We introduce a Genetic Algorithm (GA) based, open-source project to solve multi-objective optimization problems of materials characterization data analysis including EXAFS, XPS and nanoindentation. The modular design and multiple crossover and mutation options make the software extensible for additional materials characterization applications too. This automation of the analysis is crucial in the era when instrumentation acquires data orders of magnitude more rapidly than it can be analyzed by hand. Our results demonstrated good fitness scores with minimal human intervention.
@article{arxiv.2203.10152,
title = {Automated Materials Spectroscopy Analysis using Genetic Algorithms},
author = {Miu Lun Lau and Min Long and Jeff Terry},
journal= {arXiv preprint arXiv:2203.10152},
year = {2022}
}
Comments
14 pages, 5 Figures, Accepted for publication in The 23rd International Conference on Artificial Intelligence (ICAI'21: July 26-29, 2021, USA), to be appear in SPRINGER NATURE - Research Book Series: Transactions on Computational Science & Computational Intelligence https://www.springer.com/series/11769"