Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration

The significance of air pollution and the problems associated with it are fueling deployments quality monitoring stations worldwide. most common approach for is to rely on environmental stations, which unfortunately very expensive both acquire maintain. Hence, typically sparsely deployed, resulting in limited spatial resolution measurements. Recently, low-cost sensors have emerged as an alternative that can improve granularity monitoring. use sensors, however, presents several challenges: They suffer from cross-sensitivities between different ambient pollutants; they be affected by external factors, such traffic, weather changes, human behavior; their accuracy degrades over time. Periodic re-calibration particularly machine-learning-based calibration, has shown great promise due its capability calibrate in-field. In this article, we survey rapidly growing research landscape sensor technologies calibration using machine learning techniques. We also identify open challenges present directions future research.