ml-uncertainty-quantification.md

name	Uncertainty quantification
description	Uncertainty quantification, active learning, and optimization tools for materials science.
tags	Code/ML Code/Lib Code/WF

Uncertainty quantification

Item (URL)	Description	Tags
AGOX	Atomistic Global Optimization X for structural energy minimization and global search.	Code/ML, Code/Lib
PyAPX	Integration of DFT codes with Bayesian optimization to explore stable atomic configurations.	Code/ML, Code/Lib
PyPhysTree	Physics-informed tree search framework for high-dimensional computational design and scientific optimization.	Code/ML, Code/Lib
information-matching	Optimal experimental design and active learning to identify informative training data.	Code/ML, Code/Lib
ChemNavigator	Photocatalyst design rule discovery through hypothesis-driven molecular design, quantum calculations, and statistical validation.	Code/ML, Code/WF
ARROWS	Automated precursor selection and synthesis planning utilizing thermodynamics and active learning.	Code/ML, Code/Lib
LLEMA	Evolutionary search with Large Language Models for multi-objective materials discovery.	Code/ML, Code/Lib
activemiao	Active learning neuroevolution potential construction for molecular dynamics simulations.	Code/ML, Code/WF
GEWUM	General exploration workflow for automated structure generation, selection, and validation.	Code/ML, Code/WF
ACAL	Activity coefficient acquisition using thermodynamics-informed active learning for phase diagram construction.	Code/ML, Code/WF
LEAP	Closed-loop active learning framework for perovskite precursor additive discovery.	Code/ML, Code/WF
chemfit	Parameter fitting of objective functions in model parameterization.	Code/ML, Code/Lib
UQ-uMLIP	Uncertainty quantification framework for universal interatomic potentials.	Code/ML, Code/Lib
GNN_Uncertainty	Uncertainty quantification and error estimation scripts for graph neural networks.	Code/ML, Code/Lib
bayesaenet	Benchmarking uncertainty quantification methods in machine learning interatomic potentials.	Code/ML, Code/Lib
Bgolearn	Bayesian optimization and active learning for materials discovery and design.	Code/ML, Code/WF