From a Low-Cost Air Quality Sensor Network to Decision Support Services: Steps towards Data Calibration and Service Development

Developing a Cloud-Based Air Quality Monitoring Platform Using Low-Cost Sensors

Conventional air quality monitoring has been traditionally carried out in a few fixed places with expensive measuring equipment. This results in sparse spatial air quality data, which do not represent the real air quality of an entire area, e.g., when hot spots are missing. To obtain air quality data with higher spatial and temporal resolution, this research focused on developing a low-cost network of cloud-based air quality measurement platforms. These platforms should be able to measure air quality parameters including particulate matter (PM10, PM2.5, PM1) as well as gases like NO, NO2, O3, and CO, air temperature, and relative humidity. These parameters were measured every second and transmitted to a cloud server every minute on average. The platform developed during this research used one main computer to read the sensor data, process it, and store it in the cloud. Three prototypes were tested in the field: two of them at a busy traffic site in Stuttgart, Marienplatz and one at a remote site, Ötisheim, where measurements were performed near busy railroad tracks. The developed platform had around 1500 € in materials costs for one Air Quality Sensor Node and proved to be robust during the measurement phase. The notion of employing a Proportional-Integral-Derivative (PID) controller for the efficient working of a dryer that is used to reduce the negative effect of meteorological parameters such as air temperature and relative humidity on the measurement results was also pursued. This is seen as one way to improve the quality of data captured by low-cost sensors.

Smart Multi-Sensor Calibration of Low-Cost Particulate Matter Monitors

A variety of low-cost sensors have recently appeared to measure air quality, making it feasible to face the challenge of monitoring the air of large urban conglomerates at high spatial resolution. However, these sensors require a careful calibration process to ensure the quality of the data they provide, which frequently involves expensive and time-consuming field data collection campaigns with high-end instruments. In this paper, we propose machine-learning-based approaches to generate calibration models for new Particulate Matter (PM) sensors, leveraging available field data and models from existing sensors to facilitate rapid incorporation of the candidate sensor into the network and ensure the quality of its data. In a series of experiments with two sets of well-known PM sensor manufacturers, we found that one of our approaches can produce calibration models for new candidate PM sensors with as few as four days of field data, but with a performance close to the best calibration model adjusted with field data from periods ten times longer.

Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting

Data-driven forecasts of air quality have recently achieved more accurate short-term predictions. However, despite their success, most of the current data-driven solutions lack proper quantifications of model uncertainty that communicate how much to trust the forecasts. Recently, several practical tools to estimate uncertainty have been developed in probabilistic deep learning. However, there have not been empirical applications and extensive comparisons of these tools in the domain of air quality forecasts. Therefore, this work applies state-of-the-art techniques of uncertainty quantification in a real-world setting of air quality forecasts. Through extensive experiments, we describe training probabilistic models and evaluate their predictive uncertainties based on empirical performance, reliability of confidence estimate, and practical applicability. We also propose improving these models using "free" adversarial training and exploiting temporal and spatial correlation inherent in air quality data. Our experiments demonstrate that the proposed models perform better than previous works in quantifying uncertainty in data-driven air quality forecasts. Overall, Bayesian neural networks provide a more reliable uncertainty estimate but can be challenging to implement and scale. Other scalable methods, such as deep ensemble, Monte Carlo (MC) dropout, and stochastic weight averaging-Gaussian (SWAG), can perform well if applied correctly but with different tradeoffs and slight variations in performance metrics. Finally, our results show the practical impact of uncertainty estimation and demonstrate that, indeed, probabilistic models are more suitable for making informed decisions.

Optimization-Based Approaches for Minimizing Deployment Costs for Wireless Sensor Networks with Bounded Estimation Errors

As wireless sensor networks have become more prevalent, data from sensors in daily life are constantly being recorded. Due to cost or energy consumption considerations, optimization-based approaches are proposed to reduce deployed sensors and yield results within the error tolerance. The correlation-aware method is also designed in a mathematical model that combines theoretical and practical perspectives. The sensor deployment strategies, including XGBoost, Pearson correlation, and Lagrangian Relaxation (LR), are determined to minimize deployment costs while maintaining estimation errors below a given threshold. Moreover, the results significantly ensure the accuracy of the gathered information while minimizing the cost of deployment and maximizing the lifetime of the WSN. Furthermore, the proposed solution can be readily applied to sensor distribution problems in various fields.