Further processing options
Predicting the inhibition efficiencies of magnesium dissolution modulators using sparse machine learning models
Saved in:
| Published in: | npj computational materials year:2021; elocationid:193; volume:7; pages:1-9; 7(2021), 1, Artikel-ID 193, Seite 1-9; number:1 |
|---|---|
| Authors and Corporations: | , , , , , , , , , , , |
| Other Authors: | Würger, Tim [Author] • Lamaka, Sviatlana V. [Author] • Meißner, Robert [Author] • Cyron, Christian J. [Author] • Zheludkevich, Mikhail L. 1976- [Author] • Feiler, Christian [Author] • Aydin, Roland C. [Author] |
| Type of Resource: | E-Book Component Part |
| Language: | English |
| published: |
2021
|
| Series: |
npj computational materials, 7(2021), 1, Artikel-ID 193, Seite 1-9
|
| Source: | Verbunddaten SWB Lizenzfreie Online-Ressourcen |
| ISSN: | 2057-3960 |
| License: |
| Summary: | 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. |
|---|---|
| Item Description: |
Sonstige Körperschaft: Technische Universität Hamburg Sonstige Körperschaft: Technische Universität Hamburg, Institute of Continuum Mechanics and Materials Mechanics Sonstige Körperschaft: Technische Universität Hamburg, Arbeitsgruppe Molekulardynamische Simulation Weicher Materie Sonstige Körperschaft: Technische Universität Hamburg, Institut für Kunststoffe und Verbundwerkstoffe |
| Physical Description: | Diagramme |
| ISSN: | 2057-3960 |
| DOI: | 10.15480/882.4040 |
| Access: | Open Access |