Predicting carbonaceous aerosols and identifying their source contribution with advanced approaches

Applying the total carbon-black carbon approach method to investigate the characteristics of primary and secondary carbonaceous aerosols in ambient PM2.5 in northern Taiwan

Ambient fine particulate matter (PM2.5) comprises a diverse array of carbonaceous species, and the impact of carbonaceous aerosols (CA) extends to both long-term and short-term effects on human health and the environment. Understanding the distinctive composition of CA is crucial for gaining insights into the origins of airborne particulate matter. Due to their diverse physicochemical properties and intricate heterogeneous reactions, CA often exhibits temporal and spatial variations. Ground-based and highly time-resolved apportionment methods play a vital role in discerning CA emissions. This study utilized high-time resolution data of total carbon (TC) and black carbon (BC) for CA apportionment in northern Taiwan. The advanced numerical model (TC-BC(λ)), coupled with continuous measurement data, facilitated CA allocation based on optical absorption characteristics, organic or elemental carbon composition, and the distinction between primary and secondary origins. Primary carbonaceous aerosols dominated the monitoring site, accounting for 67.5 % compared to the 32.5 % contribution from secondary forms of CA. The summer season exhibited a maximum increase in secondary organic aerosols (SOA) at 41.5 %. Diurnal variations for primary emissions, such as BCc and primary organic aerosols (POA), showed marked peaks for BCff and POAnon-abs during morning rush hours. In contrast, BCbb and POABrC displayed bimodal peaks with increased concentrations during evening hours. Conversely, SOA exhibited significantly different diurnal trends, with SOABrC peaking late at night due to aqueous phased reactions and a noontime peak of SOAnon-abs observed due to photo-oxidation processes. Furthermore, the study employed backward trajectory analysis and concentration-weighted trajectories (CWTs) to examine the long-range transport of CA, identifying potential sources, origins, and transport patterns of CA components to the receptor site in Taiwan during different seasons.

Quantifying source contributions to ambient NH3 using Geo-AI with time lag and parcel tracking functions

Ambient ammonia (NH3) plays an important compound in forming particulate matters (PMs), and therefore, it is crucial to comprehend NH3's properties in order to better reduce PMs. However, it is not easy to achieve this goal due to the limited range/real-time NH3 data monitored by the air quality stations. While there were other studies to predict NH3 and its source apportionment, this manuscript provides a novel method (i.e., GEO-AI)) to look into NH3 predictions and their contribution sources. This study represents a pioneering effort in the application of a novel geospatial-artificial intelligence (Geo-AI) base model with parcel tracking functions. This innovative approach seamlessly integrates various machine learning algorithms and geographic predictor variables to estimate NH3 concentrations, marking the first instance of such a comprehensive methodology. The Shapley additive explanation (SHAP) was used to further analyze source contribution of NH3 with domain knowledge. From 2016 to 2018, Taichung's hourly average NH3 values were predicted with total variance up to 96%. SHAP values revealed that waterbody, traffic and agriculture emissions were the most significant factors to affect NH3 concentrations in Taichung among all the characteristics. Our methodology is a vital first step for shaping future policies and regulations and is adaptable to regions with limited monitoring sites.

Constructing transferable and interpretable machine learning models for black carbon concentrations

Black carbon (BC) has received increasing attention from researchers due to its adverse health effects. However, in-situ BC measurements are often not included as a regulated variable in air quality monitoring networks. Machine learning (ML) models have been studied extensively to serve as virtual sensors to complement the reference instruments. This study evaluates and compares three white-box (WB) and four black-box (BB) ML models to estimate BC concentrations, with the focus to show their transferability and interpretability. We train the models with the long-term air pollutant and weather measurements in Barcelona urban background site, and test them in other European urban and traffic sites. Despite the difference in geographical locations and measurement sites, BC correlates the strongest with particle number concentration of accumulation mode (PNacc, r = 0.73-0.85) and nitrogen dioxide (NO2, r = 0.68-0.85) and the weakest with meteorological parameters. Due to its similarity of correlation behaviour, the ML models trained in Barcelona performs prominently at the traffic site in Helsinki (R2 = 0.80-0.86; mean absolute error MAE = 3.90-4.73 %) and at the urban background site in Dresden (R2 = 0.79-0.84; MAE = 4.23-4.82 %). WB models appear to explain less variability of BC than BB models, long short-term memory (LSTM) model of which outperforms the rest of the models. In terms of interpretability, we adopt several methods for individual model to quantify and normalize the relative importance of each input feature. The overall static relative importance commonly used for WB models demonstrate varying results from the dynamic values utilized to show local contribution used for BB models. PNacc and NO2 on average have the strongest absolute static contribution; however, they simultaneously impact the estimation positively and negatively at different sites. This comprehensive analysis demonstrates that the possibility of these interpretable air pollutant ML models to be transfered across space and time.

The application of machine learning to air pollution research: A bibliometric analysis

Machine learning (ML) is an advanced computer algorithm that simulates the human learning process to solve problems. With an explosion of monitoring data and the increasing demand for fast and accurate prediction, ML models have been rapidly developed and applied in air pollution research. In order to explore the status of ML applications in air pollution research, a bibliometric analysis was made based on 2962 articles published from 1990 to 2021. The number of publications increased sharply after 2017, comprising approximately 75% of the total. Institutions in China and United States contributed half of all publications with most research being conducted by individual groups rather than global collaborations. Cluster analysis revealed four main research topics for the application of ML: chemical characterization of pollutants, short-term forecasting, detection improvement and optimizing emission control. The rapid development of ML algorithms has increased the capability to explore the chemical characteristics of multiple pollutants, analyze chemical reactions and their driving factors, and simulate scenarios. Combined with multi-field data, ML models are a powerful tool for analyzing atmospheric chemical processes and evaluating the management of air quality and deserve greater attention in future.

Spatiotemporal variations and relationships of absorbing aerosol-radiation-gross primary productivity over China

High-load carbonaceous and dust aerosols can significantly reduce direct radiation (DIRR), which would affect photosynthesis in terrestrial ecosystems, thereby further affecting the productivity of vegetation. Based on this, a variety of remote sensing data were used to study the spatiotemporal distributions and changing tendencies of the absorbing aerosols, CO, DIRR, and gross primary productivity (GPP) in China during 2005-2019; then, the relationships were analyzed between different types of absorbing aerosols and DIRR as well as GPP. The results showed that the annual mean absorbing aerosols index (AAI) in China during 2005-2019 was 0.39, with a slow growth rate of 0.02 year^-1, and the emission of CO showed a decreasing trend with each passing year, especially in North China Plain and Sichuan Basin. Carbonaceous and dust aerosols were predominantly bounded by Hu line. The east of Hu line was the dominant area of carbonaceous aerosols, and the west of Hu line was the topographical region of dust aerosols. Near the Hu line was the dominant area of carbonaceous-dust aerosols. However, the Karamay-Urumqi-Hami area and Northeast China Plain were exceptional. During the vegetation growing season, different types of absorbing aerosols significantly negatively affected GPP. From a perspective of regional scale variation pattern, the negative effect of absorbing aerosols on vegetation productivity was the most significant in Northeast China; from the perspective of the effects of different vegetation types, the negative effect of absorbing aerosols on grasslands was greater than that of woodlands; from the perspective of the composition characteristics of aerosols, the negative effect of dust aerosols on GPP was greater than that of carbonaceous aerosols.

Organic and Elemental Carbon in the Urban Background in an Eastern Mediterranean City

The Mediterranean region is an important area for air pollution as it is the crossroads between three continents; therefore, the concentrations of atmospheric aerosol particles are influenced by emissions from Africa, Asia, and Europe. Here we concentrate on an eleven-month time series of the ambient concentration of organic carbon (OC) and elemental carbon (EC) between May 2018–March 2019 in Amman, Jordan. Such a dataset is unique in Jordan. The results show that the OC and EC annual mean concentrations in PM2.5 samples were 5.9 ± 2.8 µg m–3 and 1.7 ± 1.1 µg m–3, respectively. It was found that the majority of OC and EC concentrations were within the fine particle fraction (PM2.5). During sand and dust storm (SDS) episodes OC and EC concentrations were higher than the annual means; the mean values during these periods were about 9.6 ± 3.5 µg m–3 and 2.5 ± 1.2 µg m–3 in the PM2.5 samples. Based on this, the SDS episodes were identified to be responsible for an increased carbonaceous aerosol content as well as PM2.5 and PM10 content, which may have direct implications on human health. This study encourages us to perform more extensive measurements during a longer time period and to include an advanced chemical and physical characterization for urban aerosols in the urban atmosphere of Amman, which can be representative of other urban areas in the region.

Machine Learning: New Ideas and Tools in Environmental Science and Engineering

The rapid increase in both the quantity and complexity of data that are being generated daily in the field of environmental science and engineering (ESE) demands accompanied advancement in data analytics. Advanced data analysis approaches, such as machine learning (ML), have become indispensable tools for revealing hidden patterns or deducing correlations for which conventional analytical methods face limitations or challenges. However, ML concepts and practices have not been widely utilized by researchers in ESE. This feature explores the potential of ML to revolutionize data analysis and modeling in the ESE field, and covers the essential knowledge needed for such applications. First, we use five examples to illustrate how ML addresses complex ESE problems. We then summarize four major types of applications of ML in ESE: making predictions; extracting feature importance; detecting anomalies; and discovering new materials or chemicals. Next, we introduce the essential knowledge required and current shortcomings in ML applications in ESE, with a focus on three important but often overlooked components when applying ML: correct model development, proper model interpretation, and sound applicability analysis. Finally, we discuss challenges and future opportunities in the application of ML tools in ESE to highlight the potential of ML in this field.