Machine learning-assisted CeO₂ nanorod sensor platform for visual detection of paraoxon

Area of Science:

• Nanomaterials Science
• Chemical Sensing
• Machine Learning Applications

Background:

• Paraoxon is a toxic organophosphate pesticide.
• Selective and accurate detection of paraoxon is crucial for environmental and health monitoring.
• Existing detection methods may lack real-time capabilities or high selectivity.

Purpose of the Study:

• To develop a machine learning-assisted sensor platform for real-time paraoxon detection.
• To investigate the selectivity of cerium oxide (CeO₂) nanorods for paraoxon.
• To achieve high accuracy in paraoxon detection using a colorimetric approach.

Main Methods:

• Fabrication of cerium oxide (CeO₂) nanorods.
• Development of a machine learning algorithm for sensor data analysis.
• Real-time colorimetric detection assay for paraoxon.
• Evaluation of sensor selectivity and accuracy.

Main Results:

• The CeO₂ nanorod sensor platform demonstrated real-time colorimetric detection of paraoxon.
• The sensor achieved a high selectivity for paraoxon.
• The accuracy rate for paraoxon detection reached 90%.
• Selective breaking of P-O bonds in paraoxon by CeO₂ nanorods produced a yellow color, indicating paraoxon presence.

Conclusions:

• Machine learning-assisted CeO₂ nanorod sensors offer a promising approach for selective and accurate real-time paraoxon detection.
• The sensor's mechanism relies on the specific chemical interaction between CeO₂ nanorods and paraoxon.
• This technology has potential applications in environmental monitoring and food safety.