Improving the Quality of Measurements Made by Alphasense NO2 Non-Reference Sensors Using the Mathematical Methods

Leveraging Temporal Information to Improve Machine Learning-Based Calibration Techniques for Low-Cost Air Quality Sensors

Low-cost ambient sensors have been identified as a promising technology for monitoring air pollution at a high spatio-temporal resolution. However, the pollutant data captured by these cost-effective sensors are less accurate than their conventional counterparts and require careful calibration to improve their accuracy and reliability. In this paper, we propose to leverage temporal information, such as the duration of time a sensor has been deployed and the time of day the reading was taken, in order to improve the calibration of low-cost sensors. This information is readily available and has so far not been utilized in the reported literature for the calibration of cost-effective ambient gas pollutant sensors. We make use of three data sets collected by research groups around the world, who gathered the data from field-deployed low-cost CO and NO2 sensors co-located with accurate reference sensors. Our investigation shows that using the temporal information as a co-variate can significantly improve the accuracy of common machine learning-based calibration techniques, such as Random Forest and Long Short-Term Memory.

Unexpected Performance Improvements of Nitrogen Dioxide and Ozone Sensors by Including Carbon Monoxide Sensor Signal

Low-cost air quality (LCAQ) sensors are increasingly being used for community air quality monitoring. However, data collected by low-cost sensors contain significant noise, and proper calibration of these sensors remains a widely discussed, but not yet fully addressed, area of concern. In this study, several LCAQ sensors measuring nitrogen dioxide (NO₂) and ozone (O₃) were deployed in six cities in the United States (Atlanta, GA; New York City, NY; Sacramento, CA; Riverside, CA; Portland, OR; Phoenix, AZ) to evaluate the impacts of different climatic and geographical conditions on their performance and calibration. Three calibration methods were applied, including regression via linear and polynomial models and random forest methods. When signals from carbon monoxide (CO) sensors were included in the calibration models for NO₂ and O₃ sensors, model performance generally increased, with pronounced improvements in selected cities such as Riverside and New York City. Such improvements may be due to (1) temporal co-variation between concentrations of CO and NO₂ and/or between CO and O₃; (2) different performance levels of low-cost CO, NO₂, and O₃ sensors; and (3) different impacts of environmental conditions on sensor performance. The results showed an innovative approach for improving the calibration of NO₂ and O₃ sensors by including CO sensor signals into the calibration models. Community users of LCAQ sensors may be able to apply these findings further to enhance the data quality of their deployed NO₂ and O₃ monitors.

Sensors Network as an Added Value for the Characterization of Spatial and Temporal Air Quality Patterns at the Urban Scale

Within the scope of the Aveiro STEAM City project, an air quality monitoring network was installed in the city of Aveiro (Portugal), to evaluate the potential of sensors to characterize spatial and temporal patterns of air quality in the city. The network consists of nine sensors stations with air quality sensors (PM10, PM2.5, NO₂, O₃ and CO) and two meteorological stations, distributed within selected locations in the city of Aveiro. The analysis of the data was done for a one-year measurement period, from June 2020 to May 2021, using temporal profiles, statistical comparisons with reference stations and Air Quality Indexes (AQI). The analysis of sensors data indicated that air quality variability exists for all pollutants and stations. The majority of the study area is characterized by good air quality, but specific areas-associated with hotspot traffic zones-exhibit medium, poor and bad air quality more frequently. The daily patterns registered are significantly different between the affected and non-affected road traffic sites, mainly for PM and NO₂ pollutants. The weekly profile, significative deltas are found between week and weekend: NO₂ is reduced on the weekends at traffic sites, but PM10 is higher in specific areas during winter weekends, which is explained by residential combustion sources.

Low-Cost CO Sensor Calibration Using One Dimensional Convolutional Neural Network

The advent of cost-effective sensors and the rise of the Internet of Things (IoT) presents the opportunity to monitor urban pollution at a high spatio-temporal resolution. However, these sensors suffer from poor accuracy that can be improved through calibration. In this paper, we propose to use One Dimensional Convolutional Neural Network (1DCNN) based calibration for low-cost carbon monoxide sensors and benchmark its performance against several Machine Learning (ML) based calibration techniques. We make use of three large data sets collected by research groups around the world from field-deployed low-cost sensors co-located with accurate reference sensors. Our investigation shows that 1DCNN performs consistently across all datasets. Gradient boosting regression, another ML technique that has not been widely explored for gas sensor calibration, also performs reasonably well. For all datasets, the introduction of temperature and relative humidity data improves the calibration accuracy. Cross-sensitivity to other pollutants can be exploited to improve the accuracy further. This suggests that low-cost sensors should be deployed as a suite or an array to measure covariate factors.

Low-Cost Nitric Oxide Sensors: Assessment of Temperature and Humidity Effects

High equipment cost is a significant entry barrier to research for small organizations in developing solutions to air pollution problems. Low-cost electrochemical sensors show sensitivity at parts-per-billion by volume mixing ratios but are subject to variation due to changing environmental conditions, in particular temperature. In this study, we demonstrate a low-cost Internet of Things (IoT)-based sensor system for nitric oxide analysis. The sensor system used a four-electrode electrochemical sensor exposed to a series of isothermal/isohume conditions. When deployed under these conditions, stable baseline responses were achieved, in contrast to ambient air conditions where temperature and humidity conditions may be variable. The interrelationship between working and auxiliary electrodes was linear within an environmental envelope of 20-40 °C and 30-80% relative humidity, with correlation coefficients from 0.9980 to 0.9999 when measured under isothermal/isohume conditions. These data enabled the determination of surface functions that describe the working to auxiliary electrode offsets and calibration curve gradients and intercepts. The linear and reproducible nature of individual calibration curves for stepwise nitric oxide (NO) additions under isothermal/isohume environments suggests the suitability of these sensors for applications aside from their role in air quality monitoring. Such applications would include nitric oxide kinetic studies for atmospheric applications or measurement of the potential biocatalytic activity of nitric oxide consuming enzymes in biocatalytic coatings, both of which currently employ high-capital-cost chemiluminescence detectors.