Machine-Learning-Aided NO₂ Discrimination with an Array of Graphene Chemiresistors Covalently Functionalized by...

Area of Science:

• Materials Science
• Chemical Engineering
• Sensor Technology

Background:

• The Internet of Things (IoT) necessitates advanced gas sensors for environmental monitoring and healthcare.
• Nitrogen dioxide (NO2) detection is crucial for environmental safety and medical diagnostics.
• Existing gas sensors often struggle with selectivity in complex gas mixtures.

Purpose of the Study:

• To develop a highly sensitive and selective electronic nose for NO2 detection.
• To functionalize graphene layers using diazonium chemistry for enhanced sensing capabilities.
• To demonstrate the discrimination of NO2 from interfering gases using a multi-layer graphene sensor array.

Main Methods:

• Covalent functionalization of graphene layers with 4-nitrophenyl, 4-carboxyphenyl, and 4-bromophenyl aryl rings via diazonium chemistry.
• Assembly of functionalized graphene layers with a pristine layer to create a multi-sensor electronic nose.
• Exposure of the electronic nose to varying concentrations of NO2 (1-10 ppm) and interfering gases at room temperature.
• Application of multivariate statistical analysis, including Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), for data interpretation and sensor training.

Main Results:

• Demonstrated high sensitivity to NO2 at room temperature within the 1-10 ppm range.
• Successfully discriminated NO2 from a mixture of interfering gases using PCA, visualizing distinct clusters.
• Achieved a prediction accuracy exceeding 95% for NO2 recognition through LDA-based training.

Conclusions:

• The functionalized graphene-based electronic nose offers a promising platform for selective NO2 sensing.
• The developed sensor array demonstrates robust discrimination capabilities applicable to environmental and medical monitoring.
• The combination of diazonium chemistry and multivariate analysis provides an effective strategy for advanced gas sensing applications.