Great to see @nom_D_plumes' #OpenAccess paper in its final form. This really is a nice study looking at #geochemistry of the #Platinum Group Elements (PGEs) using #MachineLearning techniques.

Link here: https://doi.org/10.1016/j.gsf.2020.10.005

Take home messages below!

#geology #scicomm https://twitter.com/nom_D_plumes/status/1349368794729369602

The main thrust of the paper is reducing complex #geochemical datasets into fewer variables that make it easier to analyse whilst retaining the information from lots of geochemical elements. @nom_D_plumes started with a rather nice correlation matrix - note Pd-Cu association.

To make this a bit more manageable, Principal Component Analysis (PCA) reduced the number of variables and was used as inputs to a k-means clustering algorithm ( #unsupervised learning). The #clusters showed some fairly nice correlations when plotted with the original #elements

However, t-SNE (t-distributed stochastic neighbour embedding) brought everything together. t-SNE takes all the information and preserves data structure whilst reducing the information to just two variables (embeddings). Now the #clusters are clear!

https://doi.org/10.1016/j.gsf.2020.10.005

The paper is a great example of using data science in geochemistry.

It goes on to discuss the nuances of #platinum and #palladium in plume systems. This paper is building towards a fantastic piece that is still in the works from @nom_D_plumes! https://doi.org/10.1016/j.gsf.2020.10.005