Oxyfluoride prediction with GRID

## Access ##
This dataset is held in the Edinburgh DataVault, directly accessible only to authorised University of Edinburgh staff. External users may request access to a copy of the data by contacting the Principal Investigator, Contact Person or Data Manager named on this page. University of Edinburgh users who wish to have direct access should consult the information about retrieving data from the DataVault at: https://www.ed.ac.uk/is/research-support/datavault .

Outputs from RSC-funded summer internship (2022, Marta Chronowska) focussed on predicting new oxyfluoride materials using GRID representations of crystal structures. The outputs consist of:
- computed GRIDs for ~120k materials extracted from the ICSD
- Dissimilarities (Earth mover distances) between each pair of GRIDs
- t-SNE embeddings of the materials labelled as oxides and fluorides, with mapped oxide-oxyfluoride pairs
- README files, processing scripts and Jupyter notebook for t-SNE plotting.