Gas Sensing with Nanoporous In<sub>2</sub>O<sub>3</sub> under Cyclic Optical Activation: Machine Learning-Aided Classification of H<sub>2</sub> and H<sub>2</sub>O

Clean hydrogen is a key aspect of carbon neutrality, necessitating robust methods for monitoring hydrogen concentration in critical infrastructures like pipelines or power plants. While semiconducting metal oxides such as In<sub>2</sub>O<sub>3</sub> can monitor gas concentrat...

Full description

Saved in:
Bibliographic Details
Main Authors: Dominik Baier, Alexander Krüger, Thorsten Wagner, Michael Tiemann, Christian Weinberger
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Chemosensors
Subjects:
Online Access:https://www.mdpi.com/2227-9040/12/9/178
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261270743220224
author Dominik Baier
Alexander Krüger
Thorsten Wagner
Michael Tiemann
Christian Weinberger
author_facet Dominik Baier
Alexander Krüger
Thorsten Wagner
Michael Tiemann
Christian Weinberger
author_sort Dominik Baier
collection DOAJ
description Clean hydrogen is a key aspect of carbon neutrality, necessitating robust methods for monitoring hydrogen concentration in critical infrastructures like pipelines or power plants. While semiconducting metal oxides such as In<sub>2</sub>O<sub>3</sub> can monitor gas concentrations down to the ppm range, they often exhibit cross-sensitivity to other gases like H<sub>2</sub>O. In this study, we investigated whether cyclic optical illumination of a gas-sensitive In<sub>2</sub>O<sub>3</sub> layer creates identifiable changes in a gas sensor’s electronic resistance that can be linked to H<sub>2</sub> and H<sub>2</sub>O concentrations via machine learning. We exposed nanostructured In<sub>2</sub>O<sub>3</sub> with a large surface area of 95 m<sup>2</sup> g<sup>−1</sup> to H<sub>2</sub> concentrations (0–800 ppm) and relative humidity (0–70%) under cyclic activation utilizing blue light. The sensors were tested for 20 classes of gas combinations. A support vector machine achieved classification rates up to 92.0%, with reliable reproducibility (88.2 ± 2.7%) across five individual sensors using 10-fold cross-validation. Our findings suggest that cyclic optical activation can be used as a tool to classify H<sub>2</sub> and H<sub>2</sub>O concentrations.
format Article
id doaj-art-fb09547e8f2c4e55ae237426ae0e866a
institution OA Journals
issn 2227-9040
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Chemosensors
spelling doaj-art-fb09547e8f2c4e55ae237426ae0e866a2025-08-20T01:55:27ZengMDPI AGChemosensors2227-90402024-09-0112917810.3390/chemosensors12090178Gas Sensing with Nanoporous In<sub>2</sub>O<sub>3</sub> under Cyclic Optical Activation: Machine Learning-Aided Classification of H<sub>2</sub> and H<sub>2</sub>ODominik Baier0Alexander Krüger1Thorsten Wagner2Michael Tiemann3Christian Weinberger4Department of Chemistry, Paderborn University, Warburger Str. 100, D-33098 Paderborn, GermanyDepartment of Chemistry, Paderborn University, Warburger Str. 100, D-33098 Paderborn, GermanyDepartment of Chemistry, Paderborn University, Warburger Str. 100, D-33098 Paderborn, GermanyDepartment of Chemistry, Paderborn University, Warburger Str. 100, D-33098 Paderborn, GermanyDepartment of Chemistry, Paderborn University, Warburger Str. 100, D-33098 Paderborn, GermanyClean hydrogen is a key aspect of carbon neutrality, necessitating robust methods for monitoring hydrogen concentration in critical infrastructures like pipelines or power plants. While semiconducting metal oxides such as In<sub>2</sub>O<sub>3</sub> can monitor gas concentrations down to the ppm range, they often exhibit cross-sensitivity to other gases like H<sub>2</sub>O. In this study, we investigated whether cyclic optical illumination of a gas-sensitive In<sub>2</sub>O<sub>3</sub> layer creates identifiable changes in a gas sensor’s electronic resistance that can be linked to H<sub>2</sub> and H<sub>2</sub>O concentrations via machine learning. We exposed nanostructured In<sub>2</sub>O<sub>3</sub> with a large surface area of 95 m<sup>2</sup> g<sup>−1</sup> to H<sub>2</sub> concentrations (0–800 ppm) and relative humidity (0–70%) under cyclic activation utilizing blue light. The sensors were tested for 20 classes of gas combinations. A support vector machine achieved classification rates up to 92.0%, with reliable reproducibility (88.2 ± 2.7%) across five individual sensors using 10-fold cross-validation. Our findings suggest that cyclic optical activation can be used as a tool to classify H<sub>2</sub> and H<sub>2</sub>O concentrations.https://www.mdpi.com/2227-9040/12/9/178resistive gas sensorchemiresistorsemiconductormetal oxideIn<sub>2</sub>O<sub>3</sub>mesoporous
spellingShingle Dominik Baier
Alexander Krüger
Thorsten Wagner
Michael Tiemann
Christian Weinberger
Gas Sensing with Nanoporous In<sub>2</sub>O<sub>3</sub> under Cyclic Optical Activation: Machine Learning-Aided Classification of H<sub>2</sub> and H<sub>2</sub>O
Chemosensors
resistive gas sensor
chemiresistor
semiconductor
metal oxide
In<sub>2</sub>O<sub>3</sub>
mesoporous
title Gas Sensing with Nanoporous In<sub>2</sub>O<sub>3</sub> under Cyclic Optical Activation: Machine Learning-Aided Classification of H<sub>2</sub> and H<sub>2</sub>O
title_full Gas Sensing with Nanoporous In<sub>2</sub>O<sub>3</sub> under Cyclic Optical Activation: Machine Learning-Aided Classification of H<sub>2</sub> and H<sub>2</sub>O
title_fullStr Gas Sensing with Nanoporous In<sub>2</sub>O<sub>3</sub> under Cyclic Optical Activation: Machine Learning-Aided Classification of H<sub>2</sub> and H<sub>2</sub>O
title_full_unstemmed Gas Sensing with Nanoporous In<sub>2</sub>O<sub>3</sub> under Cyclic Optical Activation: Machine Learning-Aided Classification of H<sub>2</sub> and H<sub>2</sub>O
title_short Gas Sensing with Nanoporous In<sub>2</sub>O<sub>3</sub> under Cyclic Optical Activation: Machine Learning-Aided Classification of H<sub>2</sub> and H<sub>2</sub>O
title_sort gas sensing with nanoporous in sub 2 sub o sub 3 sub under cyclic optical activation machine learning aided classification of h sub 2 sub and h sub 2 sub o
topic resistive gas sensor
chemiresistor
semiconductor
metal oxide
In<sub>2</sub>O<sub>3</sub>
mesoporous
url https://www.mdpi.com/2227-9040/12/9/178
work_keys_str_mv AT dominikbaier gassensingwithnanoporousinsub2subosub3subundercyclicopticalactivationmachinelearningaidedclassificationofhsub2subandhsub2subo
AT alexanderkruger gassensingwithnanoporousinsub2subosub3subundercyclicopticalactivationmachinelearningaidedclassificationofhsub2subandhsub2subo
AT thorstenwagner gassensingwithnanoporousinsub2subosub3subundercyclicopticalactivationmachinelearningaidedclassificationofhsub2subandhsub2subo
AT michaeltiemann gassensingwithnanoporousinsub2subosub3subundercyclicopticalactivationmachinelearningaidedclassificationofhsub2subandhsub2subo
AT christianweinberger gassensingwithnanoporousinsub2subosub3subundercyclicopticalactivationmachinelearningaidedclassificationofhsub2subandhsub2subo