Data mining for materials science
-
Updated
Oct 15, 2026 - HTML
#
matminer
Here are 7 public repositories matching this topic...
A comprehensive, interactive learning path for applying machine learning to materials discovery, property prediction, and atomistic simulations.
machine-learning tutorial jupyter-notebook computational-chemistry materials-science materials-informatics pymatgen machine-learning-tutorial shap matminer
-
Updated
Oct 17, 2026 - Jupyter Notebook
A composition-based ML framework for predicting electronic band gaps of inorganic materials. XGBoost & Random Forest on 15,537 Materials Project compounds using Magpie descriptors.
python data-science machine-learning dft random-forest scikit-learn regression open-science density-functional-theory computational-chemistry xgboost feature-engineering materials-science materials-informatics semiconductors pymatgen matminer band-gap materials-project compositional-descriptors
-
Updated
Aug 26, 2026 - Jupyter Notebook
Machine-learning analysis of how chemical composition, sintering conditions and physics-based descriptors contribute to ionic conductivity prediction in zirconia-based electrolytes. Includes grouped validation, SHAP interpretation and candidate screening.
machine-learning materials-informatics ionic-conductivity shap matminer zirconia solid-oxide-fuel-cells
-
Updated
Sep 29, 2026 - Python
Data-variance capture ability of Composition-descriptors while predicting the band gap (primarily semiconductor family choosen)
-
Updated
Apr 13, 2026 - Python
Inverse catalyst design with GP surrogates and multi-objective BO. Validated on published propane-dehydrogenation data: recovers Ga-Mo top-yield and Mg-modified low-deactivation families.
materials-informatics gradio gaussian-processes bayesian-optimization gpytorch botorch matminer inverse-design catalyst-design propane-dehydrogenation
-
Updated
Aug 8, 2026 - Python
Machine learning model to predict band gap of iron-oxide materials using Materials Project database and matminer chemistry features. Built with Python, scikit-learn and Random Forest achieving R² of 0.665.
python machine-learning random-forest materials-science materials-informatics matminer band-gap band-gap-prediction
-
Updated
Aug 7, 2026 - Python
Add this topic to your repo
To associate your repository with the matminer topic, visit your repo's landing page and select "manage topics."