Long-term evaluation of a low-cost air sensor network for monitoring indoor and outdoor air quality at the community scale

Empowering Participatory Research in Urban Health: Wearable Biometric and Environmental Sensors for Activity Recognition

Participatory exposure research, which tracks behaviour and assesses exposure to stressors like air pollution, traditionally relies on time-activity diaries. This study introduces a novel approach, employing machine learning (ML) to empower laypersons in human activity recognition (HAR), aiming to reduce dependence on manual recording by leveraging data from wearable sensors. Recognising complex activities such as smoking and cooking presents unique challenges due to specific environmental conditions. In this research, we combined wearable environment/ambient and wrist-worn activity/biometric sensors for complex activity recognition in an urban stressor exposure study, measuring parameters like particulate matter concentrations, temperature, and humidity. Two groups, Group H (88 individuals) and Group M (18 individuals), wore the devices and manually logged their activities hourly and minutely, respectively. Prioritising accessibility and inclusivity, we selected three classification algorithms: k-nearest neighbours (IBk), decision trees (J48), and random forests (RF), based on: (1) proven efficacy in existing literature, (2) understandability and transparency for laypersons, (3) availability on user-friendly platforms like WEKA, and (4) efficiency on basic devices such as office laptops or smartphones. Accuracy improved with finer temporal resolution and detailed activity categories. However, when compared to other published human activity recognition research, our accuracy rates, particularly for less complex activities, were not as competitive. Misclassifications were higher for vague activities (resting, playing), while well-defined activities (smoking, cooking, running) had few errors. Including environmental sensor data increased accuracy for all activities, especially playing, smoking, and running. Future work should consider exploring other explainable algorithms available on diverse tools and platforms. Our findings underscore ML's potential in exposure studies, emphasising its adaptability and significance for laypersons while also highlighting areas for improvement.

Quantification of ambient PM2.5 concentrations adjacent to informal brick kilns in the Vhembe District using low-cost sensors

The widespread exposure to ambient PM2.5 poses a substantial health risk globally, with a more pronounced impact on low- to medium-income nations. This study investigates the spatiotemporal distribution of PM2.5 in the communities hosting informal brickmaking industries in Vhembe District. Utilizing Dylos DC1700, continuous monitoring of PM2.5 was conducted at nine stations adjacent to informal brick kilns from March 2021 to February 2022. The study determined the correction factor for PM2.5 measurements obtained from the Dylos DC1700 when it was collocated with the GRIMM Environmental Dust Monitor 180. Additionally, the diurnal and seasonal variations across monitoring stations were assessed, and potential PM2.5 sources were identified. The study also evaluated the compliance of ambient PM2.5 concentrations across the stations with the South African National Ambient Air Quality Standard (NAAQS) limits. Annual PM2.5 concentrations for the stations ranged from 22.6 to 36.2 μgm-3. Diurnal patterns exhibited peak concentrations in the morning and evening, while seasonal variations showed higher concentrations in winter and lower concentrations in summer and spring. All monitoring stations reported the highest daily exceedance with respect to the daily NAAQS limit in the winter. Major PM2.5 sources included domestic biomass combustion, vehicular emissions, industrial emissions, and construction sites. Well-calibrated low-cost sensors could be employed in suburb regions with scarce air quality data. Findings from the study could be used for developing mitigation strategies to reduce health risks associated with PM2.5 exposure in the area.

A novel approach for the prediction and analysis of daily concentrations of particulate matter using machine learning

Traditional air quality analysis and prediction methods depend on the statistical and numerical analyses of historical air quality data with more information related to a specific region; therefore, the results are unsatisfactory. In particular, fine particulate matter (PM2.5, PM10) in the atmosphere is a major concern for human health. The modelling (analysis and prediction) of particulate matter concentrations remains unsatisfactory owing to the rapid increase in urbanization and industrialization. In the present study, we reconstructed a prediction model for both PM2.5 and PM10 with varying meteorological conditions (windspeed, temperature, precipitation, specific humidity, and air pressure) in a specific region. In this study, a prediction model was developed for the two observation stations in the study region. The analysis of particulate matter shows that seasonal variation is a primary factor that highly influences air pollutant concentrations in urban regions. Based on historical data, the maximum number of days (92 days in 2019) during the winter season exceeded the maximum permissible level of particulate matter (PM2.5 = 15 μg/m3) concentration in air. The prediction results showed better performance of the Gaussian process regression model, with comparatively larger R2 values and smaller errors than the other models. Based on the analysis and prediction, these novel methods may enhance the accuracy of particulate matter prediction and influence policy- and decision-makers among pollution control authorities to protect air quality.

Potential of a Miniature Spectral Analyzer for District-Scale Monitoring of Multiple Gaseous Air Pollutants

Gas sensors that can measure multiple pollutants simultaneously are highly desirable for on-site air pollution monitoring at various scales, both indoor and outdoor. Herein, we introduce a low-cost multi-parameter gas analyzer capable of monitoring multiple gaseous pollutants simultaneously, thus allowing for true analytical measurement. It is a spectral sensor consisting of a Fourier-transform infrared (FTIR) gas analyzer based on a mid-infrared (MIR) spectrometer. The sensor is as small as 7 × 5 × 2.5 cm³. It was deployed in an open-path configuration within a district-scale climatic chamber (Sense City, Marne-la-Vallée, France) with a volume of 20 × 20 × 8 m³. The setup included a transmitter and a receiver separated by 38 m to enable representative measurements of the entire district domain. We used a car inside the climatic chamber, turning the engine on and off to create time sequences of a pollution source. The results showed that carbon dioxide (CO₂) and water vapor (H₂O) were accurately monitored using the spectral sensor, with agreement with the reference analyzers used to record the pollution levels near the car exhaust. Furthermore, the lower detection limits of CO, NO₂ and NO were assessed, demonstrating the capability of the sensor to detect these pollutants. Additionally, a preliminary evaluation of the potential of the spectral sensor to screen multiple volatile organic compounds (VOCs) was conducted at the laboratory scale. Overall, the results demonstrated the potential of the proposed multi-parameter spectral gas sensor in on-site gaseous pollution monitoring.

A sensor-based framework for layout and workflow assessment in operating rooms

Due to their large sizes and impediments to personnel workflows, integrating robotic technologies into the existing operating rooms (OR) is a challenge. In this study, we developed an ultra-wideband sensor-based human-machine-environment framework for layout and workflow assessments within the OR. In addition to providing best practices for use of the framework, we also demonstrated its effectiveness in understanding layout and workflow inefficiencies in 12 robotic-assisted surgeries (RAS) across 4 different surgical specialties. We found avoidable movements as the circulating nurse covers at least twice the distance of any other OR personnel before the patient cart (robot) is docked. OR areas of congestion and undesirable personnel-pair proximities across RAS phases that impose extra non-technical skill challenges were determined. Our findings highlight several implications for the added complexity of integrating robotic technologies into the OR, which can serve as drivers for objective evidence-based recommendations to combat RAS OR layout and workflow inefficiencies.

Environmental justice analysis of wildfire-related PM2.5 exposure using low-cost sensors in California

The increasing number and severity of wildfires is negatively impacting air quality for millions of California residents each year. Community exposure to PM_2.5 in two main population centers (San Francisco Bay area and Los Angeles County area) was assessed using the low-cost PurpleAir sensor network for the record-setting 2020 California wildfire season. Estimated PM_2.5 concentrations in each study area were compared to census tract-level environmental justice vulnerability indicators, including environmental, health, and demographic data. Higher PM_2.5 concentrations were positively correlated with poverty, cardiovascular emergency department visits, and housing inequities. Sensors within 30 km of actively burning wildfires showed statistically significant increases in indoor (~800 %) and outdoor (~540 %) PM_2.5 during the fires. Results indicate that wildfire emissions may exacerbate existing health disparities as well as the burden of pollution in disadvantaged communities, suggesting a need to improve monitoring and adaptive capacity among vulnerable populations.

Electrical and Gas Sensor Properties of Nb(V) Doped Nanocrystalline β-Ga2O3

A flame spray pyrolysis (FSP) technique was applied to obtain pure and Nb(V)-doped nanocrystalline β-Ga₂O₃, which were further studied as gas sensor materials. The obtained samples were characterized with XRD, XPS, TEM, Raman spectroscopy and BET method. Formation of GaNbO₄ phase is observed at high annealing temperatures. Transition of Ga(III) into Ga(I) state during Nb(V) doping prevents donor charge carriers generation and hinders considerable improvement of electrical and gas sensor properties of β-Ga₂O₃. Superior gas sensor performance of obtained ultrafine materials at lower operating temperatures compared to previously reported thin film Ga₂O₃ materials is shown.

Exposure of construction workers to hazardous emissions in highway rehabilitation projects measured with low-cost sensors

Construction workers on highway rehabilitation projects can be exposed to a combination of traffic- and construction-related emissions. To assess the personal exposure a worker experiences, a portable battery-operated Air Quality Device (AQD) was utilised to measure emissions during normal construction operations of a major road rehabilitation project. Emissions measured were nitrogen dioxide (NO₂), Total Volatile Organic Compounds (TVOCs) and Particulate Matter (PM₁₀, PM_2.5, and PM₁). The objective of the paper is to document the hazardous emissions that construction workers may be exposed to and allow for a basis of informed decision making to mitigate the risks of a road construction project. Most critically, this article is designed to raise awareness of the potential impact to a worker's wellbeing as well as highlight the need for further research. Through statistical analysis, asphalt paving was identified as the most hazardous activity in terms of exposure relative to other activities. This activity was further assessed using discrete-time Markov chain Monte Carlo simulations with results indicating a high probability that workers may be exposed to greater hazardous emission concentrations than measured. Limiting the distance to the source of emissions, large-scale use of warm-mix asphalt and reducing the idling times of construction vehicles were identified as practical mitigation measures to reduce exposure and aid in achieving zero-harm objectives. Finally, it is found that males are more susceptible to long-term implications of hazardous emission inhalation and should be more aware if the scenarios they might work in expose them to this.

Fine Particulate Matter Concentrations during Independence Day Fireworks Display in the Lower Rio Grande Valley Region, South Texas, USA

Fireworks are typically discharged as a mark of celebration and joy in many societies spanning various cultures. In the United States of America, 4th July is celebrated as the Independence Day when the nation overthrew the British colonial yoke in 1776. While this day instills a sense of patriotism in every American’s heart, it is also a major PM2.5 air pollution concern. This study is first of its type in the Lower Rio Grande Valley (RGV) Region of South Texas, USA, that characterizes fine particulate matter pollution. Using a low-cost sensor (TSI BlueSky Air Quality Monitor), real-time PM2.5 measurements were assessed at eleven different locations in four different towns and cities of Lower RGV Region: Brownsville, Edinburg, Weslaco, and Port Isabel. Hourly PM2.5 concentrations from July 03–06, 2021 are presented in this research work. Intraurban PM2.5 spatial and temporal variations provide an insight on the general population’s exposure burden during the festive period. Results indicate an increase in fine particulate matter pollution across the region, but the levels do not exceed the U.S. National Ambient Air Quality Standards (NAAQS). Findings from this study would possibly help in the formulation of effective firework policies to minimize the pollution impact.

Leveraging Citizen Science and Low-Cost Sensors to Characterize Air Pollution Exposure of Disadvantaged Communities in Southern California

Assessing exposure to fine particulate matter (PM_2.5) across disadvantaged communities is understudied, and the air monitoring network is inadequate. We leveraged emerging low-cost sensors (PurpleAir) and engaged community residents to develop a community-based monitoring program across disadvantaged communities (high proportions of low-income and minority populations) in Southern California. We recruited 22 households from 8 communities to measure residential outdoor PM_2.5 concentrations from June 2021 to December 2021. We identified the spatial and temporal patterns of PM_2.5 measurements as well as the relationship between the total PM_2.5 measurements and diesel PM emissions. We found that communities with a higher percentage of Hispanic and African American population and higher rates of unemployment, poverty, and housing burden were exposed to higher PM_2.5 concentrations. The average PM_2.5 concentrations in winter (25.8 µg/m³) were much higher compared with the summer concentrations (12.4 µg/m³). We also identified valuable hour-of-day and day-of-week patterns among disadvantaged communities. Our results suggest that the built environment can be targeted to reduce the exposure disparity. Integrating low-cost sensors into a citizen-science-based air monitoring program has promising applications to resolve monitoring disparity and capture “hotspots” to inform emission control and urban planning policies, thus improving exposure assessment and promoting environmental justice.

Assessment of ANN Algorithms for the Concentration Prediction of Indoor Air Pollutants in Child Daycare Centers

As the time spent by people indoors continues to significantly increase, much attention has been paid to indoor air quality. While many IAQ studies have been conducted through field measurements, the use of data-driven techniques such as machine learning has been increasingly used for the prediction of indoor air pollutants. For the present study, the concentrations of indoor air pollutants such as CO2, PM2.5, and VOCs in child daycare centers were predicted by using an artificial neural network model with three different training algorithms including Levenberg–Marquardt, Bayesian regularization, and Broyden–Fletcher–Goldfarb–Shanno quasi-Newton methods. For training and validation, data of indoor pollutants measured in child daycare facilities over a 1-month period were used. The results showed all the models produced a good performance for the prediction of indoor pollutants compared with the measured data. Among the models, the prediction by the LM model met the acceptable criteria of ASHRAE guideline 14 under all conditions. It was observed that the prediction performance decreased as the number of hidden layers increased. Moreover, the prediction performance was differed by the type of indoor pollutant. This was caused by patterns observed in the measured data. Considering the outcomes of the study, better prediction results can be obtained through the selection of suitable prediction models for time series data as well as the adjustment of training algorithms.

Towards the Development of a Sensor Educational Toolkit to Support Community and Citizen Science

As air quality sensors increasingly become commercially available, a deeper consideration of their usability and usefulness is needed to ensure effective application by the public. Much of the research related to sensors has focused on data quality and potential applications. While this information is important, a greater understanding of users’ experience with sensors would provide complementary information. Under a U.S. EPA-funded Science to Achieve Results grant awarded to the South Coast Air Quality Management District in California, titled “Engage, Educate, and Empower California Communities on the Use and Applications of Low-Cost Air Monitoring Sensors”, approximately 400 air quality sensors were deployed with 14 California communities. These communities received sensors and training, and they participated in workshops. Widely varying levels of sensor installation and engagement were observed across the 14 communities. However, despite differences between communities (in terms of participation, demographics, and socioeconomic factors), many participants offered similar feedback on the barriers to sensor use and strategies leading to successful sensor use. Here, we assess sensor use and participant feedback, as well as discuss the development of an educational toolkit titled “Community in Action: A Comprehensive Toolkit on Air Quality Sensors”. This toolkit can be leveraged by future community and citizen science projects to develop networks designed to collect air quality information that can help reduce exposure to and the emissions of pollutants, leading to improved environmental and public health.

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.

Environmental Sustainability Approaches and Positive Energy Districts: A Literature Review

During the last decade, increasing attention has been paid to the emerging concept of Positive Energy Districts (PED) with the aim of pushing the transition to clean energy, but further research efforts are needed to identify design approaches optimized from the point of view of sustainable development. In this context, this literature review is placed, with a specific focus on environmental sustainability within innovative and eco-sustainable districts. The findings show that some sustainability aspects such as sustainable food, urban heat islands mitigation and co-impacts, e.g., green gentrification, are not adequately assessed, while fragmented thinking limits the potential of circularity. In this regard, targeted strategies should be developed. On the other hand, the Key Performance Indicators framework needs some integrations. In this direction, indicators were suggested, among those defined in the Sustainable Development Agenda, the main European standards and initiatives and the relevant literature experiences. Future outlooks should be directed towards: the harmonization of the Life Cycle Assessment in PEDs with reference to modeling assumptions and analysis of multiple impacts; the development of dynamic environmental analyses taking into account the long-term uncertainty due to climate change, data availability and energy decarbonization; the combination of Life Cycle Assessment and Key Performance Indicators based techniques, from a holistic thinking perspective, for a comprehensive design environment and the analysis of the contribution of energy flexibility approaches on the environmental impact of a project.