Contributions of various driving factors to air pollution events: Interpretability analysis from Machine learning perspective

Evaluating drivers of PM2.5 air pollution at urban scales using interpretable machine learning

Reducing urban fine particulate matter (PM2.5) concentrations is essential for China to achieve the Sustainable Development Goals (SDGs). Identifying the key drivers of PM2.5 will enable the development of targeted strategies to reduce PM2.5 levels. This study introduces a machine-learning model that combines CatBoost and the Tree-Structured Parzen Estimator (TPE) to analyze PM2.5 concentration across 297 cities between 2000 and 2021. SHapley Additive exPlanations (SHAP) were employed to identify the primary factors influencing urban PM2.5 concentrations. The study revealed that the proposed model has high accuracy in predicting urban PM2.5 concentrations, achieving a coefficient of determination (R2) score of 96.44%. Socioeconomic and industrial activity are key drivers of PM2.5 concentrations. This study not only quantifies the primary factors exacerbating or alleviating pollution for each city or province during the 2000-2021 period but also evaluates the influence of operational factors such as technological and public financial expenditures. In 2000, the main contributors to pollution in four heavily polluted cities included substantial nitrogen oxide emissions, inadequate technology investments, and excessive population density and liquefied gas consumption. Due to the rapid reduction in nitrogen oxide emissions, pollution levels in these cities have improved substantially. In the future, the most effective strategies for pollution reduction in these cities will focus on controlling population density and slowing down mining development. The proposed framework serves as a robust evaluation tool and can propose tailored strategies to control PM2.5 concentrations effectively in each city.

Towards Cleaner Air in Urban Areas: The Dual Influence of Urban Built Environment Factors and Regional Transport

Exposure to air pollution significantly elevates the risk of disease among urban populations. Improving city air quality requires not only traditional emission reduction strategies but also a focus on the intricate impacts of the urban built environment and meteorological elements. The complexity and diversity of factors within the urban built environment pose significant challenges to pollution control. This study employs machine learning to predict the spatial distribution of inhalable particulate matter (PM10) and fine particulate matter (PM2.5), integrating the clustering of pollutant-emitting enterprises and prevailing wind direction to trace pollutant sources. The results indicate that, compared to the multiple linear regression model, the R2 of the PM10 random forest prediction model improved from 0.64 to 0.88, while the RMSE decreased from 48.63 to 27.34. Similarly, the R2 of the PM2.5increased from 0.70 to 0.92, and the RMSE decreased from 30.85 to 15.31. High concentrations of PM10 and PM2.5 in Xi'an are primarily concentrated in the northeast and southwest of the central urban area. By integrating a kernel density analysis of polluting enterprises with the analysis of prevailing wind patterns, it is evident that particulate matter in Xi'an is substantially influenced by regional urban transport. Therefore, pollution control efforts must be enhanced through coordinated regional governance. According to the analysis results of the partial dependence plot, reducing winter temperature proves beneficial in reducing PM10 and PM2.5 levels. Effective measures encompass sprinkling and humidifying, reducing traffic emissions, and controlling various dust sources to lower PM10. Enhancing ventilation, increasing green spaces, and regulating vehicle and industrial emissions effectively reduce PM2.5. The study's findings offer a scientific foundation for administrative authorities to craft pollution reduction management policies and create adaptable territorial spatial planning. Moreover, they contribute to diminishing public exposure to pollution and improving the quality of public environmental health.

Pollution investigation of wintertime VOCs in the coastal atmosphere of the Yellow Sea: Insights from on-line photoionization-induced CI-TOFMS

Volatile Organic Compounds (VOCs) are pivotal in tropospheric atmospheric chemistry, significantly impacting the formation of photochemical smog, fine particle pollution, and the atmospheric oxidizing potential, all of which affect air quality. Chemical ionization time-of-flight mass spectrometry, renowned for its exceptional sensitivity, precision, and swift response time, has proven to be exceptionally effective for real-time VOCs monitoring. In this study, a custom-built photoionization-induced CI-TOFMS was deployed to individually detect 116 VOCs standard gases specified by the United States Environmental Protection Agency, quantifying their responses and establishing a distinctive mass spectrogram database. A 12-day comparative analysis with online gas chromatography coupled with a flame ionization detector and mass spectrometer demonstrated the high reliability of the PICI-TOFMS, confirming its effectiveness for field VOCs monitoring. During two months of stationary monitoring, the PICI-TOFMS could further refine the timing of pollution events with high temporal resolution and identified four distinct air pollution episodes, including local emissions, coal burning, sand and dust transport and festival-related pollution. Employing a Hysplit model, the Concentration Weighted Trajectory model, and a source apportionment method based on tracer gases, the air trajectories were calculated and contributions from different potential source areas were quantified. Our findings reveal that transport was the main contributor to pollution in December 2022, while burning was the primary source in January 2023. This study refines our understanding of the dynamics of air pollution, providing valuable insights into the temporal and spatial distribution of VOCs and their sources.

Exploring the relationship between personal exposure to multiple water-soluble components and ROS in size-resolved PMs in solid fuel combustion households

Water-soluble species are the main components of particulate matters (PMs), which have important impacts on visibility, climate change and human health. Here, personal exposure (PE) to size-resolved PMs from housewives using different solid fuels (biomass and coal) was collected during winter in rural Yuncheng city, Fenwei Plain, China. The concentrations of water-soluble organic carbon (WSOC) and reactive oxygen species (ROS) were higher in the biomass group than coal group, whereas the concentrations of water-soluble inorganic ions and water-soluble nitrogen were higher in the coal group than biomass group. Almost all measured water-soluble components in both groups showed a pattern of increasing concentration with decreasing particle size, with more than 50% of WSOC and water-soluble total nitrogen (WSTN) enriched in PM0.25. The Pearson correlation result was in general agreement with the relationship between water-soluble components and ROS found by random forest model. There was a strong positive correlation between ROS and WSOC in PMs in the coal group, especially in PMs <0.25 μm, which may be due to the emission of a large number of transition metals chelated with WSOC from coal combustion. The contribution of Cl- and F- to ROS was greater in the biomass group. NO2- in both coal and biomass groups had a decent positive effect on ROS generation. The strongest positive linear correlation (R = 0.95) between ROS and K+ in total suspended particulates in the biomass group, whereas there was almost no contribution of K+ to ROS when particle size was distinguished or in random forest model, which reflects the specificity of K+ in inducing ROS. The present study provides new insights for a deeper exploration of the relationship between water-soluble components and oxidative potential in PE PMs from domestic combustion sources.

Challenges in Observation of Ultrafine Particles: Addressing Estimation Miscalculations and the Necessity of Temporal Trends

Ultrafine particles (UFPs) pose a significant health risk, making comprehensive assessment essential. The influence of emission sources on particle concentrations is not only constrained by meteorological conditions but often intertwined with them, making it challenging to separate these effects. This study utilized valuable long-term particle number and size distribution (PNSD) data from 2018 to 2023 to develop a tree-based machine learning model enhanced with an interpretable component, incorporating temporal markers to characterize background or time series residuals. Our results demonstrated that, differing from PM2.5, which is significantly shaped by planetary boundary layer height, wind speed plays a crucial role in determining the particle number concentration (PNC), showing strong regional specificity. Furthermore, we systematically identified and analyzed anthropogenically influenced periodic trends. Notably, while Aitken mode observations are initially linked to traffic-related peaks, both Aitken and nucleation modes contribute to concentration peaks during rush hour periods on short-term impacts after deweather adjustment. Pollutant baseline concentrations are largely driven by human activities, with meteorological factors modulating their variability, and the secondary formation of UFPs is likely reflected in temporal residuals. This study provides a flexible framework for isolating meteorological effects, allowing more accurate assessment of anthropogenic impacts and targeted management strategies for UFP and PNC.

Significant spatiotemporal changes in atmospheric particulate mercury pollution in China: Insights from meta-analysis and machine-learning

PM2.5 bound mercury (PBM2.5) in the atmosphere is a major component of total mercury, which is a pollutant of global concern and a potent neurotoxicant when converted to methylmercury. Despite its importance, comprehensive macroanalyses of PBM2.5 on large scales are still lacking. To explore the driving factors, spatiotemporal pollution distribution, and associated health risks, we compiled a comprehensive dataset consisting of PBM2.5 concentrations and spatiotemporal information across China from 2000 to 2023 that was collected from the published scientific literature with valid data. By incorporating corresponding multidimensional predicting variables, the best-fitted random forest model was applied to predict PBM2.5 concentrations with a high spatial resolution of 0.25° × 0.25°, and the health risk assessment model was used for subsequent health risk assessment. Our results indicated that population density and PM2.5 emissions from power generation were the main contributors to PBM2.5 concentrations. In 2020, the pollution was primarily concentrated in northern, central, and eastern China, with the highest annual average concentration of 815.91 pg/m3 in Shanghai. Beijing experienced the most significant seasonal increase, with PBM2.5 concentrations rising by 146.92 % from summer to winter. Nationally, the annual average PBM2.5 pollution decreased extensively and markedly from 2015 to 2020. The non-carcinogenic risk of PBM2.5 alone was negligible in 2020, with HQ values generally <0.02 in winter. This study may provide an important assessment of the effectiveness of China's measures against mercury pollution and offer valuable insights for future prevention and control of PBM2.5 pollution.

Effects of Various Heavy Metal Exposures on Insulin Resistance in Non-diabetic Populations: Interpretability Analysis from Machine Learning Modeling Perspective

Increasing and compelling evidence has been proved that heavy metal exposure is involved in the development of insulin resistance (IR). We trained an interpretable predictive machine learning (ML) model for IR in the non-diabetic populations based on levels of heavy metal exposure. A total of 4354 participants from the NHANES (2003-2020) with complete information were randomly divided into a training set and a test set. Twelve ML algorithms, including random forest (RF), XGBoost (XGB), logistic regression (LR), GaussianNB (GNB), ridge regression (RR), support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), AdaBoost (AB), Gradient Boosting Decision Tree (GBDT), Voting Classifier (VC), and K-Nearest Neighbour (KNN), were constructed for IR prediction using the training set. Among these models, the RF algorithm had the best predictive performance, showing an accuracy of 80.14%, an AUC of 0.856, and an F1 score of 0.74 in the test set. We embedded three interpretable methods, the permutation feature importance analysis, partial dependence plot (PDP), and Shapley additive explanations (SHAP) in RF model for model interpretation. Urinary Ba, urinary Mo, blood Pb, and blood Cd levels were identified as the main influencers of IR. Within a specific range, urinary Ba (0.56-3.56 µg/L) and urinary Mo (1.06-20.25 µg/L) levels exhibited the most pronounced upwards trend with the risk of IR, while blood Pb (0.05-2.81 µg/dL) and blood Cd (0.24-0.65 µg/L) levels showed a declining trend with IR. The findings on the synergistic effects demonstrated that controlling urinary Ba levels might be more crucial for the management of IR. The SHAP decision plot offered personalized care for IR based on heavy metal control. In conclusion, by utilizing interpretable ML approaches, we emphasize the predictive value of heavy metals for IR, especially Ba, Mo, Pb, and Cd.

Integrating Doppler LiDAR and machine learning into land-use regression model for assessing contribution of vertical atmospheric processes to urban PM2.5 pollution

Air pollution has been recognized as a global issue, through adverse effects on environment and health. While vertical atmospheric processes substantially affect urban air pollution, traditional epidemiological research using Land-use regression (LUR) modeling usually focused on ground-level attributes without considering upper-level atmospheric conditions. This study aimed to integrate Doppler LiDAR and machine learning techniques into LUR models (LURF-LiDAR) to comprehensively evaluate urban air pollution in Hong Kong, and to assess complex interactions between vertical atmospheric processes and urban air pollution from long-term (i.e., annual) and short-term (i.e., two air pollution episodes) views in 2021. The results demonstrated significant improvements in model performance, achieving CV R2 values of 0.81 (95 % CI: 0.75-0.86) for the long-term PM2.5 prediction model and 0.90 (95 % CI: 0.87-0.91) for the short-term models. Approximately 69 % of ground-level air pollution arose from the mixing of ground- and lower-level (105 m-225 m) particles, while 21 % was associated with upper-level (825 m-945 m) atmospheric processes. The identified transboundary air pollution (TAP) layer was located at ~900 m above the ground. The identified Episode one (E1: 7 Jan-22 Jan) was induced by the accumulation of local emissions under stable atmospheric conditions, whereas Episode two (E2: 13 Dec-24 Dec) was regulated by TAP under instable and turbulent conditions. Our improved air quality prediction model is accurate and comprehensive with high interpretability for supporting urban planning and air quality policies.

Spatial patterns and mechanism of the impact of soil salinity on potentially toxic elements in coastal areas

Soil salinization and heavy metal pollution in the Yellow River Delta region have elicited increasing concern. Therefore, revealing the underlying mechanism of the impact of soil salinity on potential toxic elements (PTEs) is crucial for environmental protection and the rational utilization of resources in this area. In this study, we employed CatBoost-SHAP and multiscale geographically weighted regression (MGWR) models to comprehensively investigate the spatial effects of soil electrical conductivity (EC1:5) on PTEs. Additionally, we employed a space-for-time substitution strategy with the aim of investigating how increasing soil salinity, represented by EC1:5, K+, Na+, Ca2+, and Mg2+, affects the bioavailability of PTEs over time. The primary findings are as follows: (1) for most PTEs, the influence of soil EC1:5 on the bioavailable forms of these elements surpassed its impact on their total concentrations. (2) The results of the MGWR model indicated that exchangeable Ca (aCa) in the soils of the eastern coastal areas markedly increased the bioavailable Cd (aCd), bioavailable Cu (aCu), and bioavailable Zn (aZn). (3) When the soil EC1:5 ranges between 2 and 6 dS/m, exchangeable Na (aNa) primarily competed for the adsorption sites of bioavailable Pb (aPb). However, as the soil EC1:5 increases to 6-10 dS/m, exchangeable Mg (aMg) and aCa became the primary competing ions, with aMg playing a more significant role than aCa. These findings provide valuable theoretical insights and practical guidance for saline-alkali soil improvement and PTEs pollution control in the Yellow River Delta region, thereby providing a foundation for sustainable environmental management and resource utilization.

Quantifying the pollution changes and meteorological dependence of airborne trace elements coupling source apportionment and machine learning

Airborne trace elements (TEs) present in atmospheric fine particulate matter (PM2.5) exert notable threats to human health and ecosystems. To explore the impact of meteorological conditions on shaping the pollution characteristics of TEs and the associated health risks, we quantified the variations in pollution characteristics and health risks of TEs due to meteorological impacts using weather normalization and health risk assessment models, and analyzed the source-specific contributions and potential sources of primary TEs affecting health risks using source apportionment approaches at four sites in Shandong Province from September to December 2021. Our results indicated that TEs experience dual effects from meteorological conditions, with a tendency towards higher TE concentrations and related health risks during polluted period, while the opposite occurred during clean period. The total non-carcinogenic and carcinogenic risks of TEs during polluted period increased approximately by factors of 0.53-1.74 and 0.44-1.92, respectively. Selenium (Se), manganese (Mn), and lead (Pb) were found to be the most meteorologically influenced TEs, while chromium (Cr) and manganese (Mn) were identified as the dominant TEs posing health risks. Enhanced emissions of multiple sources for Cr and Mn were found during polluted period. Depending on specific wind speeds, industrialized and urbanized centers, as well as nearby road dusts, could be key sources for TEs. This study suggested that attentions should be paid to not only the TEs from primary emissions but also the meteorology impact on TEs especially during pollution episodes to reduce health risks in the future.

Spatial source, simulating improvement, and short-term health effect of high PM2.5 exposure during mutation event in the key urban agglomeration regions in China

Air quality in China has significantly improved owing to the effective implementation of pollution control measures. However, mutation events caused by short-term spikes in PM2.5 in urban agglomeration regions continue to occur frequently. Identifying the spatial sources and influencing factors, as well as improving the prediction accuracy of high PM2.5 during mutation events, are crucial for public health. In this study, we firstly introduced discrete wavelet transform (DWT) to identify the mutation events with high PM2.5 concentration in the four key urban agglomerations, and evaluated the spatial sources for the polluted scenario using Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model. Additionally, DWT was combined with a widely used artificial neural network (ANN) to improve the prediction accuracy of PM2.5 concentration seven days in advance (seven-day forecast). Results indicated that mutation events commonly occurred in the northern regions during winter time, which were under the control of both short-range transportation of dirty airmass as well as negative meteorology conditions. Compared with the ANN model alone, the average band errors decreased by 9% when using DWT-ANN model. The average correlation coefficient (R) and root mean square error (RMSE) obtained using the DWT-ANN improved by 10% and 12% compared to those obtained using the ANN, indicating the efficiency and accuracy of simulating PM2.5, by combining the DWT and ANN. The short-term mortality during mutation events was then calculated, with the total averted all-cause, cardiovascular, and respiratory deaths in the four regions, being 4751, 2554, and 582 persons, respectively. A declining trend in prevented deaths from 2018 to 2020 demonstrated that the pollution intensity during mutation events gradually decreased owing to the implementation of the Three-Year Action Plan to Win the Blue Sky Defense War. The method proposed in this study can be used by policymakers to take preventive measures in response to a sudden increase in PM2.5, thereby ensuring public health.

A machine learning algorithm to explore the drivers of carbon emissions in Chinese cities

As the world's largest energy consumer and carbon emitter, the task of carbon emission reduction is imminent. In order to realize the dual-carbon goal at an early date, it is necessary to study the key factors affecting China's carbon emissions and their non-linear relationships. This paper compares the performance of six machine learning algorithms to that of traditional econometric models in predicting carbon emissions in China from 2011 to 2020 using panel data from 254 cities in China. Specifically, it analyzes the comparative importance of domestic economic, external economic, and policy uncertainty factors as well as the nonparametric relationship between these factors and carbon emissions based on the Extra-trees model. Results show that energy consumption (ENC) remains the root cause of increased carbon emissions among domestic economic factors, although government intervention (GOV) and digital finance (DIG) can significantly reduce it. Next, among the external economic and policy uncertainty factors, foreign direct investment (FDI) and economic policy uncertainty (EPU) are important factors influencing carbon emissions, and the partial dependence plots (PDPs) confirm the pollution haven hypothesis and also reveal the role of EPU in reducing carbon emissions. The heterogeneity of factors affecting carbon emissions is also analyzed under different city sizes, and it is found that ENC is a common driving factor in cities of different sizes, but there are some differences. Finally, appropriate policy recommendations are proposed by us to help China move rapidly towards a green and sustainable development path.

Sources and formation characteristics of particulate nitrate in the Pearl River Delta region of China: Insights from three-year online observations

Nitrate (NO3-) has been identified as a key component of particulate matter (PM2.5) in China. However, there is still a lack of understanding regarding its sources and how it forms, especially in the context of high-frequency and long-term data. In this study, NO3- levels were observed on an hourly basis over an almost three-year period at an urban site in the Pearl River Delta (PRD) region, China, from January 2019 to December 2021. The results reveal an average daily NO3- concentration ranging from 0.08 μg m-3 to 61.69 μg m-3, constituting 11.9 ± 12.5 % of PM2.5. This percentage rose to as high as 57 % during pollution episodes, highlighting NO3-'s significant role in pollution formation. The ammonia-rich environment was found to be the most important factor in promoting NO3- formation. Positive Matrix Factorization (PMF) analysis indicates that the primary sources of NO3- in the PRD region were vehicle emissions (43.8 ± 21.2 %) and coal combustion (39.1 ± 21.5 %), with shipping emissions, sea salt, soil dust and industrial emissions + biomass burning following in importance. Regarding source areas, the primary contributor of vehicle emissions was predominantly from the PRD region, whereas the coal combustion, aside from local contributions, also originates from the northern region. From a long-term perspective, NO3- pollution has remained relatively stable since the summer of 2020. Concurrently, coal combustion source has shown a localization trend. These insights derived from the extensive, high-frequency observation presented in this study serve as a valuable reference for devising strategies to control NO3- and PM2.5 in the PRD region and China.

Domain knowledge-enhanced multi-spatial multi-temporal PM2.5 forecasting with integrated monitoring and reanalysis data

Accurate air quality forecasting is crucial for public health, environmental monitoring and protection, and urban planning. However, existing methods fail to effectively utilize multi-scale information, both spatially and temporally. There is a lack of integration between individual monitoring stations and city-wide scales. Temporally, the periodic nature of air quality variations is often overlooked or inadequately considered. To overcome these limitations, we conduct a thorough analysis of the data and tasks, integrating spatio-temporal multi-scale domain knowledge. We present a novel Multi-spatial Multi-temporal air quality forecasting method based on Graph Convolutional Networks and Gated Recurrent Units (M2G2), bridging the gap in air quality forecasting across spatial and temporal scales. The proposed framework consists of two modules: Multi-scale Spatial GCN (MS-GCN) for spatial information fusion and Multi-scale Temporal GRU (MT-GRU) for temporal information integration. In the spatial dimension, the MS-GCN module employs a bidirectional learnable structure and a residual structure, enabling comprehensive information exchange between individual monitoring stations and the city-scale graph. Regarding the temporal dimension, the MT-GRU module adaptively combines information from different temporal scales through parallel hidden states. Leveraging meteorological indicators and four air quality indicators, we present comprehensive comparative analyses and ablation experiments, showcasing the higher accuracy of M2G2 in comparison to nine currently available advanced approaches across all aspects. The improvements of M2G2 over the second-best method on RMSE of 72-h future predictions are as follows: PM2.5: 6%∼10%; PM10: 5%∼7%; NO2: 5%∼16%; O3: 6%∼9%. Furthermore, we demonstrate the effectiveness of each module of M2G2 by ablation study. We conduct a sensitivity analysis of air quality and meteorological data, finding that the introduction of O3 adversely impacts the prediction accuracy of PM2.5.

Understanding the variability of ground-level ozone and fine particulate matter over the Tibetan plateau with data-driven approach

The Tibetan Plateau, known as the "Third Pole", is susceptible to ground-level ozone (O3) and fine particulate matter (PM2.5) pollution due to its unique high-altitude environment. This study constructed random forest regression models using multi-source data from ground measurements and meteorological satellites to predict variations in ground-level O3 and PM2.5 concentrations and their influencing factors across seven major cities in the Tibetan Plateau over two-year periods. The models successfully reproduced O3 and PM2.5 levels with satisfactory R-squared values of 0.71 and 0.73, respectively. Results reveal combustion-related carbon monoxide (CO) and nitrogen dioxide (NO2) as the most substantial influences on O3 and PM2.5 concentrations. Solar radiation, geographical factors, and meteorological variables also played crucial roles in driving pollutant variations. Conversely, transport-related and human activity factors exhibited relatively lower significance. High O3 and PM2.5 pollution occurred during pre-monsoon and post-monsoon/winter seasons, driven by solar radiation and emissions, respectively. While CO consistently contributed across cities and seasons, key influencing factors varied locally. This study unveils the key driving forces governing air pollutant variations across the Tibetan Plateau, shedding light on complex atmospheric processes in this unique high-altitude region.

Key drivers of the oxidative potential of PM2.5 in Beijing in the context of air quality improvement from 2018 to 2022

The mass concentration of atmospheric particulate matter (PM) has been continuously decreasing in the Beijing-Tianjin-Hebei region. However, health endpoints do not exhibit a linear correlation with PM mass concentrations. Thus, it is urgent to clarify the prior toxicological components of PM to further improve air quality. In this study, we analyzed the long-term oxidative potential (OP) of water-soluble PM2.5, which is generally considered more effective in assessing hazardous exposure to PM in Beijing from 2018 to 2022 based on the dithiothreitol assay and identified the crucial drivers of the OP of PM2.5 based on online monitoring of air pollutants, receptor model, and random forest (RF) model. Our results indicate that dust, traffic, and biomass combustion are the main sources of the OP of PM2.5 in Beijing. The complex interactions of dust particles, black carbon, and gaseous pollutants (nitrogen dioxide and sulfur dioxide) are the main factors driving the OP evolution, in particular, leading to the abnormal rise of OP in Beijing in 2022. Our data shows that a higher OP is observed in winter and spring compared to summer and autumn. The diurnal variation of the OP is characterized by a declining trend from 0:00 to 14:00 and an increasing trend from 14:00 to 23:00. The spatial variation in OP of PM2.5 was observed as the OP in Beijing is lower than that in Shijiazhuang, while it is higher than that in Zhenjiang and Haikou, which is primarily influenced by the distribution of black carbon. Our results are of significance in identifying the key drivers influencing the OP of PM2.5 and provide new insights for advancing air quality improvement efforts with a focus on safeguarding human health in Beijing.

Exploring the primary magnetic parameters affecting chemical fractions of heavy metal(loid)s in lake sediment through an interpretable workflow

The magnetic properties of lake sediments account for close relationships with heavy metal(loid)s (HMs), but little is known about their relationships with chemical fractions (CFs) of HMs. Establishing an effective workflow to predict HMs risk among various machine learning (ML) methods in conjunction with magnetic measurement remains challenging. This study evaluated the simulation efficiency of nine ML methods in predicting the risk assessment code (RAC) and ratio of the secondary and primary phases (RSP) of HMs with magnetic parameters in sediment cores of a shallow lake. The sediment cores were collected and sliced, and the total amount and CFs of HMs, as well as magnetic parameters, were determined. Support vector machine (SVM) outperformed other models, as evidenced by coefficient of determination (R2) > 0.8. Interpretable machine learning (IML) methods were employed to identify key indicators of RAC and RSP among the magnetic parameters. Values of χARM, HIRM, χARM/χ, and χARM/SIRM of sediments ranging in 220-500 × 10-8 m3/kg, 30-40 × 10-5Am2/kg, 15-25, and 0.5-1, respectively, indicated the potential ecological risks of Cd, Hg, and Sb. This study offers new perspectives on the risk assessment of HMs in lake sediments by combining magnetic measurement with IML workflow.

Development and application of a multi-task oriented deep learning model for quantifying drivers of air pollutant variations: A case study in Taiyuan, China

Quantitative assessment of the drivers behind the variation of six criteria pollutants, namely fine particulate matter (PM2.5), ozone (O3), nitrogen dioxide (NO2), sulfur dioxide (SO2), particulate matter (PM10), and carbon monoxide (CO), in the warming climate will be critical for subsequent decision-making. Here, a novel hybrid model of multi-task oriented CNN-BiLSTM-Attention was proposed and performed in Taiyuan during 2015-2020 to synchronously and quickly quantify the impact of anthropogenic and meteorological factors on the six criteria pollutants variations. Empirical results revealed the residential and transportation sectors distinctly decreased SO2 by 25 % and 22 % and CO by 12 % and 10 %. Gradual downward trends for PM2.5, PM10, and NO2 were mainly ascribed to the stringent measures implemented in transportation and power sectors as part of the Blue Sky Defense War, which were further reinforced by the COVID-19 pandemic. Nevertheless, temperature-dependent adverse meteorological effects (27 %) and anthropogenic intervention (12 %) jointly increased O3 by 39 %. The O3-driven pollution events may be inevitable or even become more prominent under climate warming. The industrial (5 %) and transportation sectors (6 %) were mainly responsible for the anthropogenic-driven increase of O3 and precursor NO2, respectively. Synergistic reduction of precursors (VOCs and NOx) from industrial and transportation sectors requires coordination with climate actions to mitigate the temperature-dependent O3-driven pollution, thereby improving regional air quality. Meanwhile, the proposed model is expected to be applied flexibly in various regions to quantify the drivers of the pollutant variations in a warming climate, with the potential to offer valuable insights for improving regional air quality in near future.

Weather and the City: Machine Learning for Predicting and Attributing Fine Scale Air Quality to Meteorological and Urban Determinants

Urban air quality persists as a global concern, with critical health implications. This study employs a combination of machine learning (gradient boosting regression, GBR) and spatial analysis to better understand the key drivers behind air pollution and its prediction and mitigation strategies. Focusing on New York City as a representative urban area, we investigate the interplay between urban characteristics and weather factors, showing that urban features, including traffic-related parameters and urban morphology, emerge as crucial predictors for pollutants closely associated with vehicular emissions, such as elemental carbon (EC) and nitrogen oxides (NOx). Conversely, pollutants with secondary formation pathways (e.g., PM2.5) or stemming from nontraffic sources (e.g., sulfur dioxide, SO2) are predominantly influenced by meteorological conditions, particularly wind speed and maximum daily temperature. Urban characteristics are shown to act over spatial scales of 500 × 500 m2, which is thus the footprint needed to effectively capture the impact of urban form, fabric, and function. Our spatial predictive model, needing only meteorological and urban inputs, achieves promising results with mean absolute errors ranging from 8 to 32% when using full-year data. Our approach also yields good performance when applied to the temporal mapping of spatial pollutant variability. Our findings highlight the interacting roles of urban characteristics and weather conditions and can inform urban planning, design, and policy.

Spatial distribution and source identification of potentially toxic elements in Yellow River Delta soils, China: An interpretable machine-learning approach

Identifying the driving factors and quantifying the sources of potentially toxic elements (PTEs) are essential for protecting the ecological environment of the Yellow River Delta. In this study, data from 201 surface soil samples and 16 environmental variables were collected, and the random forest (RF) and Shapley additive explanations (SHAP) methods were then combined to explore the key factors affecting soil PTEs. An innovative t-distributed random neighbor embedding-RF-SHAP model was then constructed, based on the absolute principal component score and multivariate linear regression model, to quantitatively determine PTE sources. Although average PTE concentrations did not exceed the risk control values, PTE distributions exhibited significant differences. It was found that sodium, soil organic matter, and phosphorus contents were the three most important factors affecting PTEs, and human activities and natural environmental factors both influence PTE contents by altering the soil properties. The proposed model successfully determined PTE sources in the soil, outperforming the original linear regression model with a significantly lower RMSE. Source analysis revealed that the parent material was the main contributor to soil PTEs, accounting for more than half of the total PTE content. Industrial and agricultural activities also contributed to an increase in soil PTEs, with average contributions of 19.91 % and 17.44 %, respectively. Unknown sources accounted for 10.83 % of the total PTE content. Thus, the proposed model provides innovative perspectives on source parsing. These findings provide valuable scientific insights for policymakers seeking to develop effective environmental protection measures and improve the quality of saline-alkali land in the Yellow River Delta.

Application of machine learning in atmospheric pollution research: A state-of-art review

Machine learning (ML) is an artificial intelligence technology that has been used in atmospheric pollution research due to their powerful fitting ability. In this review, 105 articles related to ML and the atmospheric pollution research are critically reviewed. Applications of ML in the prediction of atmospheric pollution (mainly particulate matters) are systematically described, including the principle of prediction, influencing factors and improvement measures. Researchers can improve the accuracy of the prediction model through three main aspects, namely considering the geographical features of the study area into the model, introducing the physical characteristics of pollutants, matching and optimizing ML models. And by using interpretable ML tools, researchers are able to understand the mechanism of the model and gain in-depth information. Then, the state-of-art applications of ML in the source apportionment of atmospheric particulate matter and the effect of atmospheric pollutants on human health are also described. In addition, the advantages and disadvantages of the current applications of ML in atmospheric pollution research are summarized, and the application perspective of ML in this field is elucidated. Given the scarcity of source apportionment applications and human health research, standardized research methods and specialized ML methods are required in atmospheric pollution research to connect these two disciplines.

Characteristics of secondary inorganic aerosols and contributions to PM2.5 pollution based on machine learning approach in Shandong Province

Primary emissions of particulate matter and gaseous pollutants, such as SO2 and NOx have decreased in China following the implementation of a series of policies by the Chinese government to address air pollution. However, controlling secondary inorganic aerosol pollution requires attention. This study examined the characteristics of the secondary conversion of nitrate (NO3-) and sulfate (SO42-) in three coastal cities of Shandong Province, namely Binzhou (BZ), Dongying (DY), and Weifang (WF), and an inland city, Jinan (JN), during December 2021. Furthermore, the Shapley Additive Explanation (SHAP), an interpretable attribution technique, was adopted to accurately calculate the contributions of secondary formations to PM2.5. The nitrogen oxidation rate exhibited a significant dependence on the concentration of O3. High humidity facilitates sulfur oxidation. Compared to BZ, DY, and WF, the secondary conversion of NO3- and SO42- was more intense in JN. The light-gradient boosting model outperformed the random forest and extreme-gradient boosting models, achieving a mean R2 value of 0.92. PM2.5 pollution events in BZ, DY, and WF were primarily attributable to biomass burning, whereas pollution in Jinan was contributed by the secondary formation of NO3- and vehicle emissions. Machine learning and the SHAP interpretable attribution technique offer a precise analysis of the causes of air pollution, showing high potential for addressing environmental concerns.

Effects of heavy metal exposure on hypertension: A machine learning modeling approach

Heavy metal exposure is a common risk factor for hypertension. To develop an interpretable predictive machine learning (ML) model for hypertension based on levels of heavy metal exposure, data from the NHANES (2003-2016) were employed. Random forest (RF), support vector machine (SVM), decision tree (DT), multilayer perceptron (MLP), ridge regression (RR), AdaBoost (AB), gradient boosting decision tree (GBDT), voting classifier (VC), and K-nearest neighbour (KNN) algorithms were utilized to generate an optimal predictive model for hypertension. Three interpretable methods, the permutation feature importance analysis, partial dependence plot (PDP), and Shapley additive explanations (SHAP) methods, were integrated into a pipeline and embedded in ML for model interpretation. A total of 9005 eligible individuals were randomly allocated into two distinct sets for predictive model training and validation. The results showed that among the predictive models, the RF model demonstrated the highest performance, achieving an accuracy rate of 77.40% in the validation set. The AUC and F1 score for the model were 0.84 and 0.76, respectively. Blood Pb, urinary Cd, urinary Tl, and urinary Co levels were identified as the main influencers of hypertension, and their contribution weights were 0.0504 ± 0.0482, 0.0389 ± 0.0256, 0.0307 ± 0.0179, and 0.0296 ± 0.0162, respectively. Blood Pb (0.55-2.93 μg/dL) and urinary Cd (0.06-0.15 μg/L) levels exhibited the most pronounced upwards trend with the risk of hypertension within a specific value range, while urinary Tl (0.06-0.26 μg/L) and urinary Co (0.02-0.32 μg/L) levels demonstrated a declining trend with hypertension. The findings on the synergistic effects indicated that Pb and Cd were the primary determinants of hypertension. Our findings underscore the predictive value of heavy metals for hypertension. By utilizing interpretable methods, we discerned that Pb, Cd, Tl, and Co emerged as noteworthy contributors within the predictive model.