New Study Reveals Urgent Need to Improve Urban Public Transportation Air Quality

Strategic Insights -

Researchers at the Institute of Combustion Problems in Almaty, Kazakhstan, have conducted a study to investigate the air quality within urban public transport, revealing alarming concentrations of CO and PM in the city's metro, buses, and trolleybuses. The study used a low-cost IoT sensor and machine learning models to analyze data from three of the city's busiest transport corridors, highlighting the urgent need to combine real-time monitoring with ventilation upgrades. The research suggests that passenger occupancy is the primary driver of in-cabin pollution, and that machine learning models can effectively capture nonlinear relationships among environmental variables.

Key Takeaways:

  • The study revealed high concentrations of CO and PM in the air quality within Almaty's metro, buses, and trolleybuses, elevating the risk of respiratory and cardiovascular diseases.
  • The use of a low-cost IoT sensor and machine learning models allowed researchers to analyze data from three of the city's busiest transport corridors, identifying passenger occupancy as the primary driver of in-cabin pollution.
  • The study achieved a predictive accuracy of 91.25% using the XGBoost model, demonstrating the effectiveness of machine learning in capturing nonlinear relationships among environmental variables.
  • The research identifies the need to combine real-time monitoring with ventilation upgrades to improve the air quality within urban public transport.
  • The study highlights the practical value of using low-cost IoT technologies and data-driven analytics to safeguard public health in urban mobility systems.
  • The surveyed routes serve Almaty's most densely populated districts, emphasizing the importance of improving ventilation on these lines.

Statistics:

  • The study measured CO concentrations of up to [2] and PM [2.5] in the air quality within Almaty's metro, buses, and trolleybuses.
  • The XGBoost model achieved a predictive accuracy of 91.25% in analyzing data from three of the city's busiest transport corridors.
  • The study collected 10,000 data points from the Tynys mobile IoT device, allowing researchers to identify patterns in in-cabin pollution.

Sources:

  • A Low-Cost IoT Sensor and Preliminary Machine-Learning Feasibility Study for Monitoring In-Cabin Air Quality: A Pilot Case from Almaty. Sensors, 2025,25(14):4521. (Sensors - http://www.mdpi.com/journal/sensors). The publisher for Sensors is MDPI AG. A free version of this journal article is available at https://doi-org.sdpl.idm.oclc.org/10.3390/s25144521.