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: In this article, the authors evaluated an Aeroqual Ltd. Series 500 semiconducting metal oxide O3 and an electrochemical NO2 sensor against UK national network reference analysers for more than 2 months at an urban background site in central Edinburgh.
95 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers methods in this paper
...LR models have widely been used as calibration methods for air quality monitoring [27, 110, 71], or as a baseline for comparing the calibration performances of more complex approaches [72, 25, 39]....
[...]
TL;DR: In this article, the performance of low-cost and portable PM sensors under the condition of steady-state particle mass concentration by challenging them with lab-generated particles in different size distributions and compositions was evaluated.
94 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers background in this paper
...Sensors Gas sensor technologies [48, 29, 49, 33] MOS sensors [50] NDIR sensors [51] Portable sensors [52, 53] Wearable sensors [54] Commercial sensors [55, 26] Low-cost sensors quality [56, 57] Usability of low-cost air quality sensors (AQSs) for atmospheric measurements [58] Deployment Cities and projects [33] Calibration Adaptation to drift [42] Optical PM sensors [43, 44] Error sources in calibration [45]...
[...]
01 May 2018
TL;DR: The report highlights that low-cost sensors are not currently a direct substitute for reference instruments, especially for mandatory purposes; they are however a complementary source of information on air quality, provided an appropriate sensor is used.
Abstract: Measurement of reactive air pollutants and greenhouse gases underpin a huge variety of applications that span from academic research through to regulatory functions and services for individuals, governments, and businesses. Whilst the vast majority of these observations continue to use established analytical reference methods, miniaturization has led to a growth in the prominence of a generation of devices that are often described generically as “low-cost sensors” (LCSs). LCSs can in practice have other valuable features other than cost that differentiate them from previous technologies including being of smaller size, lower weight and having reduced power consumption. Different technologies falling within this class include passive electrochemical and metal oxide sensors that may have costs of only a few dollars each, through to more complex microelectromechanical devices that use the same analytical principles as reference instruments, but in smaller size and power packages. As a class of device, low-cost sensors encompass a very wide range of technologies and as a consequence they produce a wide range of quality of measurements. When selecting a LCS approach for a particular task, users need to ensure the specific sensor to be used will meet application’s data quality requirements. This report considers sensors that are designed for the measurement of atmospheric composition at ambient concentrations focusing on reactive gaseous air pollutants (CO, NOx, O3, SO2), particulate matter (PM) and greenhouse gases CO2 and CH4. It examines example applications where new scientific and technical insight may potentially be gained from using a network of sensors when compared to more sparsely located observations. Access to low-cost sensors appears to offer exciting new atmospheric applications, can support new services and potentially facilitates the inclusion of a new cohort of users. Based on the scientific literature available up to the end of 2017, it is clear however that some trade-offs arise when LCSs are used in place of existing reference methods. Smaller and/or lower cost devices tend to be less sensitive, less precise and less chemically-specific to the compound or variable of interest. This is balanced by a potential increase in the spatial density of measurements that can be achieved by a network of sensors. The current state of the art in terms of accuracy, reliability and reproducibility of a range of different sensors is described along with the key analytical principles and what has been learned so far about low-cost sensors from both laboratory studies and real-world tests. A summary of concepts is included on how sensors and reference instruments may be used together, as well as with modelling in a complementary way, to improve data quality and generate additional insight into pollution behaviour. The report provides some advice on key considerations when matching a project/study/application with an appropriate sensor monitoring strategy, and the wider application-specific requirements for calibration and data quality. The report contains a number of suggestions on future requirements for low-cost sensors aimed at manufacturers and users and for the broader atmospheric community. The report highlights that low-cost sensors are not currently a direct substitute for reference instruments, especially for mandatory purposes; they are however a complementary source of information on air quality, provided an appropriate sensor is used. It is important for prospective users to identify their specific application needs first, examine examples of studies or deployments that share similar characteristics, identify the likely limitations associated with using LCSs and then evaluate whether their selected LCS approach/technology would sufficiently meet the needs of the measurement objective. Previous studies in both the laboratory and field have shown that data quality from LCSs are highly variable and there is no simple answer to basic questions like “are low-cost sensors reliable?”. Even when the same basic sensor components are used, real-world performance can vary due to different data correction and calibration approaches. This can make the task of understanding data quality very challenging for users, since good or bad performance demonstrated from one device or commercial supplier does not mean that similar devices from others will work the same way. Manufacturers should provide information on their characterizations of sensors and sensor system performance in a manner that is as comprehensive as possible, including results from in-field testing. Reporting of that data should where possible parallel the metrics used for reference instrument specifications, including information on the calibration conditions. Whilst not all users will actively use this information it will support the general development framework for LCS use. Openness in assessment of sensor performance across varying environmental conditions would be very valuable in guiding new user applications and help the field develop more rapidly. Users and operators of low-cost sensors should have a clearly-defined application scope and set of questions they wish to address prior to selection of a sensor approach. This will guide the selection of the most appropriate technology to support a project. Renewed efforts are needed to enhance engagement and sharing of knowledge and skills between the data science community, the atmospheric science community and others to improve LCS data processing and analysis methods. Improved information sharing between manufacturers and user communities should be supported through regular dialogue on emerging issues related to sensor performance, best practice and applications. Adoption of open access and open data policies to further facilitate the development, applications, and use of LCS data is essential. Such practices would facilitate exchange of information among the wide range of interested communities including national/local government, research, policy, industry, and public, and encourage accountability for data quality and any resulting advice derived from LCS data. This assessment was initiated at the request of the WMO Commission for Atmospheric Sciences (CAS) and supported by broader stakeholder atmospheric community including the International Global Atmospheric Chemistry (IGAC) project, Task Force on Measurement and Modelling of the European Monitoring and Evaluation Programme of the LRTAP Convention, UN Environment, World Health Organization, Network of Air Quality Reference Laboratories of the European Commission (AQUILA).
93 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers background in this paper
...Sensors Gas sensor technologies [48, 29, 49, 33] MOS sensors [50] NDIR sensors [51] Portable sensors [52, 53] Wearable sensors [54] Commercial sensors [55, 26] Low-cost sensors quality [56, 57] Usability of low-cost air quality sensors (AQSs) for atmospheric measurements [58] Deployment Cities and projects [33] Calibration Adaptation to drift [42] Optical PM sensors [43, 44] Error sources in calibration [45]...
[...]
23 Oct 2012
TL;DR: CitiSense is presented, a participatory air quality sensing system that bridges the gap between personal sensing and regional measurement to provide micro-level detail at a regional scale and suggests that the cumulative impact of many individuals using personal sensing devices may have an important role to play in the future of environmental measurement for public health.
Abstract: Environmental exposures are a critical component in the development of chronic conditions such as asthma and cancer. Yet, medical and public health practitioners typically must depend on sparse regional measurements of the environment that provide macro-scale summaries. Recent projects have begun to measure an individual's exposure to these factors, often utilizing body-worn sensors and mobile phones to visualize the data. Such data, collected from many individuals and analyzed across an entire geographic region, holds the potential to revolutionize the practice of public health.We present CitiSense, a participatory air quality sensing system that bridges the gap between personal sensing and regional measurement to provide micro-level detail at a regional scale. In a user study of 16 commuters using CitiSense, measurements were found to vary significantly from those provided by official regional pollution monitoring stations. Moreover, applying geostatistical kriging techniques to our data allows CitiSense to infer a regional map that contains considerably greater detail than official regional summaries. These results suggest that the cumulative impact of many individuals using personal sensing devices may have an important role to play in the future of environmental measurement for public health.
89 citations
"A Gap Analysis of Low-Cost Outdoor ..." refers methods in this paper
...Specifically, these indexes include the following gases: sulfur dioxide (SO2), ozone (O3), carbon monoxide (CO) and nitrogen dioxide (NO2)....
[...]
...For NO, the best model is the FFNN model by Spinelle et al. (2017) [25]; for NOx, the best is the TDNN model by Esposito et al. [78]; for SO2, the best model is the RF model by Borrego et al. (2018) [57]; and for For PM2....
[...]
...RFs models have been widely applied to the calibration of sensors for many pollutants, such as CO [39, 57], CO2 [39], NO2 and O3 [39, 109, 57], NO, SO2, PM2....
[...]
...EC sensors have been used to monitor CO, NO, NO2, O3 and sulphur dioxide (SO2) [77, 71, 70, 72, 25, 78, 79, 39]....
[...]
TL;DR: In this article, a review of recent developments in the field within the context of the establishment/expansion of high spatial and temporal resolution air quality monitoring networks is presented, highlighting the need for investment in the fundamental analytical chemistry of the sensing platforms required to achieve smart-cities.
89 citations