Crowdsensing IoT Architecture for Pervasive Air Quality and Exposome Monitoring: Design, Development, Calibration,...

Area of Science:

• Environmental Science
• Sensor Technology
• Data Science

Background:

• Accurate air quality assessment is crucial for public health and urban planning.
• Existing monitoring networks often lack the resolution or real-time capabilities needed for effective exposure reduction.
• Personal exposure monitoring is vital for understanding individual health impacts and advancing predictive medicine.

Purpose of the Study:

• To develop and validate an integrated architecture for high-resolution air quality monitoring.
• To enable real-time and cumulative personal exposure assessment.
• To support the validation of advanced air quality predictive models.

Main Methods:

• Development of an integrated system leveraging chemical sensing, machine learning, and Internet of Things (IoT).
• Deployment of a hybrid network combining regulatory-grade and low-cost fixed and mobile sensors.
• Two-year field validation of the developed architecture and monitoring system.

Main Results:

• Successful design, development, and validation of the integrated air quality monitoring architecture.
• Demonstrated capability for high-resolution air quality assessment in urban and mobile scenarios.
• Collected extensive data over two years for system validation and model refinement.

Conclusions:

• The developed integrated architecture effectively addresses the challenges of pervasive air quality assessment.
• The hybrid sensor network provides a robust platform for real-time exposure monitoring and model validation.
• This approach advances the potential for informed public health interventions and predictive health strategies.