Reproducibility Package for "Quantitative Assessment of Peridotite Tectonomagmatic Affinities Using Compositional Data Analysis and Explainable Machine Learning"
Abstract
This archive contains all code, scripts, processed datasets, model artifacts, and environment files required to reproduce the workflow described in the manuscript “Quantitative Assessment of Peridotite Tectonomagmatic Affinities Using Compositional Data Analysis and Explainable Machine Learning ” submitted to Geochemistry, Geophysics, Geosystems. It includes the Python scripts for data ingestion, ILR transformation, feature engineering, SMOTE balancing, nested cross-validation, XGBoost model training, the trained pipeline, and dataset.
Fields of Study & Subjects
Geochemistry and Geologic Mapping
Geological and Geochemical Analysis
Machine Learning in Materials Science
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 9 January 2026
- Language
- EN
- Document type
- Dataset