Related Experiment Video
Updated: Mar 27, 2026
07:12
Façade-Level Monitoring of CO2 Variability under Urban Heat Island Conditions using Low-Cost Sensor Data Loggers
Published on: December 12, 2025
285
RAQ-A Random Forest Approach for Predicting Air Quality in Urban Sensing Systems
Ruiyun Yu1, Yu Yang2, Leyou Yang3
1Software College, Northeastern University, Shenyang 110819, China. yury@mail.neu.edu.cn.
Sensors (Basel, Switzerland)
|January 14, 2016
Summary
Predicting urban air quality is crucial for health and city planning. A new random forest approach (RAQ) accurately infers air quality using urban sensing data, outperforming other methods.
Area of Science:
- Environmental Science
- Urban Planning
- Data Science
Background:
- Air quality monitoring is vital for public health and urban management.
- Limited monitoring stations in cities lead to spatial data gaps.
- Air quality exhibits significant variation across urban areas.
Purpose of the Study:
- To propose a novel approach for predicting air quality in urban environments.
- To leverage urban sensing data for enhanced air quality inference.
- To improve the accuracy of air quality predictions in data-scarce regions.
Main Methods:
- Development of a Random Forest Approach for Air Quality prediction (RAQ).
- Utilized diverse urban sensing data: meteorology, road information, traffic status, and Point of Interest (POI) distribution.
- Employed the random forest algorithm for data training and predictive modeling.
Main Results:
- RAQ demonstrated superior prediction precision compared to three other algorithms.
- Experiments validated the high accuracy of inferring air quality from urban sensing data.
- The approach successfully predicted air quality with "amazingly high accuracy".
Conclusions:
- The proposed RAQ method offers a highly accurate solution for urban air quality prediction.
- Urban sensing data provides a rich source for inferring localized air quality.
- This approach can significantly enhance urban sensing systems for environmental monitoring.
