Dataset for: High-throughput mineralogical characterization using automated in-situ microscopy and Raman spectroscopy

Read full text Summarise with VIRAT
Authors: Luca Stigliano, Julie Cosmidis
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This dataset contains the processed particle-resolved data, training datasets, microscopy images, and associated analysis code corresponding to the manuscript: “High-throughput mineralogical characterisation using automated in-situ microscopy and Raman spectroscopy”. The dataset includes: Particle-level morphological data for 307 mineralisation experiments, extracted from automated image analysis of in-situ optical microscopy. Indexed microscopy images corresponding to each experiment, where detected particles are labelled and linked to extracted morphometric descriptors. Training dataset for Random Forest classification, including labelled particle populations across ten morphological classes. An Excel file containing the experimental conditions corresponding to the 307 mineralisation experiments included in this dataset. Analysis workflows (Jupyter notebooks) used for particle detection, feature extraction, model training, and prediction. A README file describing the repository structure and providing guidance on data and code usage. These data and workflows support the analysis of particle populations and morphological classification described in the manuscript, and enable reproducibility of the full experimental and analytical pipeline.

Fields of Study & Subjects

Mineral Processing and Grinding Mineralogy and Gemology Studies Machine Learning in Materials Science

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 March 2026
Language
EN