AMLRO
This is the documentation of amlro.
Active Machine Learning Reaction Optimizer (AMLRO) for data-efficient reaction process condition discovery and optimization.
AMLRO is an open-source framework designed to accelerate chemical reaction optimization using active learning with classical machine learning regression models. AMLRO integrates space-filling sampling strategies (e.g., Sobol and Latin Hypercube sampling) with iterative model training, prediction, and experiment selection to efficiently navigate complex reaction spaces. The platform supports multiple regression models, flexible multi-objective definitions, and user-defined parameter bounds, enabling data-efficient optimization from small initial datasets. AMLRO is designed for ease of use by experimentalists and can operate as a standalone decision-support tool or be integrated into closed-loop automated experimentation workflows.
AMLRO follows a three-step workflow:
Reaction space generation
Training set generation with experimental feedback
Active learning-loop -> prediction of optimal reaction conditions.
How to Cite AMLRO
If you use AMLRO in academic research, please cite:
Kulathunga, D. P.; Crandall, Z. RxnRover/amlro. Computer Software. USDOE Office of Energy Efficiency and Renewable Energy (EERE), Advanced Materials & Manufacturing Technologies Office (AMMTO), 2026. DOI: https://doi.org/10.11578/dc.20260205.1
Key Features
Active learning for reaction optimization
Continuous and categorical reaction parameters
Modular regression and acquisition strategies
Designed for experimental feedback loops