Leeds Institute for Fluid Dynamics Machine Learning For Earth Sciences

Dimensionality Reduction

This Jupyter notebook is based on Jonathan Coney's work on identifying and characterising trapped lee waves using dimensionality reduction. The work is outlined in Coney et al., 2023. This notebook will go through the basics of Principal Component Analysis and Dimensionality Reduction methods using some toy code from a Kaggle tutorial and the MNIST dataset, and then apply those methods to an Earth Science application based on Jonathan Coney's work.

Quick look

Quick start

Binder and Colab buttons

Will launch this tutorial in binder (CPU) or Google Colab (GPU)

Running Locally

If you're already familiar with git, Anaconda and virtual environments, the environment you need to create is found in DR.yml and the code below will install, activate and launch the notebook. The .yml file has been tested on the latest Linux, macOS and Windows operating systems.

git clone git@github.com:cemac/LIFD_DimensionalityReduction.git
cd LIFD_DimensionalityReduction
conda env create -f DR.yml
conda activate DR
jupyter-notebook

Installation and Requirements

This notebook is designed to run on a laptop with no special hardware required. Therefore, it is recommended to do a local installation as outlined in the repository howtorun and jupyter_notebooks sections.

Licence information

LIFD_ENV_ML_NOTEBOOKS by cemac is licensed under a Creative Commons Attribution 4.0 International License.

Acknowledgements

Thanks to Jonathan Coney for the basis of this tutorial. This tutorial is part of the LIFD ENV ML NOTEBOOKS series. Please refer to the parent repository for full acknowledgements.