Air Quality Sensor Network Research Articles

Exploring spatiotemporal dynamics, seasonality, and time-of-day trends of PM2.5 pollution with a low-cost sensor network: Insights from classic and spatially explicit Markov chains

Fine particulate matter (PM2.5) is a major health and environmental concern, with significant spatiotemporal dynamics in urban areas. Low-cost air quality sensor (LCS) networks offer a paradigm-changing opportunity to acquire high spatiotemporal resolution data, revealing the urban pollution landscape with sufficient detail for effective policymaking and health assessment. This study advances geospatial air quality research by using classic and spatial Markov chains to analyze the seasonality and intra-daily variations of PM2.5 using LCS data. Results highlight distinctive PM2.5 seasonality, with the “Good” state predominating in summer and being least common in winter. Midday is the peak period for the “Good” state, while mornings and nights have poorer conditions, suggesting a need for stricter pollution control during evening traffic rush hours. Notably, the impact of temporal scale on spatial Markov analysis is substantial, showing a broader range of air pollution states, increased stability, and reduced variation between time intervals compared to daily assessments. Site-level analysis reveals that rural sites are more likely to maintain “Good” state and less likely to transition out of it. Overall, this study highlights the effectiveness of high spatiotemporal resolution data and demonstrates the capacity of Markov chains to reveal nuances in phenomena such as air pollution.

Montana Statewide Google Earth Engine-Based Wildfire Hazardous Particulate (PM2.5) Concentration Estimation

Wildfires pose a direct threat to the property, life, and well-being of the population of Montana, USA, and indirectly to their health through hazardous smoke and gases emitted into the atmosphere. Studies have shown that elevated levels of particulate matter cause impacts to human health ranging from early death, to neurological and immune diseases, to cancer. Although there is currently a network of ground-based air quality sensors (n = 20) in Montana, the geographically sparse network has large gaps and lacks the ability to make accurate predictions for air quality in many areas of the state. Using the random forest method, a predictive model was developed in the Google Earth Engine (GEE) environment to estimate PM2.5 concentrations using satellite-based aerosol optical depth (AOD), dewpoint temperature (DPT), relative humidity (RH), wind speed (WIND), wind direction (WDIR), pressure (PRES), and planetary-boundary-layer height (PBLH). The validity of the prediction model was evaluated using 10-fold cross validation with a R2 value of 0.572 and RMSE of 9.98 µg/m3. The corresponding R2 and RMSE values for ‘held-out data’ were 0.487 and 10.53 µg/m3. Using the validated prediction model, daily PM2.5 concentration maps (1 km-resolution) were estimated from 2012 to 2023 for the state of Montana. These concentration maps are accessible via an application developed using GEE. The product provides valuable insights into spatiotemporal trends of PM2.5 concentrations, which will be useful for communities to take appropriate mitigation strategies and minimize hazardous PM2.5 exposure.

IoT Based Air Pollution Monitoring System

Abstract: In light of the growing concern for air quality and its impact on public health, there is an increasing demand for air pollution monitoring systems that are both effective and efficient. This article introduces an IoT-based Air Pollution Detection System that utilizes the power of Internet of Things (IoT) technology to provide real-time monitoring and analysis of air quality parameters. The system incorporates a network of advanced air quality sensors that can measure particulate matter (PM) concentrations, as well as various gas levels such as carbon dioxide (CO2), carbon monoxide (CO), nitrogen dioxide (NO2), sulfur dioxide (SO2), and ozone (O3). These sensors are integrated with a microcontroller that enables data processing and communication capabilities.

RPCA-based techniques for pattern extraction, hotspot identification and signal correction using data from a dense network of low-cost NO2 sensors in London

High-density low-cost air quality sensor networks are a promising technology to monitor air quality at high temporal and spatial resolution. However the collected data is high-dimensional and it is not always clear how to best leverage this information, particularly given the lower data quality coming from the sensors. Here we report on the use of robust Principal Component Analysis (RPCA) using nitrogen dioxide data obtained from a recently deployed dense network of 225 air pollution monitoring nodes based on low-cost sensors in the Borough of Camden in London. RPCA addresses the brittleness of singular value decomposition towards outliers by using a decomposition of the data into low-rank and sparse contributions, with the latter containing outliers. The modal decomposition enabled by RPCA identifies major periodic patterns including spatial and temporal bias, dominant spatial variance, and north-south bias. The five most descriptive components capture 98 % of the data's variance, achieving a compression by a factor of 1500. We present a new technique that uses the sparse part of the data to identify hotspots. The data indicates that at the locations of the top 15 % most susceptible nodes in the network, the model identifies 23 % more hotspots than in all other locations combined. Moreover, the median hotspot event at these at-risk locations exceeds the mean NO2concentration by 33μg/m3. We show the potential of RPCA for signal correction; it corrects random errors yielding a reference signal with R2>0.8. Moreover, RPCA successfully reconstructs missing data from a sensor with R2=0.72 from the rest of the sensor network, an improvement upon PCA of around 50 %, allowing air quality estimations even if a sensor is out of use temporarily.

Using synthetic data to benchmark correction methods for low-cost air quality sensor networks

A benchmark was performed, comparing the results of three different methodologies proposed by three institutions to calibrate a network of low-cost PM2.5 sensors, on an hourly basis, using synthetically generated real concentrations and sensor measurements. The objective of the network calibrations was to correct the 2000+ sensor measurements in the Netherlands for the sensitivity to (local) environmental conditions. The option to use real measurements was dropped because the number of low-cost sensors sufficiently close to the 40 reference measurement locations was assessed to be spatially insufficient to benchmark the proposed approaches. Instead, synthetic real concentrations were generated to enable validation at all sensor locations. Hourly actual sensor and actual fixed concentrations, as well as interpolated concentration maps, were used as underlying data to generate the synthetic data sets for the period of 1 month. The synthetic sensor measurement errors were constructed by sampling from a collection of differences between actual sensor values and actual measurements. Of the three tested calibration methods, two follow a similar approach, although having differences in, e.g., outlier analyses and method of grouping sensors, leading also to comparable corrections to the raw sensor measurements. A third method uses significantly stricter rules in outlier selection, discarding considerably more sensors because of insufficient quality. Differences between the methods become most apparent when analyzing data at a smaller time scale. It is shown that two network calibration methods are better at correcting the hourly/daily bias.

Application of roadside air purifiers in urban street canyons: A pilot-scale study in Hong Kong

The implementation of roadside air purifiers has emerged as an effective active control measure to alleviate air pollution in urban street canyons. However, technical questions raised under real conditions remain challenging. In this study, we conducted a pilot-scale investigation involving seven units of self-designed roadside air purifiers in an urban street canyon in Hong Kong. The air cleaning effects were quantified with an air quality sensor network after rigorous quality control. The removal efficiencies of Nitrogen dioxide (NO2), Fine suspended particulates (PM2.5), Carbon monoxide (CO), and Nitric oxide (NO) were determined by comparing with simultaneously measured ambient concentrations, with hourly average efficiencies of 14.0 %–16.9 %, 3.5–10.0 %, 11.9 %–18.7 %, and 19.2 %–44.9 %, respectively. Generally, the purification effects presented variations depending on the ambient pollutants' levels. Higher ambient concentrations of NO2, PM2.5, CO correlated with increased purification effects, while NO presented the opposite trend. The influence of interval distance combined with spatial distribution indicated the operation of purifiers will induce local NO2 attenuation even at an interval distance of four meters. Statistical analysis delivered evidence the air cleaning ability exhibited optimal performance when relative humidity level is ranged from 70 % to 90 %, aligning with the prevailing conditions in Hong Kong. Additionally, improved purification effects were observed at the downwind direction, and their performance was enhanced when the wind speed exceeded 2.5 m/s. Moreover, we estimated the operational lifetime of the air purifiers to be approximately 130 days, offering crucial information regarding the filter replacement cycle. This work serves as a pioneering case study, showcasing the feasibility and deployment considerations of roadside air purifiers in effectively controlling air pollution in urban environments.

Spectral analysis approach for assessing the accuracy of low-cost air quality sensor network data

Abstract. Extensive monitoring of particulate matter (PM) smaller than 2.5 µm, i.e., PM2.5, is critical for understanding changes in local air quality due to policy measures. With the emergence of low-cost air quality sensor networks, high spatiotemporal measurements of air quality are now possible. However, the sensitivity, noise, and accuracy of field data from such networks are not fully understood. In this study, we use spectral analysis of a 2-year data record of PM2.5 from both the Environmental Protection Agency (EPA) and PurpleAir (PA), a low-cost sensor network, to identify the contributions of individual periodic sources to local air quality in Chicago. We find that sources with time periods of 4, 8, 12, and 24 h have significant but varying relative contributions to the data for both networks. Further analysis reveals that the 8 and 12 h sources are traffic-related and photochemistry-driven, respectively, and that the contributions of both these sources are significantly lower in the PA data than in the EPA data. The presence of distinct peaks in the power spectrum analysis highlights recurring patterns in the air quality data; however, the underlying factors contributing to these peaks require further investigation and validation. We also use a correction model that accounts for the contribution of relative humidity and temperature, and we observe that the PA temporal components can be made to match those of the EPA over the medium and long term but not over the short term. Thus, standard approaches to improve the accuracy of low-cost sensor network data will not result in unbiased measurements. The strong source dependence of low-cost sensor network measurements demands exceptional care in the analysis of ambient data from these networks, particularly when used to evaluate and drive air quality policies.

Image-based Air Quality Prediction using Convolutional Neural Networks and Machine Learning

Air quality has become a major public concern due to the significant threat posed by air pollution to human health, and rapid and efficient monitoring of air quality is crucial for pollution control and human health. In this paper, deep learning and image-based models are proposed to estimate air quality. To evaluate the level of air quality, the model collects feature information from landscape photos taken by mobile cameras. To analyze public perception of air quality, researchers collected questionnaire data from 257 people. The Smartpls method allows for structural analysis to determine the influence of each variable on other variables and the extent of their contribution to the final variable of overall perception of air quality. This study aims to develop a novel approach for air quality prediction using image-based data and machine learning techniques. The research used convolutional neural networks to extract features from images and predict the air quality index. The study was conducted using a dataset obtained from a network of air quality sensors across the city. The results of the study showed that the proposed approach can provide accurate air quality predictions compared to the traditional methods. The developed model was able to capture the complex relationships between air quality and environmental factors, such as temperature and humidity. The implications of the study suggest that image-based air quality prediction can be a powerful tool for improving public health and reducing the impact of air pollution. The study's findings hold promise for a healthier future by facilitating more effective pollution management and improved air quality regulation. The study's primary novelty lies in its approach to air quality prediction by deploying convolutional neural networks to extract image features for predicting air quality indices. This application of advanced machine learning techniques to image-based data for air quality estimation marks a significant advancement.

Intra- and inter-city variability of PM2.5 concentrations in Greece as determined with a low-cost sensor network

Measurements of PM2.5 concentrations in five major Greek cities over a two-year period using calibrated low-cost sensor-based particulate matter (PM) monitors (Purple Air PA-II) were combined with local meteorological parameters, synoptic patterns and air mass residence time models to investigate the factors controlling PM2.5 spatiotemporal variability over continental Greece. Fourteen sensors nodes in Athens, Patras, Ioannina, Xanthi, and Thermi (in the Metropolitan Area of Thessaloniki) were selected out of more than 100 of a countrywide network for detailed analysis. The cities have populations ranging from 65k to 3M inhabitants and cover different latitudes along the South-North axis. High correlations between the daily average PM2.5 levels were observed among all sites, indicating strong intra- and inter-city covariance of concentrations, both in cold and warm periods. Higher PM2.5 concentrations in all cities during the cold period were primarily associated with low temperatures and stagnant anticyclonic conditions, favoring the entrapment of residential heating emissions from biomass burning. Anticyclonic conditions were also connected to an increased frequency of PM2.5 episodes, exceeding the updated daily guideline value (15 μg m−3) of the World Health Organization (WHO). During the warm period, nearly uniform PM2.5 levels were encountered across continental Greece, independently of their population size. This uniformity strongly suggests the importance of long-range transport and regional secondary aerosol formation for PM2.5 during this period. Peak concentrations were associated mainly with regional northern air flows over Greece and the Balkan Peninsula. The use of the measurements from dense air quality sensor networks, provided that a robust calibration protocol and continuous data quality assurance practices are followed, appears to be an efficient tool to gain insights on the levels and variability of PM2.5 concentrations, underpinning the characterization of spatial and seasonal particularities and supporting real-time public information and warning.

Dense Air Quality Sensor Networks: Validation, Analysis, and Benefits

Air pollution is known to be harmful to human health and the environment. Official air quality monitoring stations have been established across many smart cities around the world. Unfortunately, these monitoring stations are sparsely located and consequently do not provide high-resolution spatio-temporal air quality information. This article demonstrates how a dense sensor network deployment offers significant advantages in providing better and more detailed air quality information. We use data from a dense sensor network consisting of 126 low-cost sensors (LCSs) deployed in a highly populated district in Nanjing, China. Using data obtained from 13 existing reference stations installed in the same district, we propose three LCS validation methods to evaluate the performance of LCSs in the network. The methods assess the reliability, accuracy of tests, and failure and anomaly detection performance. We also demonstrate how the reliable data generated from the sensor network provides deep insights into air pollution information at a higher spatio-temporal resolution. We further discuss potential improvements and applications derived from the dense deployment of LCSs in cities.

Calibrating networks of low-cost air quality sensors

Abstract. Ambient fine particulate matter (PM2.5) pollution is a major health risk. Networks of low-cost sensors (LCS) are increasingly being used to understand local-scale air pollution variation. However, measurements from LCS have uncertainties that can act as a potential barrier to effective decision making. LCS data thus need adequate calibration to obtain good quality PM2.5 estimates. In order to develop calibration factors, one or more LCS are typically co-located with reference monitors for short or long periods of time. A calibration model is then developed that characterizes the relationships between the raw output of the LCS and measurements from the reference monitors. This calibration model is then typically transferred from the co-located sensors to other sensors in the network. Calibration models tend to be evaluated based on their performance only at co-location sites. It is often implicitly assumed that the conditions at the relatively sparse co-location sites are representative of the LCS network overall and that the calibration model developed is not overfitted to the co-location sites. Little work has explicitly evaluated how transferable calibration models developed at co-location sites are to the rest of an LCS network, even after appropriate cross-validation. Further, few studies have evaluated the sensitivity of key LCS use cases, such as hotspot detection, to the calibration model applied. Finally, there has been a dearth of research on how the duration of co-location (short-term or long-term) can impact these results. This paper attempts to fill these gaps using data from a dense network of LCS monitors in Denver deployed through the city's “Love My Air” program. It offers a series of transferability metrics for calibration models that can be used in other LCS networks and some suggestions as to which calibration model would be most useful for achieving different end goals.

The Impacts of Air Quality on Vegetation Health in Dense Urban Environments: A Ground-Based Hyperspectral Imaging Approach

We examine the impact of changes in ozone (O3), particulate matter (PM2.5), temperature, and humidity on the health of vegetation in dense urban environments, using a very high-resolution, ground-based Visible and Near-Infrared (VNIR, 0.4–1.0 μm with a spectral resolution of 0.75 nm) hyperspectral camera deployed by the Urban Observatory (UO) in New York City. Images were captured at 15 min intervals from 08h00 to 18h00 for 30 days between 3 May and 6 June 2016 with each image containing a mix of dense built structures, sky, and vegetation. Vegetation pixels were identified using unsupervised k-means clustering of the pixel spectra and the time dependence of the reflection spectrum of a patch of vegetation at roughly 1 km from the sensor that was measured across the study period. To avoid illumination and atmospheric variability, we introduce a method that measures the ratio of vegetation pixel spectra to the spectrum of a nearby building surface at each time step relative to that ratio at a fixed time. This “Compound Ratio” exploits the (assumed) static nature of the building reflectance to isolate the variability of vegetation reflectance. Two approaches are used to quantify the health of vegetation at each time step: (a) a solar-induced fluorescence indicator (SIFi) calculated as the simple ratio of the amplitude of the Compound Ratio at 0.75 μm and 0.9 μm, and (b) Principal Component Analysis (PCA) decomposition designed to capture more global spectral features. The time dependence of these vegetation health indicators is compared to that of O3, PM2.5, temperature, and humidity values from a distributed and publicly available in situ air quality sensor network. Assuming a linear relationship between vegetation health indicators and air quality indicators, we find that changes in both SIF indicator values and PC amplitudes show a strong correlation (r2 value of 40% and 47%, respectively) with changes in air quality, especially in comparison with nearby buildings used as controls (r2 value of 1% and 4%, respectively, and with all molecular correlations consistent with zero to within 3σ uncertainty). Using the SIF indicator, O3 and temperature exhibit a positive correlation with changes in photosynthetic rate in vegetation, while PM2.5 and humidity exhibit a negative correlation. We estimate full covariant uncertainties on the coefficients using a Markov Chain Monte Carlo (MCMC) approach and demonstrate that these correlations remain statistically significant even when controlling for the effects of diurnal sun-sensor geometry and temperature variability. This work highlights the importance of quantifying the effects of various air quality parameters on vegetation health in urban environments in order to uncover the complexity, covariance, and interdependence of the numerous factors involved.

Network of low-cost air quality sensors for monitoring indoor, outdoor, and personal PM2.5 exposure in Seattle during the 2020 wildfire season

The increased frequency of wildfires in the Western United States has raised public awareness of the impact of wildfire smoke on air quality and human health. Exposure to wildfire smoke has been linked to an increased risk of cancer and cardiorespiratory morbidity. Evidence-driven interventions can alleviate the adverse health impact of wildfire smoke. During wildfires, public health guidance is based on regional air quality data with limited spatiotemporal resolution. Recently, low-cost air quality sensors have been used in air quality studies, given their ability to capture high-resolution spatiotemporal data. We demonstrate the use of a network of low-cost particulate matter (PM) sensors to gather indoor and outdoor PM2.5 data from seven locations in the urban Seattle area, along with a personal exposure monitor worn by a resident living in one of these locations during the 2020 Washington wildfire event. The data were used to determine PM concentration indoor/outdoor (I/O) ratios, PM reduction, and personal exposure levels. The result shows that locations equipped with high-efficiency particulate air (HEPA) filters and HVAC filtration systems had significantly lower I/O ratios (median I/O = 0.43) than those without air filtration (median I/O = 0.82). The median PM2.5 reduction for the locations with HEPA is 58% compared to 20% for the locations without HEPA. The outdoor PM sensor showed a high correlation to the nearby regional air quality monitoring stations (pre-calibration R2 = 0.92). The personal monitor showed higher variance in PM measurements as the user moved through different microenvironments and could not be fully characterized by the network of indoor or outdoor monitors. The findings imply that evidence-based interventions can be developed to reduce pollution exposure when combining data from indoor and outdoor sensors. Personal exposure monitoring captured temporal spikes in PM exposure.

Air Quality Sensor Networks for Evidence-Based Policy Making: Best Practices for Actionable Insights

(1) Background: This work evaluated the usability of commercial “low-cost” air quality sensor systems to substantiate evidence-based policy making. (2) Methods: Two commercially available sensor systems (Airly, Kunak) were benchmarked at a regulatory air quality monitoring station (AQMS) and subsequently deployed in Kampenhout and Sint-Niklaas (Belgium) to address real-world policy concerns: (a) what is the pollution contribution from road traffic near a school and at a central city square and (b) do local traffic interventions result in quantifiable air quality impacts? (3) Results: The considered sensor systems performed well in terms of data capture, correlation and intra-sensor uncertainty. Their accuracy was improved via local re-calibration, up to data quality levels for indicative measurements as set in the Air Quality Directive (Uexp < 50% for PM and <25% for NO2). A methodological setup was proposed using local background and source locations, allowing for quantification of the (3.1) maximum potential impact of local policy interventions and (3.2) air quality impacts from different traffic interventions with local contribution reductions of up to 89% for NO2 and 60% for NO throughout the considered 3 month monitoring period; (4) Conclusions: Our results indicate that commercial air quality sensor systems are able to accurately quantify air quality impacts from (even short-lived) local traffic measures and contribute to evidence-based policy making under the condition of a proper methodological setup (background normalization) and data quality (recurrent calibration) procedure. The applied methodology and learnings were distilled in a blueprint for air quality sensor networks for replication actions in other cities.

Learning Calibration Functions on the Fly: Hybrid Batch Online Stacking Ensembles for the Calibration of Low-Cost Air Quality Sensor Networks in the Presence of Concept Drift

Deployment of an air quality low-cost sensor network (AQLCSN), with proper calibration of low-cost sensors (LCS), offers the potential to substantially increase the ability to monitor air pollution. However, to leverage this potential, several drawbacks must be ameliorated, thus the calibration of such sensors is becoming an essential component in their use. Commonly, calibration takes place in a laboratory environment using gasses of known composition to measure the response and a linear calibration is often reached. On site calibration is a promising complementary technique where an LCS and a reference instrument are collocated with the former being calibrated to match the measurements of the latter. In a scenario where an AQLCSN is already operational, both calibration approaches are resource and time demanding procedures to be implemented as frequently repeated actions. Furthermore, sensors are sensitive to the local meteorology and adaptation is a slow process making relocation a complex and expensive option. We concentrate our efforts in keeping the LCS positions fixed and propose to blend a genetic algorithm (GA) with a hybrid stacking (HS) ensemble into the GAHS framework. GAHS employs a combination of batch machine learning algorithms and regularly updated online machine learning calibration function(s) for the whole network when a small number of reference instruments are present. Furthermore, we introduce the concept of spatial online learning to achieve better spatial generalization. The frameworks are tested for the case of Thessaloniki where a total of 33 devices are installed. The AQLCSN is calibrated on the basis of on-site matching with high quality observations from three reference station measurements. The O3 LCS are successfully calibrated for 8–10 months and the PM10 LCS calibration is evaluated for 13–24 months showing a strong seasonal dependence on their ability to correctly capture the pollution levels.

Ambient Air Quality Measurement with Low-Cost Optical and Electrochemical Sensors: An Evaluation of Continuous Year-Long Operation

Sensor technology is attractive to the public due to its availability and ease of use. However, its usage raises numerous questions. The general trustworthiness of sensor data is widely discussed, especially with regard to accuracy, precision, and long-term signal stability. The VSB-Technical University of Ostrava has operated an air quality sensor network for more than two years, and its large sets of valid results can help in understanding the limitations of sensory measurement. Monitoring is focused on the concentrations of dust particles, NO2, and ozone to verify the impact of newly planted greenery on the reduction in air pollution. The sensor network currently covers an open field on the outskirts of Ostrava, between Liberty Ironworks and the nearby ISKO1650 monitoring station, where some of the worst air pollution levels in the Czech Republic are regularly measured. In the future, trees should be allowed to grow over the sensors, enabling assessment of the green barrier effect on air pollution. As expected, the service life of the sensors varies from 1 to 3 years; therefore, checks are necessary both prior to the measurement and regularly during operation, verifying output stability and overall performance. Results of the PMx sensory measurements correlated well with the reference method. Concentration values measured by NO2 sensors correlated poorly with the reference method, although timeline plots of concentration changes were in accordance. We suggest that a comparison of timelines should be used for air quality evaluations, rather than particular values. The results showed that the sensor measurements are not yet suitable to replace the reference methods, and dense sensor networks proved useful and robust tools for indicative air quality measurements (AQM).

Added Value of Vaisala AQT530 Sensors as a Part of a Sensor Network for Comprehensive Air Quality Monitoring

Poor air quality influences the quality of life in the urban environment. The regulatory observation stations provide the backbone for the city administration to monitor urban air quality. Recently a suite of cost-effective air quality sensors has emerged to provide novel insights into the spatio-temporal variability of aerosol particles and trace gases. Particularly in low concentrations these sensors might suffer from issues related e.g., to high detection limits, concentration drifts and interdependency between the observed trace gases and environmental parameters. In this study we characterize the optical particle detector used in AQT530 (Vaisala Ltd.) air quality sensor in the laboratory. We perform a measurement campaign with a network of AQT530 sensors in Helsinki, Finland in 2020–2021 and present a long-term performance evaluation of five sensors for particulate (PM10, PM2.5) and gaseous (NO2, NO, CO, O3) components during a half-year co-location study with reference instruments at an urban traffic site. Furthermore, short-term (3–5 weeks) co-location tests were performed for 25 sensors to provide sensor-specific correction equations for the fine-tuning of selected pollutants in the sensor network. We showcase the added value of the verified network of 25 sensor units to address the spatial variability of trace gases and aerosol mass concentrations in an urban environment. The analysis assesses road and harbor traffic monitoring, local construction dust monitoring, aerosol concentrations from fireworks, impact of sub-urban small scale wood combustion and detection of long-range transport episodes on a city scale. Our analysis illustrates that the calibrated network of Vaisala AQT530 air quality sensors provide new insights into the spatio-temporal variability of air pollution within the city. This information is beneficial to, for example, optimization of road dust and construction dust emission control as well as provides data to tackle air quality problems arising from traffic exhaust and localized wood combustion emissions in the residential areas.

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

Air pollution is a widespread problem due to its impact on both humans and the environment. Providing decision makers with artificial intelligence based solutions requires to monitor the ambient air quality accurately and in a timely manner, as AI models highly depend on the underlying data used to justify the predictions. Unfortunately, in urban contexts, the hyper-locality of air quality, varying from street to street, makes it difficult to monitor using high-end sensors, as the cost of the amount of sensors needed for such local measurements is too high. In addition, development of pollution dispersion models is challenging. The deployment of a low-cost sensor network allows a more dense cover of a region but at the cost of noisier sensing. This paper describes the development and deployment of a low-cost sensor network, discussing its challenges and applications, and is highly motivated by talks with the local municipality and the exploration of new technologies to improve air quality related services. However, before using data from these sources, calibration procedures are needed to ensure that the quality of the data is at a good level. We describe our steps towards developing calibration models and how they benefit the applications identified as important in the talks with the municipality.

High-Resolution Assessment of Air Quality in Urban Areas—A Business Model Perspective

The increasing availability of low-cost air quality sensors has led to novel sensing approaches. Distributed networks of low-cost sensors, together with data fusion and analytics, have enabled unprecedented, spatiotemporal resolution when observing the urban atmosphere. Several projects have demonstrated the potential of different approaches for high-resolution measurement networks ranging from static, low-cost sensor networks over vehicular and airborne sensing to crowdsourced measurements as well as ranging from a research-based operation to citizen science. Yet, sustaining the operation of such low-cost air quality sensor networks remains challenging because of the lack of regulatory support and the lack of an organizational framework linking these measurements to the official air quality network. This paper discusses the logical inclusion of lower-cost air quality sensors into the existing air quality network via a dynamic field calibration process, the resulting sustainable business models, and how this expansion can be self-funded.

Improving data reliability: A quality control practice for low-cost PM2.5 sensor network.

Low-cost air quality sensor networks have been increasingly used for high spatial resolution air quality monitoring in recent years. Ensuring data reliability during continuous operation is critical for these sensor networks. Using particulate matter sensor as an example, this study reports a data quality control method, including sensor selection, pre-calibration, and online inspection. It was used in developing and operating the dense low-cost particle sensor networks in two Chinese cities. Firstly, seven mainstream sensors were tested and one model of particle sensor was selected due to its better linearity and stability. For a batch of sensors of the same model, although they were calibrated after manufactured, there are differences in response toward the same concentration of pollutants. The systematical variation of sensors was corrected and unified through pre-calibration. After deploying them in the field, a data analysis method is established for online inspecting their working status. Using data from these sensors, it evaluates parameters such as intraclass correlation coefficients and normalized root mean square error. These two metrics help to construct a two-dimensional coordinate system and to classify sensors into four status, including normal, fluctuation, hotspots, and malfunction. During a one-month operation in the two cities, 8 (out of 82) and 10 (out of 59) sensors with suspected malfunctions were screened out for further on-site inspection. Moreover, the sensor networks show potential in identifying illegal emission sources that cannot be typically detected by sparse regulatory air quality monitoring stations.