.\n",
     "* Visualising good results with increased network size and runtime.\n",
     "* If researching, consider [extending the functionality of the API to include revised or completely new implementations, such as additional data sources](https://github.com/icenet-ai/icenet-notebooks/blob/main/05.library_extension.ipynb)\n",