Air Pollution Sensors Research Articles

A study on extending the use of air quality monitor data via deep learning techniques

As the environmental awareness of urban citizens increases, traditional air quality monitoring stations cannot satisfy the need for air quality data at high temporal and spatial resolution due to their high construction and maintenance costs. Low-cost air quality monitors are being increasingly used for this purpose because of their portability and affordable price. However, low-cost monitors are usually beset by data quality issues, and the number of mounted air pollutant sensors is limited by the restriction of the cost and size of monitors. Therefore, we propose to extend the use of air quality monitor data via a deep learning technique called long short-term memory (LSTM). The extension is embodied in two aspects: first, calibration of air pollutant concentration data; and second, provision of indicative information about air pollutants where no corresponding sensors are available. A low-cost air quality monitor called KOALA (Knowing Our Ambient Local Air Quality), which was deployed in Sydney (Australia), was used as an example to prove this method’s feasibility. Data from a 90-day period were used for model training, and data from a 30-day period were used for model validation. Random forest models were used for selecting the most useful LSTM model input variables. Historical 24-h information was incorporated to improve the performance of the LSTM models. The results showed that: first, LSTM models can be used to calibrate KOALA carbon monoxide (CO) data with the optimum input being raw CO measurements and the corresponding standard deviation information; and second, LSTM models can be used to estimate ozone concentration with the optimum input being CO concentration and three meteorological parameters [i.e. top soil layer temperature, 10 m U wind (earth-relative), and net shortwave radiation flux at the ground] generated through a deterministic model known as WRF (Weather Research and Forecasting). In addition, the LSTM ozone estimation model showed good performance at both the training location and a location 11 km away, indicating that the proposed method can be used to provide indicative information about air pollutants around the training location.

Monitoring Excess Exposure to Air Pollution for Professional Drivers in London Using Low-Cost Sensors

In this pilot study, low-cost air pollution sensor nodes were fitted in waste removal trucks, hospital vans and taxis to record drivers’ exposure to air pollution in Central London. Particulate matter (PM 2.5 and PM 10 ), CO 2 , NO 2 , temperature and humidity were recorded in real-time with nodes containing low-cost sensors, an electrochemical gas sensor for NO 2 , an optical particle counter for PM 2.5 and PM 10 and a non-dispersive infrared (NDIR) sensor for CO 2 , temperature and relative humidity. An intervention using a pollution filter to trap PM and NO 2 was also evaluated. The measurements were compared with urban background and roadside monitoring stations at Honor Oak Park and Marylebone Road, respectively. The vehicle records show PM and NO 2 concentrations similar to Marylebone Road and a higher NO 2 -to-PM ratio than at Honor Oak Park. Drivers are exposed to elevated pollution levels relative to Honor Oak Park: 1.72 μ g m − 3 , 1.92 μ g m − 3 and 58.38 ppb for PM 2.5 , PM 10 , and NO 2 , respectively. The CO 2 levels ranged from 410 to over 4000 ppm. There is a significant difference in average concentrations of PM 2.5 and PM 10 between the vehicle types and a non-significant difference in the average concentrations measured with and without the pollution filter within the sectors. In conclusion, drivers face elevated air pollution exposure as part of their jobs.

Developing of Low-Cost Air Pollution Sensor-Measurements with the Unmanned Aerial Vehicles in Poland.

This article presents the capabilities and selected measurement results from the newly developed low-cost air pollution measurement system mounted on an unmanned aerial vehicle (UAV). The system is designed and manufactured by the authors and is intended to facilitate, accelerate, and ensure the safety of operators when measuring air pollutants. It allows the creation of three-dimensional models and measurement visualizations, thanks to which it is possible to observe the location of leakage of substances and the direction of air pollution spread by various types of substances. Based on these models, it is possible to create area audits and strategies for the elimination of pollution sources. Thanks to the usage of a multi-socket microprocessor system, the combination of nine different air quality sensors can be installed in a very small device. The possibility of simultaneously measuring several different substances has been achieved at a very low cost for building the sensor unit: 70 EUR. The very small size of this device makes it easy and safe to mount it on a small drone (UAV). Because of this device, many harmful chemical compounds such as ammonia, hexane, benzene, carbon monoxide, and carbon dioxide, as well as flammable substances such as hydrogen and methane, can be detected. Additionally, a very important function is the ability to perform measurements of PM2.5 and PM10 suspended particulates. Thanks to the use of UAV, the measurement is carried out remotely by the operator, which allows us to avoid the direct exposure of humans to harmful factors. A big advantage is the quick measurement of large spaces, at different heights above the ground, in different weather conditions. Because of the three-dimensional positioning from GPS receiver, users can plot points and use colors reflecting a concentration of measured features to better visualize the air pollution. A human-friendly data output can be used to determine the mostly hazardous regions of the sampled area.

Evaluation of air quality in Sunway City, Selangor, Malaysia from a mobile monitoring campaign using air pollution micro-sensors

Due to the increase of the human population and the rapid industrial growth in the past few decades, air quality monitoring is essential to assess the pollutant levels of an area. However, monitoring air quality in a high-density area like Sunway City, Selangor, Malaysia is challenging due to the limitation of the local monitoring network. To establish a comprehensive data for air pollution in Sunway City, a mobile monitoring campaign was employed around the city area with a duration of approximately 6 months, from September 2018 to March 2019. Measurements of air pollutants such as carbon dioxide (CO2) and nitrogen dioxide (NO2) were performed by using mobile air pollution sensors facilitated with a GPS device. In order to acquire a more in-depth understanding on traffic-related air pollution, the measurement period was divided into two different time blocks, which were morning hours (8 a.m.–12 p.m.) and afternoon hours (3 p.m.–7 p.m.). The data set was analysed by splitting Sunway City into different zones and routes to differentiate the conditions of each region. Meteorological variables such as ambient temperature, relative humidity, and wind speed were studied in line with the pollutant concentrations. The air quality in Sunway City was then compared with various air quality standards such as Malaysian Air Quality Standards and World Health Organisation (WHO) guidelines to understand the risk of exposure to air pollution by the residence in Sunway City.

Spatial modelling of particulate matter air pollution sensor measurements collected by community scientists while cycling, land use regression with spatial cross-validation, and applications of machine learning for data correction

Abstract Fine particulate matter air pollution is a global issue; cycling is a global activity. In our paper, particulate matter less than 2.5 μm (PM2.5) air pollution data obtained by community scientists while cycling is used to develop high-resolution spatial air pollution maps. Mapping is completed using a land use regression model for Charlotte, North Carolina. The air pollution observations were obtained with a low-cost sensor. We evaluated the accuracy of the sensor through a collocation study for 3203 h, which identified the sensor had a mean bias of 7.25 μg/m3 and a correlation of r = 0.77 with an US EPA Federal Equivalent Monitor. A machine learning model was developed to adjust the sensor observations, which demonstrated their highest errors during periods of high humidity. The adjustment was able to reduce the root mean squared error from 12 μg/m3 to 3.8 μg/m3, and the mean bias was reduced to −0.5 μg/m3. Cycling times were not balanced throughout the day nor the year. We applied a temporal adjustment algorithm to account for this imbalance in observation periods with the intention of producing long-term estimates representing the sampling period of 2016 and 2017. The long-term air pollution surface for the city was generated with a land use regression model. Both linear regression and machine learning approaches were applied. The linear regression model performed poorly with a training R2 of 0.15 and a cross-validation R2 of 0.15. A stacked ensemble model was developed using machine learning, which had a training 5-fold cross-validation mean residual deviance of 3.82 μg/m3, a root mean squared error of 1.95 μg/m3, and a mean absolute error of 0.95 μg/m3. Performance remained strong during cross-validation, which included both a random sample approach (RMSE = 1.52 μg/m3) and a spatial blocking cross-validation method (RMSE = 2.8 μg/m3).

Multisensor Data Fusion Calibration in IoT Air Pollution Platforms

This article investigates the calibration of low-cost sensors for air pollution. The sensors were deployed on three Internet of Things (IoT) 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. This article investigates how the fusion of data taken by sensor arrays can improve the calibration process. In particular, calibration with sensor arrays, multisensor data fusion calibration with weighted averages, and multisensor data fusion calibration with machine learning models are compared. Calibration is evaluated by combining data from various sensors with linear and nonlinear regression models.

The performance assessment of low-cost air pollution sensor in city and the prospect of the autonomous vehicle for air pollution reduction

Urban air pollution is clearly a constantly growing problem and the high level of urban air pollution has been shown to pose a significant risk to city dwellers. It is necessary to have low-cost sensors for data collection, ready data source allowing normal citizen to access to and gain information, and have prospect solutions (e.g. autonomous vehicle) for air pollution reduction in the city. The aim of the study is to illustrate the drivers behind the use of low-cost sensors and to review the performance of sensors. In addition, autonomous vehicle is expected to reduce pollution; therefore, the paper analyzes the benefits and adoption of autonomous vehicles in the future. The challenges and outlook for both low-cost sensor deployment and the adoption of self-driving vehicle will also be discussed. A literature review is used to obtain these aims. The study indicates that the main driver of low-cost sensor is to provide high-density spatiotemporal pollution data, assisting in creating emission inventories of pollutants and detecting pollution hotspots without capital investments. A number of performance aspects considered include the coefficients of determination (R2), variance (CV), repeatability, reproducibly and stability of the sensor. Self-driving vehicle is promising in the change of travel patterns and having impacts on the health of society. Technology and economic challenges, the willingness to use the sensor and the autonomous policy approach are the major challenges. In terms of the outlook, standard guidelines and the calibration methods for low-cost sensors, energy consumption savings and policy supporting for autonomous vehicle should be further investigated.

Design of Quadrotor UAV and Internet-of-Things Based Air Pollution Monitoring Systems

Air pollution is one of problems causing global warming that is currently taking a place. Several air quality monitoring devices usually located at the city center are only limited to display data at one point. Therefore, a mobile device to monitor air quality is needed so as to enable the monitoring in several points. This paper aims to design an air quality monitoring system based on quadrotor Unmanned Aerial Vehicle (UAV) and Internet-of-Things (IoT) technology. The sensor system is designed to detect CO, CO2, air quality, and temperature variables. This sensor systems was then integrated with quadrotor in order to make the monitoring process can be carried out at various points. Quadrotor was designed using Ardupilot Mega (APM) 2.6 as the flight controler. Measurement data from system sensor was transmitted wirelessly using internet network via Wi-Fi module. Based on the test results, the sensor system was able to detect concentration of several test gas and was linear to the output voltage. Quadrotor orientation parameters at takeoff produced transient responses in less than 1 second. The air pollution sensor parameter data could also be displayed every 10 seconds on the ThingSpeak and ThingView interfaces, and could be mapped based on the data retrieval coordinates.

Based on STM32F103 cowshed environment intelligent control system

The environment of the barn affects the growth, health, reproduction and fattening of the cattle. In order to control the environment of the barn, an intelligent control system based on STM32F103 was designed to monitor and control the temperature, humidity and toxic and harmful gases such as SO2 and NH3. The system adopts STM32F103 as the control core; air pollution sensor MQ135, humidity sensor DHT11, temperature sensor DS18B20 is the system data acquisition device; air purification box (pump, condenser, heating plate, fan) is the system execution device, PC end data analysis software. The experiment was carried out in Mengniu dairy farm in Shengle Economic Development Zone, Hohhot City. The results show that the system can monitor and control various environmental factors stably and reliably.

Hardware Efficient Solutions for Wireless Air Pollution Sensors Dedicated to Dense Urban Areas

This paper proposes novel solutions for the application of air pollution monitoring systems in so called ‘smart cities’. A possibility of the implementation of a relatively dense network of wireless air pollution sensors that can collect and process data in real time was the motive behind our research and investigations. We discuss the concept of the wireless sensor network, taking into account the structure of the urban development in cities and we present a novel signal processing algorithm that may be used to control the communication scheme between particular sensors and an external network. We placed a special emphasis on the computational complexity to facilitate the implementation directly at the transistor level of particular sensors. The algorithm was verified using real data obtained from air pollution sensors installed in Krakow, Poland. To ensure sufficient robustness of the variability of input data, we artificially added high amplitude noise to the real data we obtained. This paper demonstrates the performance of the algorithm. This algorithm allows for the reduction of the noise amplitude by 23 dB and enables a reduction of the number of wireless communication sessions with a base station (BS) by 70%–80%. We also present selected measurement results of a prototype current-mode digital-to-analogue converter to be used in the sensors, for signal resolutions up to 7 bits.

An Optimized Technique for Sharing Air Quality Index using Cloud Technology

This paper studies the sharing the messages of Air Quality Index (AQI) in Metropolitan areas. AQI specifies the percentage of pollutants mixed in air which creates problem in health. The pollutants level in the AQI values is between 0 to 500. Air pollution sensors are used to monitor the air pollution for outdoor environments and the cloud technology is used to display to public via private cloud. Prototype was developed with the aim to create awareness and public engagement in restoring the environment back to its healthy state. Using the prototype, the users can interact with the environment sensors in the field of view to access and visualize latest and historic environment measurements.

Novel Approaches to Air Pollution Exposure and Clinical Outcomes Assessment in Environmental Health Studies

An accurate assessment of pollutants’ exposure and precise evaluation of the clinical outcomes pose two major challenges to the contemporary environmental health research. The common methods for exposure assessment are based on residential addresses and are prone to many biases. Pollution levels are defined based on monitoring stations that are sparsely distributed and frequently distanced far from residential addresses. In addition, the degree of an association between outdoor and indoor air pollution levels is not fully elucidated, making the exposure assessment all the more inaccurate. Clinical outcomes’ assessment, on the other hand, mostly relies on the access to medical records from hospital admissions and outpatients’ visits in clinics. This method differentiates by health care seeking behavior and is therefore, problematic in evaluation of an onset, duration, and severity of an outcome. In the current paper, we review a number of novel solutions aimed to mitigate the aforementioned biases. First, a hybrid satellite-based modeling approach provides daily continuous spatiotemporal estimations with improved spatial resolution of 1 × 1 km2 and 200 × 200 m2 grid, and thus allows a more accurate exposure assessment. Utilizing low-cost air pollution sensors allowing a direct measurement of indoor air pollution levels can further validate these models. Furthermore, the real temporal-spatial activity can be assessed by GPS tracking devices within the individuals’ smartphones. A widespread use of smart devices can help with obtaining objective measurements of some of the clinical outcomes such as vital signs and glucose levels. Finally, human biomonitoring can be efficiently done at a population level, providing accurate estimates of in-vivo absorbed pollutants and allowing for the evaluation of body responses, by biomarkers examination. We suggest that the adoption of these novel methods will change the research paradigm heavily relying on ecological methodology and support development of the new clinical practices preventing adverse environmental effects on human health.

Innovative Methods of Air Pollution Exposure Assessment for Environmental Safety

Abstract Indignation from air pollution is an early signal to instinctive health issues in human. Assessment of human exposure to pollutants for the epidemiological studies will be one of the subsidiary objectives of data analytics for precision medicine forecast for the individuals in the industrially polluted region. The objective of the research determines whether to estimate personal air pollution exposure or population exposure. The exposure can be long term and short term. It includes indoor and outdoor. Direct methods like personal monitoring by using smart phones, air pollution sensors are accurate but quite expensive for huge populations. Indirect methods incorporate information gained from questionnaires accompanied by measured pollutants from the monitoring sites. Lean on the nature of analysis, the assessment pattern may vary. This paper discusses most popular air pollution assessment methods applied in the epidemiological studies related to air pollution. Recent trends in epidemiological studies led to the development of air pollution exposure assessment models that rely on satellite measurement of pollutants. Usage of geographic information system for exposure assessment demands spatial analysis. Mobile applications and sensor technology equipment for personal exposure assessment are promising methods in this study. The articles discussed in this study also observes the method of measurement of each pollutant exposure to individuals by geocoding the addresses with the average pollutant concentration measured at fixed site stations.

Machine learning for air quality prediction using meteorological and traffic related features

The presence of pollutants in the air has a direct impact on our health and causes detrimental changes to our environment. Air quality monitoring is therefore of paramount importance. The high cost of the acquisition and maintenance of accurate air quality stations implies that only a small number of these stations can be deployed in a country. To improve the spatial resolution of the air monitoring process, an interesting idea is to develop data-driven models to predict air quality based on readily available data. In this paper, we investigate the correlations between air pollutants concentrations and meteorological and road traffic data. Using machine learning, regression models are developed to predict pollutants concentration. Both linear and non-linear models are investigated in this paper. It is shown that non-linear models, namely Random Forest (RF) and Support Vector Regression (SVR), better describe the impact of traffic flows and meteorology on the concentrations of pollutants in the atmosphere. It is also shown that more accurate prediction models can be obtained when including some pollutants’ concentration as predictors. This may be used to infer the concentrations of some pollutants using those of other pollutants, thereby reducing the number of air pollution sensors.

Geographically distributed longitudinal nitrogen dioxide and other air pollution sensor measurements in the Avon Longitudinal Study of Parents and Children cohort catchment area

Longitudinal cohort studies provide unique opportunities to investigate the health impact of air pollution. We aimed to enhance the Avon Longitudinal Study of Parents and Children (ALSPAC) birth cohort study through the systematic collection of routinely monitored air pollution data collected by local authorities and the Department for Environment, Food and Rural Affairs (DEFRA) using a range of sensor technologies. These sensor data are in themselves not well suited for population epidemiology, rather these data are primarily used for validating and calibrating modelled air pollution concentration data over study areas. In this data note we describe the sources of routine air pollution monitoring data and detail data of pollutants including nitrogen dioxide, nitric oxide, nitrogen oxides, particulate matter, benzene and ozone collated from the local authorities that overlap the ALSPAC catchment area (Bristol, North Somerset, South Gloucestershire and part of Bath and North East Somerset).

Assessing Mobility-Based Real-Time Air Pollution Exposure in Space and Time Using Smart Sensors and GPS Trajectories in Beijing

Using real-time data from portable air pollutant sensors and smartphone Global Positioning System trajectories collected in Beijing, China, this study demonstrates how smart technologies and individual activity-travel microenvironments affect the assessment of individual-level pollution exposure in space and time at a very fine resolution. It compares three different types of individual-level exposure estimates generated by using residence-based monitoring station assessment, mobility-based monitoring station assessment, and mobility-based real-time assessment. Further, it examines the differences in personal exposure to PM2.5 associated with different activity places and travel modes across various environmental conditions. The results show that the exposure estimates generated by monitoring station assessment and real-time sensing assessment vary substantially across different activity locations and travel modes. Individual-level daily exposure for residents living in the same community also varies significantly, and there are substantial differences in exposure levels using different approaches. These results indicate that residence- or mobility-based monitoring station assessments, which cannot account for the differences in air pollutant exposures between outdoor and indoor environments and between different travel-related microenvironments, could generate considerably biased estimates of personal pollution exposure. Key Words: indoor environment, real-time exposure to air pollution, smart technologies, travel modes, the uncertain geographic context problem.

Next-Generation Community Air Quality Sensors for Identifying Air Pollution Episodes.

Conventional regulatory air quality monitoring sites tend to be sparsely located. The availability of lower-cost air pollution sensors, however, allows for their use in spatially dense community monitoring networks, which can be operated by various stakeholders, including concerned residents, organizations, academics, or government agencies. Networks of many community monitors have the potential to fill the spatial gaps between existing government-operated monitoring sites. One potential benefit of finer scale monitoring might be the ability to discern elevated air pollution episodes in locations that have not been identified by government-operated monitoring sites, which might improve public health warnings for populations sensitive to high levels of air pollution. In the Imperial Air study, a large network of low-cost particle monitors was deployed in the Imperial Valley in Southeastern California. Data from the new monitors is validated against regulatory air monitoring. Neighborhood-level air pollution episodes, which are defined as periods in which the PM2.5 (airborne particles with sizes less than 2.5 μm in diameter) hourly average concentration is equal to or greater than 35 μg m−3, are identified and corroborate with other sites in the network and against the small number of government monitors in the region. During the period from October 2016 to February 2017, a total of 116 episodes were identified among six government monitors in the study region; however, more than 10 times as many episodes are identified among the 38 community air monitors. Of the 1426 episodes identified by the community sensors, 723 (51%) were not observed by the government monitors. These findings suggest that the dense network of community air monitors could be useful for addressing current limitations in the spatial coverage of government air monitoring to provide real-time warnings of high pollution episodes to vulnerable populations.

Characterising low-cost sensors in highly portable platforms to quantify personal exposure in diverse environments

Abstract. The inaccurate quantification of personal exposure to air pollution introduces error and bias in health estimations, severely limiting causal inference in epidemiological research worldwide. Rapid advancements in affordable, miniaturised air pollution sensor technologies offer the potential to address this limitation by capturing the high variability of personal exposure during daily life in large-scale studies with unprecedented spatial and temporal resolution. However, concerns remain regarding the suitability of novel sensing technologies for scientific and policy purposes. In this paper we characterise the performance of a portable personal air quality monitor (PAM) that integrates multiple miniaturised sensors for nitrogen oxides (NOx), carbon monoxide (CO), ozone (O3) and particulate matter (PM) measurements along with temperature, relative humidity, acceleration, noise and GPS sensors. Overall, the air pollution sensors showed high reproducibility (mean R‾2=0.93, min–max: 0.80–1.00) and excellent agreement with standard instrumentation (mean R‾2=0.82, min–max: 0.54–0.99) in outdoor, indoor and commuting microenvironments across seasons and different geographical settings. An important outcome of this study is that the error of the PAM is significantly smaller than the error introduced when estimating personal exposure based on sparsely distributed outdoor fixed monitoring stations. Hence, novel sensing technologies such as the ones demonstrated here can revolutionise health studies by providing highly resolved reliable exposure metrics at a large scale to investigate the underlying mechanisms of the effects of air pollution on health.

TiO2/ZnO Nanofibers Prepared by Electrospinning and Their Photocatalytic Degradation of Methylene Blue Compared with TiO2 Nanofibers

TiO2 nanofibers have high chemical stability and high strength and are applied to many fields such as air pollution sensors and air pollutant removal filters. ZnO nanofibers also have very high absorptivity in that air and are used as germicides and ceramic brighteners. TiO2/ZnO nanofibers, which have a composite form of TiO2 and ZnO, were fabricated and show higher photocatalytic properties than existing TiO2. The precursor, including zinc nitrate hexahydrate, polyvinyl acetate, and titanium isopropoxide, was used as a spinning solution for TiO2/ZnO nanofibers. Electrospun TiO2/ZnO nanofibers were calcined at 600 °C and analyzed by field emission scanning electron microscope (FE-SEM) and X-ray diffraction (XRD). The average diameter of TiO2/ZnO nanofibers was controlled in the range of 189 nm to 1025 nm. XRD pattern in TiO2/ZnO nanofibers have a TiO2 anatase, ZnO, Ti2O3, and ZnTiO3 structure. TiO2/ZnO nanofibers with a diameter of 400 nm have the best photocatalytic performance in the methylene blue degradation experiments and an absorbance decrease of 96.4% was observed after ultraviolet (UV) irradiation of 12 h.

Smart Citizen Kit and Station: An open environmental monitoring system for citizen participation and scientific experimentation

Abstract In the past years, multiple research projects have explored the potential of low-cost environmental sensors for urban air pollution monitoring. However, each project has taken its own independent and in many cases, fully or partially closed approach. We present the Smart Citizen System, a flexible, easy-to-use and fully open-source environmental monitoring solution for particulate matter, carbon monoxide, nitrogen dioxide, noise levels, and many other indicators. The use of low-cost sensors in recent years has been generally approached in two different ways citizen science and educational activities, where the primary purpose is to engage citizens in the measurement process and raise awareness of environmental concerns; and a more sophisticated scientific approach, where the main aim is to study the potentiality of the low-cost sensing technologies. The Smart Citizen System balances modularity with integration to fulfil both needs by providing an extendable solution, with different ranges of sensors based on the same core components. With that aim, two solutions have been developed: the Smart Citizen Kit, intended for citizen science and awareness activities; and the Smart Citizen Station, designed to serve as a more complex and accurate set of air pollution sensors. The design is based on the principle of reproducibility, also integrating non-hardware components such as a dedicated storage platform and a sensor analysis framework. The core system bases its sensing capabilities in widely reviewed low-cost sensors and aims to provide a robust framework for environmental monitoring activities. By making everything open, from the hardware to the software platform or the sensor post-processing algorithms, we hope others might find it useful as a development platform allowing them to focus on their project particular needs instead of reinventing everything from the ground-up.