An ensemble of XGBoost regression models trained on ~2000 hydrides screens ternary A-B-H compositions for high-Tc superconductivity at 100-300 GPa and flags promising systems such as Ca-Ti-H, Li-K-H, and Na-Mg-H.
Stanev , author C
2 Pith papers cite this work, alongside 429 external citations. Polarity classification is still indexing.
2
Pith papers citing it
429
external citations · OpenAlex
verdicts
UNVERDICTED 2representative citing papers
Q-GAIN is a Python package implementing ML classification, object detection, and physics-informed metrics for analyzing images of atomic BECs, demonstrated on MNIST, soliton detection, and vortex identification tasks.
citing papers explorer
-
Composition-Based Machine Learning for Screening Superconducting Ternary Hydrides from a Curated Dataset
An ensemble of XGBoost regression models trained on ~2000 hydrides screens ternary A-B-H compositions for high-Tc superconductivity at 100-300 GPa and flags promising systems such as Ca-Ti-H, Li-K-H, and Na-Mg-H.
-
Q-GAIN: A Python Package for Machine Learning and Physically Informed Analysis Applications
Q-GAIN is a Python package implementing ML classification, object detection, and physics-informed metrics for analyzing images of atomic BECs, demonstrated on MNIST, soliton detection, and vortex identification tasks.