Machine Learning the microscopic form of nematic order in twisted double-bilayer graphene

Dataset for paper: Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene (https://arxiv.org/abs/2302.12274)

It contains the test data sets and corresponding "model.h5" with trained weights for evaluation.

The data for each case can be identified by the prefix in the .npz files. Correspondent training datasets can be created from "mpsingle.py" in github repository https://github.com/joaosds/nematic-learning;

Each .npz file usually has the DOS(r) in "DataX", scaleograms with and without noise in "DataW" and "DataZ", and correspondent labels in "DataY". This can be checked with the "utils/checknpz.py

.mat files correspond to the associated experimental dataset from the last section of the main text.

If you have any questions please reach out by [e-mail].