This paper investigates the calibration of low-cost sensors for air pollution. The sensors were deployed on three IoT (Internet of Things) platforms in Spain, Austria, and Italy during the summers of 2017, 2018, and 2019. One of the biggest challenges in the operation of an IoT platform, which has a great impact on the quality of the reported pollution values, is the calibration of the sensors in an uncontrolled environment. This calibration is performed using arrays of sensors that measure cross sensitivities and therefore compensate for both interfering contaminants and environmental conditions. The paper investigates how the fusion of data taken by sensor arrays can improve the calibration process. In particular, calibration with sensor arrays, multi-sensor data fusion calibration with weighted averages, and multi-sensor data fusion calibration with machine learning models are compared. Calibration is evaluated by combining data from various sensors with linear and nonlinear regression models.

This paper shows the result of the calibration process of an IoT platform for the measurement of tropospheric ozone (O3). This platform, formed by sixty nodes, deployed in Italy, Spain and Austria, consisted of one hundred and forty metal-oxide O3 sensors, twenty-five electro-chemical O3 sensors, twenty-five electro-chemical NO2 sensors and sixty temperature and relative humidity sensors. As ozone is a seasonal pollutant, which appears in summer in Europe, the biggest challenge is to calibrate the sensors in a short period of time. In the paper, we compare four calibration methods in the presence of a large data set for model training and we also study the impact of a limited training data set on the long-range predictions. We show that the difficulty in calibrating these sensor technologies in a real deployment is mainly due to the bias produced by the different environmental conditions found in the prediction with respect to those found in the data training phase.

Existing air pollution monitoring networks use reference stations as the main nodes. The addition of low-cost sensors calibrated in-situ with machine learning techniques allows the creation of heterogeneous air pollution monitoring networks. However, current monitoring networks or calibration techniques have limitations in estimating missing data, adding virtual sensors or recalibrating sensors. The use of graphs to represent structured data is an emerging area of research that allows the use of powerful techniques to process and analyze data for air pollution monitoring networks. In this paper, we compare two techniques that rely on structured data, one based on statistical methods and the other on signal smoothness, with a baseline technique based on the distance between nodes and that does not rely on the measured signal data. To compare these techniques, the sensor signal is reconstructed with a supervised method based on linear regression and a semi-supervised method based on Laplacian interpolation, which allows reconstruction even when data is missing. The results, on data sets measuring O3, NO2 and PM10, show that the signal smoothness-based technique behaves better than the other two, and used together with the Laplacian interpolation is near-optimal with respect to the linear regression method. Moreover, in the case of heterogeneous networks, the results show a reconstruction accuracy similar to the in-situ calibrated sensors. Thus, the use of the network data increases the robustness of the network against possible sensor failures.

New advances in sensor technologies and communications in wireless sensor networks have favored the introduction of low-cost sensors for monitoring air quality applications. In this article, we present the results of the European project H2020 CAPTOR, where three testbeds with sensors were deployed to capture tropospheric ozone concentrations. One of the biggest challenges was the calibration of the sensors, as the manufacturer provides them without calibrating. Throughout the paper, we show how short-term calibration using multiple linear regression produces good calibrated data, but instead produces biases in the calculated long-term concentrations. To mitigate the bias, we propose a linear correction based on Kriging estimation of the mean and standard deviation of the long-term ozone concentrations, thus correcting the bias presented by the sensors.

No abstract