COD Synthetic Powder X-Ray Diffraction (XRD) Patterns: 436,196 Simulated Diffractograms from the Crystallography Open Database

Provider
ohlstrom (Hugging Face); structures from the Crystallography Open Database
License
CC0-1.0 (source)
Size
7 files
Stored at
Hugging Face (https://huggingface.co/datasets/ohlstrom/Crystallography-Open-Database-XRD-Patterns)
Access
Free and public. No account with the data provider is needed.
Category
Chemistry & Materials
Source
https://www.crystallography.net/cod/

About this dataset

Simulated powder X-ray diffraction (PXRD) patterns for every CIF crystal structure in the Crystallography Open Database (COD): 436,196 diffractograms spanning metals, minerals, organic molecular crystals and metal-organic frameworks. Each pattern was computed with the pymatgen XRDCalculator for Cu K-alpha radiation (1.54184 angstrom) over 2-theta 0 to 90 degrees at a 0.02 degree step, giving a 4,500-point intensity vector min-max scaled to [0, 1]. Files are PyTorch .pt dictionaries holding a patterns tensor of shape (N, 4500) and the matching COD CIF filenames, so each pattern links back to its structure at crystallography.net by COD ID. The full set ships with random subsets of 1,000, 10,000, 50,000 and 100,000 patterns for prototyping. No measured diffractograms are included. Use it to train phase identification, crystal system and space group classifiers, or diffraction-to-structure models; load with torch.load. License CC0 1.0, the same as COD. Cite Grazulis et al., Crystallography Open Database, J. Appl. Cryst. 42, 726 (2009), and pymatgen (Ong et al. 2013).

How to load this dataset in Python

from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="ohlstrom/Crystallography-Open-Database-XRD-Patterns", filename="COD_xrd_patterns_1000.pt", repo_type="dataset")
print(path)

Data structure

Files

Example file: COD_xrd_patterns_1000.pt

Analyze this dataset without downloading it

On Scigantic, COD Synthetic Powder X-Ray Diffraction (XRD) Patterns: 436,196 Simulated Diffractograms from the Crystallography Open Database opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Chemistry & Materials datasets