Air Quality AI: Spatiotemporal Fusion, Concept Drift & Forecasting

To provide participants with a strong understanding of air quality analytics by focusing on accurate measurement techniques, sensor drift identification, and intelligent detection methods for reliable environmental monitoring and data-driven decision-making.

• Understand key air quality parameters and monitoring methods.
• Learn the basics of sensor drift and its impact on data accuracy.
• Explore methods for drift analysis, calibration, and correction.
• Identify pollution patterns and anomalies using analytics.
• Apply air quality data for effective environmental monitoring and decision-making.

 Day 1 Air Quality Components and Common Pollutants

• Air Quality Components, measurements and WHO Standards ( PM_2.5 –PM₁₀  )
• Data Sources: Ground-based sensors, satellite imagery, and meteorological data,
• Analytics Techniques time-series analysis for daily/seasonal trends, regression analysis, and spatial mapping of pollution.
• Monitoring and Visualization Methods: Ambient Air Monitoring Method, maps and dashboards (e.g., Air Gradient) that visualize pollution hotspots.
• Measure Air Quality Index and AI tools for Air Quality measure ,WHO Standards
• Hands-on: Google AI Air View, IQAir Air Visual, Computer Vision and Geospatial AI

Day 2 : Real-time monitoring  systems and Drift Systems

• Components, Data Flow, Sensors (PM_2.5, PM_{10 ,}CO, VOCs), Microcontrollers (Node MCU, ESP8266, Arduino), and communication modules (GPRS/Wi-Fi)
• Data Flow: Sensors detect pollutants, send data to a microcontroller for preprocessing, then transmit to cloud platforms (e.g., Blink) for visualization on mobile/web applications.
• Features: Automated alerts, 24-hour monitoring, and data storage for historical analysis.
• Monitoring Devices : Portable/Low-Cost Sensors: MQ-series (MQ135 for air quality, MQ7 for CO), particulate matter (PM) sensors.
• Commercial Monitors: IQAir AirVisual Pro (measures PM2.5, temperature, humidity).
• Hands –on: Climate Trace: An AI-powered platform that uses satellite data to map and monitor emissions from, major industrial sources like power plants.
• IoT-Enabled AI Sensors: Low-cost, AI-integrated sensors (like the Bosch BME 690) deployed in urban environments or schools to provide real-time data analysis, often using algorithms such as Artificial Neural Networks (ANN) or Random Forest for enhanced accuracy.

Day 3: Air Quality Analytics: Drift & Detect

• Sensor Data Drift & Calibration,
• Pollution Drift and Forecasting Systems
• Air Quality Early Warning System (AQ-EWS)
• Drift Detection Methods, AI/ML for Forecasting and Detection:
• Impact Assessment: Particulate Matter, gaseous,
• Health impact assessments and Specific software for air quality modeling
• Hands-on: Commercial Monitors: IQAir AirVisual Pro (measures PM2.5, , temperature, humidity).EPA REal TIme Geospatial Data Viewer (RETIGO):  sensortoolkit (Python Library):  IQAir AirVisual Platform:  OpenAQ API:  AQI.in API Open-Meteo Air Quality API: Computer Vision for Air Quality

• Students and early researchers in environmental science or data analytics
• Ph.D. scholars, researchers, and academicians
• Environmental engineers and air quality professionals
• AI/ML and data science practitioners working with sensor data
• IoT professionals involved in environmental monitoring
• Industry professionals in sustainability, smart cities, and pollution control