Posted Content•
A Gap Analysis of Low-Cost Outdoor Air Quality Sensor In-Field Calibration
13 Dec 2019-
TL;DR: This article presents low-cost sensor technologies, and it survey and assess machine learning-based calibration techniques for their calibration, and presents open questions and directions for future research.
Abstract: In recent years, interest in monitoring air quality has been growing. Traditional environmental monitoring stations are very expensive, both to acquire and to maintain, therefore their deployment is generally very sparse. This is a problem when trying to generate air quality maps with a fine spatial resolution. Given the general interest in air quality monitoring, low-cost air quality sensors have become an active area of research and development. Low-cost air quality sensors can be deployed at a finer level of granularity than traditional monitoring stations. Furthermore, they can be portable and mobile. Low-cost air quality sensors, however, present some challenges: they suffer from crosssensitivities between different ambient pollutants; they can be affected by external factors such as traffic, weather changes, and human behavior; and their accuracy degrades over time. Some promising machine learning approaches can help us obtain highly accurate measurements with low-cost air quality sensors. In this article, we present low-cost sensor technologies, and we survey and assess machine learning-based calibration techniques for their calibration. We conclude by presenting open questions and directions for future research.
Citations
More filters
Queensland University of Technology1, Norwegian Institute for Air Research2, United States Environmental Protection Agency3, University of Surrey4, Hong Kong University of Science and Technology5, Hong Kong Environmental Protection Department6, City University of Hong Kong7, Curtin University8, Southern Cross University9
TL;DR: In this article, the authors conducted a comprehensive literature search including both the scientific and grey literature, and concluded that there is no clear answer to the question, due to a lack of: sensor/monitor manufacturers' quantitative specifications of performance, consensus regarding recommended end-use and associated minimal performance targets of these technologies, and the ability of the prospective users to formulate the requirements for their applications, or conditions of the intended use.
Abstract: Over the past decade, a range of sensor technologies became available on the market, enabling a revolutionary shift in air pollution monitoring and assessment. With their cost of up to three orders of magnitude lower than standard/reference instruments, many avenues for applications have opened up. In particular, broader participation in air quality discussion and utilisation of information on air pollution by communities has become possible. However, many questions have been also asked about the actual benefits of these technologies. To address this issue, we conducted a comprehensive literature search including both the scientific and grey literature. We focused upon two questions: (1) Are these technologies fit for the various purposes envisaged? and (2) How far have these technologies and their applications progressed to provide answers and solutions? Regarding the former, we concluded that there is no clear answer to the question, due to a lack of: sensor/monitor manufacturers' quantitative specifications of performance, consensus regarding recommended end-use and associated minimal performance targets of these technologies, and the ability of the prospective users to formulate the requirements for their applications, or conditions of the intended use. Numerous studies have assessed and reported sensor/monitor performance under a range of specific conditions, and in many cases the performance was concluded to be satisfactory. The specific use cases for sensors/monitors included outdoor in a stationary mode, outdoor in a mobile mode, indoor environments and personal monitoring. Under certain conditions of application, project goals, and monitoring environments, some sensors/monitors were fit for a specific purpose. Based on analysis of 17 large projects, which reached applied outcome stage, and typically conducted by consortia of organizations, we observed that a sizable fraction of them (~ 30%) were commercial and/or crowd-funded. This fact by itself signals a paradigm change in air quality monitoring, which previously had been primarily implemented by government organizations. An additional paradigm-shift indicator is the growing use of machine learning or other advanced data processing approaches to improve sensor/monitor agreement with reference monitors. There is still some way to go in enhancing application of the technologies for source apportionment, which is of particular necessity and urgency in developing countries. Also, there has been somewhat less progress in wide-scale monitoring of personal exposures. However, it can be argued that with a significant future expansion of monitoring networks, including indoor environments, there may be less need for wearable or portable sensors/monitors to assess personal exposure. Traditional personal monitoring would still be valuable where spatial variability of pollutants of interest is at a finer resolution than the monitoring network can resolve.
138 citations
TL;DR: In this paper, low-cost air quality sensors (LCAQS) can be deployed in dense monitoring networks to provide timely and comprehensive snapshots of pollutant concentrations and their spatial and temporal variability at various scales with relatively less cost and labor.
Abstract: As a potential complement to traditional regulatory instruments, low-cost air quality sensors (LCAQS) can be deployed in dense monitoring networks to provide timely and comprehensive snapshots of pollutant concentrations and their spatial and temporal variability at various scales with relatively less cost and labor. However, a lack of practical guidance and a limited understanding of sensor data quality hinder the widespread application of this emerging technology. We leveraged air quality data collected from state and local monitoring agencies in metropolitan areas of the United States to evaluate how low-cost sensors could be deployed across the U.S. We found that ozone, as a secondary pollutant, is more homogeneous than other pollutants at various scales. PM2.5, CO, and NO2 displayed homogeneities that varied by city, making it challenging to design a uniform network that was suitable across geographies. Our low-cost sensor data in New York City indicated that PM2.5 sensors track well with light-scattering reference methods, particularly at low concentrations. The same phenomenon was also found after thoroughly evaluating sensor evaluation reports from the Air Quality Sensor Performance Evaluation Center (AQ-SPEC). Furthermore, LCAQS data collected during wildfire episodes in Portland, OR show that a real-time (i.e. in situ) machine learning calibration process is a promising approach to address the data quality challenges persisting in LCAQS applications. Our research highlights the urgency and importance of practical guidance for deploying LCAQS.
7 citations
2 citations
References
More filters
TL;DR: This work addresses the development of practical models for understanding and quantifying the signal response of electrolytic sensors that compensate for confounding effects on the sensor response, and address other issues that affect the usability of low-cost sensors, such as sensor drift and inter-sensor variability.
Abstract: Traditional air quality monitoring relies on point measurements from a small number of high-end devices. The recent growth in low-cost air sensing technology stands to revolutionize the way in which air quality data are collected and utilized. While several technologies have emerged in the field of low-cost monitoring, all suffer from similar challenges in data quality. One technology that shows particular promise is that of electrolytic (also known as amperometric) sensors. These sensors produce an electric current in response to target pollutants. This work addresses the development of practical models for understanding and quantifying the signal response of electrolytic sensors. Such models compensate for confounding effects on the sensor response, such as ambient temperature and humidity, and address other issues that affect the usability of low-cost sensors, such as sensor drift and inter-sensor variability.
71 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers background in this paper
...The main drawback of low-cost air quality sensors, however, is that their accuracy tends to be poor compared to professional monitoring stations [30, 31, 32, 33]....
[...]
...Measurements can also be affected by temperature, humidity and wind direction [32]....
[...]
...Periodic calibration alone, however, is not sufficient, since sensors are vulnerable to cross-sensitivities between different pollutants [31] and variations in atmospheric conditions, with temperature, humidity, and wind direction being examples of factors that influence the performance of sensors [32]....
[...]
TL;DR: This study has demonstrated the utility and affordability of the GSS technology for a variety of applications, and the effectiveness of this technology as a means substantially and economically to extend the coverage of an air quality monitoring network.
Abstract: A cost-efficient technology for accurate surface ozone monitoring using gas-sensitive semiconducting oxide (GSS) technology, solar power, and automated cell-phone communications was deployed and validated in a 50 sensor test-bed in the Lower Fraser Valley of British Columbia, over 3 months from May-September 2012. Before field deployment, the entire set of instruments was colocated with reference instruments for at least 48 h, comparing hourly averaged data. The standard error of estimate over a typical range 0-50 ppb for the set was 3 ± 2 ppb. Long-term accuracy was assessed over several months by colocation of a subset of ten instruments each at a different reference site. The differences (GSS-reference) of hourly average ozone concentration were normally distributed with mean -1 ppb and standard deviation 6 ppb (6000 measurement pairs). Instrument failures in the field were detected using network correlations and consistency checks on the raw sensor resistance data. Comparisons with modeled spatial O3 fields demonstrate the enhanced monitoring capability of a network that was a hybrid of low-cost and reference instruments, in which GSS sensors are used both to increase station density within a network as well as to extend monitoring into remote areas. This ambitious deployment exposed a number of challenges and lessons, including the logistical effort required to deploy and maintain sites over a summer period, and deficiencies in cell phone communications and battery life. Instrument failures at remote sites suggested that redundancy should be built into the network (especially at critical sites) as well as the possible addition of a "sleep-mode" for GSS monitors. At the network design phase, a more objective approach to optimize interstation distances, and the "information" content of the network is recommended. This study has demonstrated the utility and affordability of the GSS technology for a variety of applications, and the effectiveness of this technology as a means substantially and economically to extend the coverage of an air quality monitoring network. Low-cost, neighborhood-scale networks that produce reliable data can be envisaged.
70 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers background in this paper
...The main drawback of low-cost air quality sensors, however, is that their accuracy tends to be poor compared to professional monitoring stations [30, 31, 32, 33]....
[...]
TL;DR: In this paper, a model based on a stepwise approach to time-series analysis was applied to the daily average concentrations of strong acidity (SA) and black smoke (BS) in the Oporto area, using an available computer program.
69 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers background in this paper
...Furthermore, seasonal patterns also have a significant influence on them [100, 101, 102]....
[...]
TL;DR: HazeEst is introduced—a machine learning model that combines sparse fixed-station data with dense mobile sensor data to estimate the air pollution surface for any given hour on any given day in Sydney, and shows that SVR not only yields high spatial resolution estimates that correspond well with the pollution surface obtained from fixed and mobile sensor monitoring systems, but also indicates boundaries of polluted area better than other regression models.
Abstract: Metropolitan air pollution is a growing concern in both developing and developed countries. Fixed-station monitors, typically operated by governments, offer accurate but sparse data, and are increasingly being augmented by lower fidelity but denser measurements taken by mobile sensors carried by concerned citizens and researchers. In this paper, we introduce HazeEst—a machine learning model that combines sparse fixed-station data with dense mobile sensor data to estimate the air pollution surface for any given hour on any given day in Sydney. We assess our system using seven regression models and tenfold cross validation. The results show that estimation accuracy of support vector regression (SVR) is similar to decision tree regression and random forest regression, and higher than extreme gradient boosting, multi-layer perceptrons, linear regression, and adaptive boosting regression. The air pollution estimates from our models are validated via field trials, and results show that SVR not only yields high spatial resolution estimates that correspond well with the pollution surface obtained from fixed and mobile sensor monitoring systems, but also indicates boundaries of polluted area better than other regression models. Our results can be visualized using a Web-based application customized for metropolitan Sydney. We believe that the continuous estimates provided by our system can better inform air pollution exposure and its impact on human health.
66 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers methods in this paper
...They have only been used for calibrating CO, and even then only as a baseline for other methods [116]....
[...]
TL;DR: In this article, the influence of mixing layer height (MLH) on concentrations of important pollutants in an urban street canyon of a busy road was studied, and it was found that even in the immediate vicinity (kerbside) to a congested road the concentrations of air pollutants are strongly affected by MLH.
Abstract: Urban areas often suffer from high air pollutant concentrations. To study the influence of the mixing layer height (MLH) on concentrations of important pollutants in an urban street canyon of a busy road, a long-term measurement campaign was performed at the kerb site of an arterial road in Essen, Germany, during the winter 2011/2012 and the early spring in 2012. Considered pollutants were NO, NO 2 , PM 10 , benzene, toluene and isoprene. The MLH was detected continuously using a ceilometer. To study the impact of MLH on pollutant concentrations, the classification scheme of Sturges was applied for the first time for this purpose. It is found that even in the immediate vicinity (kerbside) to a busy road the concentrations of air pollutants are strongly affected by MLH. It is a new result that high quantiles of concentrations decrease stronger with increasing MLH than low quantiles. The strongest correlations between concentrations and MLH are obtained for maximum concentrations with coefficients r from −0.84 to −0.95. In general, maximum concentrations of air pollutants in a street canyon provide stronger correlations with MLH than mean concentrations. NO 2 is the pollutant whose concentration is affected least by MLH because it is mainly a secondary pollutant.
65 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers background in this paper
...For example, seasonality influences the elevation of the atmospheric mixing layer [106], which in turn affects the extent of pollutants that can be captured [107]....
[...]