Please use this identifier to cite or link to this item: https://doi.org/10.15480/882.4040
Publisher DOI: 10.1038/s41524-021-00658-7
Title: Predicting the inhibition efficiencies of magnesium dissolution modulators using sparse machine learning models
Language: English
Authors: Schiessler, Elisabeth J. 
Würger, Tim 
Lamaka, Sviatlana V. 
Meißner, Robert  
Cyron, Christian J. 
Zheludkevich, Mikhail L. 
Feiler, Christian 
Aydin, Roland C. 
Issue Date: Dec-2021
Publisher: Nature Publ. Group
Source: npj Computational Materials 7 (1): 193 (2021-12)
Abstract (english): 
The degradation behaviour of magnesium and its alloys can be tuned by small organic molecules. However, an automatic identification of effective organic additives within the vast chemical space of potential compounds needs sophisticated tools. Herein, we propose two systematic approaches of sparse feature selection for identifying molecular descriptors that are most relevant for the corrosion inhibition efficiency of chemical compounds. One is based on the classical statistical tool of analysis of variance, the other one based on random forests. We demonstrate how both can—when combined with deep neural networks—help to predict the corrosion inhibition efficiencies of chemical compounds for the magnesium alloy ZE41. In particular, we demonstrate that this framework outperforms predictions relying on a random selection of molecular descriptors. Finally, we point out how autoencoders could be used in the future to enable even more accurate automated predictions of corrosion inhibition efficiencies.
URI: http://hdl.handle.net/11420/11290
DOI: 10.15480/882.4040
ISSN: 2057-3960
Institute: Kontinuums- und Werkstoffmechanik M-15 
Molekulardynamische Simulation weicher Materie M-EXK2 
Kunststoffe und Verbundwerkstoffe M-11 
Document Type: Article
Project: SFB 986: Maßgeschneiderte Multiskalige Materialsysteme - M3 
Funded by: Deutscher Akademischer Austauschdienst (DAAD) 
Deutsche Forschungsgemeinschaft (DFG) 
More Funding information: Funding by the Helmholtz Association is gratefully acknowledged. T.W. and C.F. gratefully acknowledge funding by the Deutscher Akademischer Austauschdienst (DAAD, German Academic Exchange Service) via Projektnummer 57511455. R.M. gratefully acknowledges funding by the Deutsche Forschungsgemeinschaft (D.F.G., German Research Foundation) via Projektnummer 192346071-SFB 986 and Projektnummer 390794421-GRK 2462.
License: CC BY 4.0 (Attribution) CC BY 4.0 (Attribution)
Journal: npj computational materials 
Appears in Collections:Publications with fulltext

Files in This Item:
File Description SizeFormat
s41524-021-00658-7.pdfVerlagsversion1,83 MBAdobe PDFView/Open
Thumbnail
Show full item record

Page view(s)

95
Last Week
0
Last month
checked on Jun 26, 2022

Download(s)

27
checked on Jun 26, 2022

Google ScholarTM

Check

Note about this record

Cite this record

Export

This item is licensed under a Creative Commons License Creative Commons