Tutorial Background Information
This tutorial is on modelling the dynamics of pandemics using neural networks, focusing in particular on the use of 'Physics-Informed Neural Networks' (PINNs) for this purpose.
The COVID-19 pandemic opened the world's eyes to the reality of our vunerability to global pandemics. The public health policies of different countries was a central talking point throughout the three years - decisions had to be made around raising and lowering travel and social distancing restrictions by carefully weighing the expected social and economic costs against benefits. Having accurate predictions of future trends in numbers of cases is essential when making such decisions.
Since the pandemic, there has been a lot of work done on using the data collected to build models that could forcast oncoming peaks in numbers of cases. Such models could potentially inform decisions that save millions of lives in future pandemics. The tutorial here gives you an interactive opportunity to learn to put together such models using Python.
Prerequisite Knowledge for the Tutorial
The coder's version of the tutorial below assumes you know how to work with neural networks in Python using the machine learning library PyTorch. If you know nothing about neural networks, this online book contains an explanation from the foundations up of how they work and these official PyTorch lessons are a good resource for learning to use the library.
If you are new to coding in Python, there is a Python coding page on this website with a list of resources to help you learn to code. However, if you don't have any of the prerequisite knowledge for the tutorial and don't want to spend time doing pre-reading, don't worry, the non-coder's version shows you the same principles in action using less technical explanations and it doesn't require you to write any code.
The Tutorial
These buttons will open a Google Colab notebook which constitutes the tutorial: