Chemiresistive Gas Sensors Made with PtRu@SnO₂ Nanoparticles for Machine Learning-Assisted Discrimination of Multiple...

Area of Science:

• Environmental Science
• Materials Science
• Analytical Chemistry

Background:

• Volatile organic compounds (VOCs) are significant environmental pollutants linked to adverse health effects.
• Effective monitoring of VOCs is crucial for environmental protection and public health.
• Existing gas sensors often lack the selectivity needed for precise VOC identification.

Purpose of the Study:

• To develop highly sensitive and selective gas sensors for VOC detection.
• To enhance the performance of tin dioxide (SnO2) based gas sensors using porous platinum-ruthenium (PtRu) nanoalloys.
• To utilize machine learning for accurate classification of different VOCs.

Main Methods:

• Synthesis of porous PtRu nanoalloys via a hydrothermal method.
• Integration of PtRu nanoalloys with SnO2 nanoparticles to create a composite material for gas sensing.
• Application of Density Functional Theory (DFT) calculations to understand material interactions.
• Implementation of machine learning algorithms, specifically Particle Swarm Optimization-Support Vector Machine (PSO-SVM), for data analysis and classification.

Main Results:

• Successful synthesis and characterization of porous PtRu nanoalloys integrated with SnO2.
• DFT calculations confirmed PtRu nanoalloys enhance SnO2 sensitivity to acetone.
• Achieved 100% classification accuracy using PSO-SVM to distinguish between acetone, ethanol, methanol, and formaldehyde.
• Demonstrated enhanced performance of the fabricated gas sensors.

Conclusions:

• Porous PtRu nanoalloys significantly improve the sensitivity and selectivity of SnO2-based gas sensors for VOC detection.
• Machine learning, particularly PSO-SVM, is effective for achieving high accuracy in identifying specific VOCs.
• The developed sensor technology holds promise for advanced environmental monitoring and health hazard detection.