Loading...
Loading...
Contributors:
Dataset URI:
10.5281/zenodo.23312653Brief description This dataset contains the data needed to reproduce part of the results from the paper "Distortion states as robust embeddings for quantifying and forecasting atomistic damage from electron microscopy" by Camilo A. F. Salvador et al. (2026). Summary: The descriptor and image data are from the "larger box" in the paper (i.e., 686,000 Fe atoms). There are 151 image frames, from 4,000 fs to 604,000 fs, sampled every 4 ps. That’s a span of 600 ps, reaching approximately 0.0875 dpa. Contributors: Camilo A. F. Salvador, Clovis Lapointe, Thomas Bilyk, Maxime Filimonov, Estelle Meslin, Mihai-Cosmin MarinicaThis work has been carried out within the Cross-disciplinary Initiative for Digital Science of the French Alternative Energies and Atomic Energy Commission (CEA). For more information, please get in touch with us via https://github.com/ai-atoms/mirepoix. A brief description of each file can be found in the table of contents below; Table of contents - "descriptor.zip" -> "data/fpa70a/descriptor/dsv": 5.4 GB - "00_000_000001.npy" to "00_000_000152.npy": 7 distance scores for the first 151 configurations. - "channels.json": identification of each distance (reference). - "images.zip" -> "data/fpa70a/images": 41.8 MB - "70_000_000001.png" to "70_000_000152.png": 151 images generated from the snapshots above. - "models.zip" -> "data/npj_components/models": 103.3 MB - "convnext_in_3hl", "vitl16_in_3hl", etc, : weights for 9 models (6 encoder heads, u640-physprop, u16-physprop, VAR1) detailed in the GitHub repository.
Keyword(s):
Atomistic simulations; Radiation damage; Scanning transmission electron microscopy (STEM).
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)