Efficient data preprocessing, episode classification, and source apportionment of particle number concentrations

A probabilistic framework for identifying anomalies in urban air quality data

Just as the value of crude oil is unlocked through refining, the true potential of air quality data is realized through systematic processing, analysis, and application. This refined data is critical for making informed decisions that may protect health and the environment. Perhaps ground-based air quality monitoring data often face quality control issues, notably outliers. The outliers in air quality data are reported as error and event-based. The error-based outliers are due to instrument failure, self-calibration, sensor drift over time, and the event based focused on the sudden change in meteorological conditions. The event-based outliers are meaningful while error-based outliers are noise that needs to be eliminated and replaced post-detection. In this study, we address error-based outlier detection in air quality data, particularly targeting particulate pollutants (PM2.5 and PM10) across various monitoring sites in Delhi. Our research specifically examines data from sites with less than 5% missing values and identifies four distinct types of error-based outliers: extreme values due to measurement errors, consecutive constant readings and low variance due to instrument malfunction, periodic outliers from self-calibration exceptions, and anomalies in the PM2.5/PM10 ratio indicative of issues with the instruments' dryer unit. We developed a robust methodology for outlier detection by fitting a non-linear filter to the data, calculating residuals between observed and predicted values, and then assessing these residuals using a standardized Z-score to determine their probability. Outliers are flagged based on a probability threshold established through sensitivity testing. This approach helps distinguish normal data points from suspicious ones, ensuring the refined quality of data necessary for accurate air quality modeling. This method is essential for improving the reliability of statistical and machine learning models that depend on high-quality environmental data.

Impact of mobility restrictions on NO2 concentrations in key Latin American cities during the first wave of the COVID-19 pandemic

Between March and June 2020, activity in the major cities of Latin America declined due to containment efforts implemented by local governments to avoid the rapid spread of COVID-19. Our study compared 2020 with the previous year and demonstrated a considerable drop in tropospheric NO₂ levels obtained by the SENTINEL 5P satellite in major Latin American cities. Lima (47.5%), Santiago (36.1%), São Paulo (27%), Rio de Janeiro (23%), Quito (18.6%), Bogota (17.5%), Buenos Aires (16.6%), Guayaquil (15.3%), Medellin (14.2%), La Paz (9.5%), Belo Horizonte (7.8%), Mexico (7.6%) and Brasilia (5.9%) registered statistically significant decreases in NO₂ concentrations during the study period. In addition, we analyzed mobility data from Google and Apple reports as well as meteorological information from atmospheric reanalysis data along with satellite fields between 2011 and 2020, and performed a refined multivariate analysis (non-negative matrix approximation) to show that this decrease was associated with a reduction in population mobility rather than meteorological factors. Our findings corroborate the argument that confinement scenarios may indicate how air pollutant concentrations can be effectively reduced and managed.

Airborne particle number concentrations in China: A critical review

Particle number concentration (PNC) is an important parameter for evaluating the environmental health and climate effects of particulate matter (PM). A good understanding of PNC is essential to control atmospheric ultrafine particles (UFP) and protect public health. In this study, we reviewed the PNC studies in the literature aimed to gain a comprehensive understanding about the levels, trends, and sources of PNC in China. The PNC levels at the urban, suburban, rural, remote, and coastal sites in China were 8500-52,200, 8600-30,300, 8600-28,400, 2100-16,100, and 5700-19,600 cm^-3, respectively. The wide ranges of PNC indicate significant heterogeneity in the spatial distribution of PNC, but also are partly due to the different measurement techniques deployed in different studies. In general, it still can be concluded that the PNC levels at urban > suburban > rural > coastal > remote sites. Except for Mt. Waliguan (a remote site of 3816 m a.s.l.), other cities had the highest PNC in spring or winter and the lowest in summer or autumn. Long-term changes of PNCs in Beijing and Nanjing indicated that PNCs of Nucleation and Aitken modes had substantially declined following stricter emission controls in recent years, but more frequent new particle formation (NPF) events were observed due to reduction in coagulation sink. Overall, traffic emission was the most dominant source of PNC in more than 94.4% of the selected cities around the world, while combustion2 (the energy production and industry related combustion source), background aerosol, and nucleation sources were also important contributors to PNC. This study provides insights about PNC and its sources around the world, especially in China. A few recommendations were suggested to further improve the understanding of PNC and to develop effective PNC control strategies.

Maternal exposure to traffic-related ambient particles and risk of gestational diabetes mellitus with isolated fasting hyperglycaemia: A retrospective cohort study in Beijing, China

BACKGROUND

Ambient particles have been associated with gestational diabetes mellitus (GDM), however, no study has evaluated the effects of traffic-related ambient particles on the risks of GDM subgroups classified by oral glucose tolerance test (OGTT) values.

METHODS

A retrospective analysis was conducted among 24,001 pregnant women who underwent regular prenatal care and received OGTT at Haidian Maternal and Child Health Hospital in Beijing, China, 2014-2017. A total of 3,168 (13.2%) pregnant women were diagnosed with GDM, including 1,206 with isolated fasting hyperglycaemia (GDM-IFH). At a fixed-location monitoring station, routinely monitored ambient particles included fine particulate matter (PM_2.5), black carbon (BC) and particles in size ranges of 5-560 nm (PNC_5-560). Contributions of PNC_5-560 sources were apportioned by positive matrix factorization model. Logistic regression model was applied to estimate odds ratio (OR) of ambient particles on GDM risk.

RESULTS

Among the 24,001 pregnancy women recruited in this study, 3,168 (13.2%) were diagnosed with GDM, including 1,206 with isolated fasting hyperglycaemia (GDM-IFH) and 1,295 with isolated post-load hyperglycaemia (GDM-IPH). We observed increased GDM-IFH risk with per interquartile range increase in first-trimester exposures to PM_2.5 (OR = 1.94; 95% Confidence Intervals: 1.23-3.07), BC (OR = 2.14; 1.73-2.66) and PNC_5-560 (OR = 2.46; 1.90-3.19). PNC_5-560 originated from diesel and gasoline vehicle emissions were found in associations with increases in GDM-IFH risk, but not in GDM-IPH risk.

CONCLUSION

Our findings suggest that exposure to traffic-related ambient particles may increase GDM risk by exerting adverse effects on fasting glucose levels during pregnancy, and support continuing efforts to reduce traffic emissions for protecting vulnerable population who are at greater risk of glucose metabolism disorder.

Integrated Evolutionary Learning: An Artificial Intelligence Approach to Joint Learning of Features and Hyperparameters for Optimized, Explainable Machine Learning

Artificial intelligence and machine learning techniques have proved fertile methods for attacking difficult problems in medicine and public health. These techniques have garnered strong interest for the analysis of the large, multi-domain open science datasets that are increasingly available in health research. Discovery science in large datasets is challenging given the unconstrained nature of the learning environment where there may be a large number of potential predictors and appropriate ranges for model hyperparameters are unknown. As well, it is likely that explainability is at a premium in order to engage in future hypothesis generation or analysis. Here, we present a novel method that addresses these challenges by exploiting evolutionary algorithms to optimize machine learning discovery science while exploring a large solution space and minimizing bias. We demonstrate that our approach, called integrated evolutionary learning (IEL), provides an automated, adaptive method for jointly learning features and hyperparameters while furnishing explainable models where the original features used to make predictions may be obtained even with artificial neural networks. In IEL the machine learning algorithm of choice is nested inside an evolutionary algorithm which selects features and hyperparameters over generations on the basis of an information function to converge on an optimal solution. We apply IEL to three gold standard machine learning algorithms in challenging, heterogenous biobehavioral data: deep learning with artificial neural networks, decision tree-based techniques and baseline linear models. Using our novel IEL approach, artificial neural networks achieved ≥ 95% accuracy, sensitivity and specificity and 45–73% R2 in classification and substantial gains over default settings. IEL may be applied to a wide range of less- or unconstrained discovery science problems where the practitioner wishes to jointly learn features and hyperparameters in an adaptive, principled manner within the same algorithmic process. This approach offers significant flexibility, enlarges the solution space and mitigates bias that may arise from manual or semi-manual hyperparameter tuning and feature selection and presents the opportunity to select the inner machine learning algorithm based on the results of optimized learning for the problem at hand.

Maternal exposures to fine and ultrafine particles and the risk of preterm birth from a retrospective study in Beijing, China

Maternal exposure to fine particulate matter (PM_2.5) has been associated with increased risk of preterm birth (PTB), but evidence on particles in smaller sizes and PTB risk remains limited. In this retrospective analysis, we included birth records of 24,001 singleton live births from Haidian Maternal and Child Health Hospital in Beijing, China, 2014-2017. Concurrently, number concentrations of size-fractioned particles in size ranges of 5-560 nm (PNC_5-560) and mass concentrations of PM_2.5, black carbon (BC) and gaseous pollutants were measured from a fixed-location monitoring station in central Haidian District. Logistic regression models were used to estimate the odds ratio (OR) of air pollutants on PTB risk after controlling for temperature, relative humidity, and individual covariates (e.g., maternal age, ethnicity, gravidity, parity, gestational weight gain, fetal gender, the year and season of conception). Positive matrix factorization models were then used to apportion the sources of PNC_5-560. Among the 1062 (4.4%) PTBs, increased PTB risk was observed during the third trimester of pregnancy per 10 μg/m³ increase in PM_2.5 [OR = 1.92; 95% Confidence Interval (95% CI): 1.76, 2.09], per 1000 particles/cm³ increase in PNC_25-100 (OR = 1.09; 95% CI: 1.03, 1.15) and PNC_100-560 (OR = 1.22; 95% CI: 1.05, 1.42). Among the identified sources of PNC_5-560, emissions from gasoline and diesel vehicles were significantly associated with increased PTB risk, with ORs of 1.14 (95% CI: 1.01, 1.29) and 1.11 (95% CI: 1.04, 1.18), respectively. Exposures to other traffic-related air pollutants, such as BC and nitrogen dioxide (NO₂) were also significantly associated with increased PTB risk. Our findings highlight the importance of traffic emission reduction in urban areas.

Source apportionment of atmospheric particle number concentrations with wide size range by nonnegative matrix factorization (NMF)

Quantifying the sources of atmospheric particles is essential to air quality control but remains challenging, especially for the source apportionment of particles based on number concentration with wide size range. Here, particle number concentrations (PNC) with size range 19-20,000 nm involving four modes Nucleation, Aitken, Accumulation, and Coarse are used to do source apportionment of PNC at the Guangdong Atmospheric Supersite (Heshan) during July-October 2015 by nonnegative matrix factorization (NMF) with 6 factors. For July 2015, separated source apportionments for three different size ranges from collocated instruments nano scanning mobility particle sizer (NSMPS), SMPS, and aerodynamic particle sizer (APS) and for two different size ranges (below and above 100 nm) show similar quantitative source information with that for the one whole size range. The mean absolute difference of contribution percentages of total particle number concentrations (TPNC) based on 5 unique apportioned sources is 5.6 % (4.3-7.6 %) for the instrument segregated apportionment and 4.2 % (0-5.3 %) for the size range segregated apportionment respectively, relative to the one whole apportionment. Moreover, the contribution percentages of TPNC are close to the weighted sum of contribution percentages of all size bins, with a mean absolute difference of 1.1 % (0-3.4 %). In both these two aspects, the consistency among different technical paths proves the matrix factorization by NMF is practically desirable and the simplicity of reducing some steps or calculations saves time. Besides, dust can be identified with the wide size range including larger than 3000 nm. Six apportioned sources in the 4 months are Accumulation (32.4 %), Nucleation (20.0 %), Aitken (15.2 %), traffic (14.6 %), dust (10.6 %), and Coarse (7.1 %). Therefore, NMF would serve as a promising tool for PNC source apportionment with wide size range and conducting the apportionment with the whole size range in one matrix factorization procedure and using the single TPNC contribution percentage are feasible.

Associations of ultrafine and fine particles with childhood emergency room visits for respiratory diseases in a megacity

BACKGROUND

Ambient fine particulate matter with aerodynamic diameter less than 2.5 µm (PM_2.5) has been associated with deteriorated respiratory health, but evidence on particles in smaller sizes and childhood respiratory health has been limited.

METHODS

We collected time-series data on daily respiratory emergency room visits (ERVs) among children under 14 years old in Beijing, China, during 2015-2017. Concurrently, size-fractioned number concentrations of particles in size ranges of 5-560 nm (PNC_5-560) and mass concentrations of PM_2.5, black carbon (BC) and nitrogen dioxide (NO₂) were measured from a fixed-location monitoring station in the urban area of Beijing. Confounder-adjusted Poisson regression models were used to estimate excessive risks (ERs) of particle size fractions on childhood respiratory ERVs, and positive matrix factorisation models were applied to apportion the sources of PNC_5-560.

RESULTS

Among the 136 925 cases of all-respiratory ERVs, increased risks were associated with IQR increases in PNC_25-100 (ER=5.4%, 95% CI 2.4% to 8.6%), PNC_100-560 (4.9%, 95% CI 2.5% to 7.3%) and PM_2.5 (1.3%, 95% CI 0.1% to 2.5%) at current and 1 prior days (lag0-1). Major sources of PNC_5-560 were identified, including nucleation (36.5%), gasoline vehicle emissions (27.9%), diesel vehicle emissions (18.9%) and secondary aerosols (10.6%). Emissions from gasoline and diesel vehicles were found of significant associations with all-respiratory ERVs, with increased ERs of 6.0% (95% CI 2.5% to 9.7%) and 4.4% (95% CI 1.7% to 7.1%) at lag0-1 days, respectively. Exposures to other traffic-related pollutants (BC and NO₂) were also associated with increased respiratory ERVs.

CONCLUSION

Our findings suggest that exposures to higher levels of PNC_5-560 from traffic emissions could be attributed to increased childhood respiratory morbidity, which supports traffic emission control priority in urban areas.