Data-driven corrosion inhibition efficiency prediction model incorporating 2D–3D molecular graphs and inhibitor concentration

Jinbo Ma; Jiaxin Dai; Xin Guo; Dongmei Fu; Lingwei Ma; Patrick Keil; Arjan Mol; Dawei Zhang

doi:10.1016/j.corsci.2023.111420

Data-driven corrosion inhibition efficiency prediction model incorporating 2D–3D molecular graphs and inhibitor concentration

Jinbo Ma, Jiaxin Dai, Xin Guo, Dongmei Fu^*, Lingwei Ma, Patrick Keil, Arjan Mol, Dawei Zhang

^*Corresponding author for this work

Team Arjan Mol

Research output: Contribution to journal › Article › Scientific › peer-review

1 Citation (Scopus)

20 Downloads (Pure)

Abstract

Following the construction of a dataset of cross-category corrosion inhibitors at different concentrations based on 1241 data from 184 research papers, a performance prediction model incorporating 2D–3D molecular graph representation and corrosion inhibitor concentration information was established. This model was shown to effectively predict the inhibition efficiency (IE) of different categories of corrosion inhibitors for carbon steel in 1 mol/L HCl solution. The model was also able to predict IEs of corrosion inhibitors at different concentrations. The results demonstrated that 3D features of corrosion inhibitors, especially those of large molecules, had a significant impact on the prediction precision of IEs.

Original language	English
Article number	111420
Number of pages	7
Journal	Corrosion Science
Volume	222
DOIs	https://doi.org/10.1016/j.corsci.2023.111420
Publication status	Published - 2023

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Corrosion inhibition
Corrosion prediction
Machine learning
Molecular graph

Access to Document

10.1016/j.corsci.2023.111420

1-s2.0-S0010938X23004626-mainFinal published version, 3.32 MB

Cite this

@article{b08fd89d8e9c48ef9959f9cdbbd10b6a,

title = "Data-driven corrosion inhibition efficiency prediction model incorporating 2D–3D molecular graphs and inhibitor concentration",

abstract = "Following the construction of a dataset of cross-category corrosion inhibitors at different concentrations based on 1241 data from 184 research papers, a performance prediction model incorporating 2D–3D molecular graph representation and corrosion inhibitor concentration information was established. This model was shown to effectively predict the inhibition efficiency (IE) of different categories of corrosion inhibitors for carbon steel in 1 mol/L HCl solution. The model was also able to predict IEs of corrosion inhibitors at different concentrations. The results demonstrated that 3D features of corrosion inhibitors, especially those of large molecules, had a significant impact on the prediction precision of IEs.",

keywords = "Corrosion inhibition, Corrosion prediction, Machine learning, Molecular graph",

author = "Jinbo Ma and Jiaxin Dai and Xin Guo and Dongmei Fu and Lingwei Ma and Patrick Keil and Arjan Mol and Dawei Zhang",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.",

year = "2023",

doi = "10.1016/j.corsci.2023.111420",

language = "English",

volume = "222",

journal = "Corrosion Science",

issn = "0010-938X",

publisher = "Elsevier",

}

TY - JOUR

T1 - Data-driven corrosion inhibition efficiency prediction model incorporating 2D–3D molecular graphs and inhibitor concentration

AU - Ma, Jinbo

AU - Dai, Jiaxin

AU - Guo, Xin

AU - Fu, Dongmei

AU - Ma, Lingwei

AU - Keil, Patrick

AU - Mol, Arjan

AU - Zhang, Dawei

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2023

Y1 - 2023

N2 - Following the construction of a dataset of cross-category corrosion inhibitors at different concentrations based on 1241 data from 184 research papers, a performance prediction model incorporating 2D–3D molecular graph representation and corrosion inhibitor concentration information was established. This model was shown to effectively predict the inhibition efficiency (IE) of different categories of corrosion inhibitors for carbon steel in 1 mol/L HCl solution. The model was also able to predict IEs of corrosion inhibitors at different concentrations. The results demonstrated that 3D features of corrosion inhibitors, especially those of large molecules, had a significant impact on the prediction precision of IEs.

AB - Following the construction of a dataset of cross-category corrosion inhibitors at different concentrations based on 1241 data from 184 research papers, a performance prediction model incorporating 2D–3D molecular graph representation and corrosion inhibitor concentration information was established. This model was shown to effectively predict the inhibition efficiency (IE) of different categories of corrosion inhibitors for carbon steel in 1 mol/L HCl solution. The model was also able to predict IEs of corrosion inhibitors at different concentrations. The results demonstrated that 3D features of corrosion inhibitors, especially those of large molecules, had a significant impact on the prediction precision of IEs.

KW - Corrosion inhibition

KW - Corrosion prediction

KW - Machine learning

KW - Molecular graph

UR - http://www.scopus.com/inward/record.url?scp=85166190823&partnerID=8YFLogxK

U2 - 10.1016/j.corsci.2023.111420

DO - 10.1016/j.corsci.2023.111420

M3 - Article

AN - SCOPUS:85166190823

SN - 0010-938X

VL - 222

JO - Corrosion Science

JF - Corrosion Science

M1 - 111420

ER -

Data-driven corrosion inhibition efficiency prediction model incorporating 2D–3D molecular graphs and inhibitor concentration

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this