/nucml

End-to-end python-based supervised machine learning pipeline for ML-augmented nuclear data evaluation.

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

NucML

<pedrojrv> Maintainability

NucML is the first and only end-to-end python-based supervised machine learning pipeline for enhanced bias-free nuclear data generation and evaluation to support the advancement of next-generation nuclear systems. It offers capabilities that allows researchers to navigate through each step of the ML-based nuclear data cross section evaluation pipeline. Some of the supported activities include include dataset parsing and compilation of reaction data, exploratory data analysis, data manipulation and feature engineering, model training and evaluation, and validation via criticality benchmarks. Some of the inherit benefits of this approach are the reduced human-bias in the generation and solution and the fast iteration times. Resulting data from these models can aid the current NDE and help decisions in uncertain scenarios.

Installation and Setup

Please refer to the Installation guide in the official documentation here: https://pedrojrv.github.io/nucml/.

All educational and tutorial material can be found in the ML_Nuclear_Data repository here: https://github.com/pedrojrv/ML_Nuclear_Data

How to Cite

If you used NucML for your work, feel free to cite us:

@article{VICENTEVALDEZ2021108596,
title = {Nuclear data evaluation augmented by machine learning},
journal = {Annals of Nuclear Energy},
volume = {163},
pages = {108596},
year = {2021},
issn = {0306-4549},
doi = {https://doi.org/10.1016/j.anucene.2021.108596},
url = {https://www.sciencedirect.com/science/article/pii/S0306454921004722},
author = {Pedro Vicente-Valdez and Lee Bernstein and Massimiliano Fratoni},
keywords = {Machine learning, EXFOR, Uranium benchmark, Cross section evaluation},
}