Machine learning and deep learning modeling and simulation for predicting PM2.5 concentrations

Monitoring air quality index with EWMA and individual charts using XGBoost and SVR residuals

PM2.5 air pollution poses significant health risks, particularly in urban areas such as Jakarta, where concentrations frequently surpass acceptable levels due to rapid urbanization. This study addresses autocorrelation in air quality data and evaluates the monitoring performance of XGBoost and Support Vector Regression (SVR) models using Individual and Exponentially Weighted Moving Average (EWMA) Charts. PM2.5 levels were obtained from Jakarta's Air Quality Index. The findings reveal that the SVR model effectively manages autocorrelation, while the combination of XGBoost and the EWMA chart yielded superior monitoring performance. Specifically, this approach detected only one out-of-control (OOC) point in Phase II and none in Phase I, with identified shifts ranging from moderate to large. Overall, the XGBoost and EWMA chart integration offers a robust solution for precise air quality monitoring and minimizes false alarms. The identification of OOC points provides actionable insights by highlighting significant deviations in air quality data that may require immediate intervention. Key points:•SVR and XGBoost model regression was introduced to enhance forecasting accuracy.•EWMA chart based on XGBoost residuals has better monitoring results.

Interpreting hourly mass concentrations of PM2.5 chemical components with an optimal deep-learning model

PM2.5 constitutes a complex and diverse mixture that significantly impacts the environment, human health, and climate change. However, existing observation and numerical simulation techniques have limitations, such as a lack of data, high acquisition costs, and multiple uncertainties. These limitations hinder the acquisition of comprehensive information on PM2.5 chemical composition and effectively implement refined air pollution protection and control strategies. In this study, we developed an optimal deep learning model to acquire hourly mass concentrations of key PM2.5 chemical components without complex chemical analysis. The model was trained using a randomly partitioned multivariate dataset arranged in chronological order, including atmospheric state indicators, which previous studies did not consider. Our results showed that the correlation coefficients of key chemical components were no less than 0.96, and the root mean square errors ranged from 0.20 to 2.11 µg/m3 for the entire process (training and testing combined). The model accurately captured the temporal characteristics of key chemical components, outperforming typical machine-learning models, previous studies, and global reanalysis datasets (such as Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) and Copernicus Atmosphere Monitoring Service ReAnalysis (CAMSRA)). We also quantified the feature importance using the random forest model, which showed that PM2.5, PM1, visibility, and temperature were the most influential variables for key chemical components. In conclusion, this study presents a practical approach to accurately obtain chemical composition information that can contribute to filling missing data, improved air pollution monitoring and source identification. This approach has the potential to enhance air pollution control strategies and promote public health and environmental sustainability.

Prediction of school PM2.5 by an attention-based deep learning approach informed with data from nearby air quality monitoring stations

Predicting indoor air pollutants concentrations in schools is essential for ensuring a healthy learning environment. Traditional measurements methods pose challenges in cost, maintenance, and time. This study proposes a new approach using a deep learning (DL)-based soft sensor to predict PM2.5 concentrations in school environment both indoor (classroom) and outdoor (playground). The proposed soft sensor, based on attention deep convolutional autoencoder (ADCAE), leverages data from nearby monitoring stations, completely eliminating the need for school on-site sensors and the attendant financial and technical costs of installation, operation, and maintenance. Results indicate superior predictive performance of the ADCAE model compared to traditional machine learning methods, with significantly higher coefficient of determination (R2), lower mean squared error and lower mean absolute error across all studied schools. The prediction accuracy reached 0.97, 0.976, and 0.936 for indoor PM2.5 in the elementary school, middle school, and high school, respectively, while the school outdoor PM2.5 showed even a higher prediction performance with R2 values of 0.9923, 0.9869, and 0.943. Thus, the developed soft sensor based on DL is a promising tool to effectively monitor air quality in schools and to capture response measures to fine dust pollution at schools.

Spatiotemporal modeling of long-term PM2.5 concentrations and population exposure in Greece, using machine learning and statistical methods

The lack of high-resolution, long-term PM2.5 observations in Greece and the Eastern Mediterranean hampers the development of spatial models that are crucial for providing representative exposure estimates to health studies. This work presents a spatial modeling approach to address this gap and assess PM2.5 spatial variability for the first time on a national level in Greece, by integrating in situ observations, meteorology, emissions and satellite AOD data among others. A high-resolution (1 km2) gridded dataset of PM2.5 concentrations across Greece from 2015 to 2022 was developed, and seven statistical, machine learning, and hybrid models were evaluated under different prediction scenarios. Random Forest (RF) models demonstrated superior performance, (R2 = 0.73, MAE = 2.2 μg m-3), validated against ground-based measurements. Winter months consistently showed the highest PM2.5 levels, averaging 16.8 μg m-3, over the domain, due to residential biomass burning (BB) and limited atmospheric dispersion. Summer months had the lowest concentrations, averaging 10.3 μg m-3, while substantial decreases nationwide were observed during the 2020 COVID-19 lockdown. Population exposure analysis indicated that the entire Greek population was exposed to long-term PM2.5 concentrations exceeding the WHO air quality guideline (AQG) of 5 μg m-3. Moreover, the dataset revealed elevated PM2.5 levels across several regions of mainland Greece. Notably, 70 % to 90 % of the population experience levels exceeding 10 μg m-3 in Central and Northern regions of continental Greece like Thessaly, Central Macedonia, and Ioannina. The Ioannina region, which is severely impacted by residential BB, recorded pollution levels up to five times the WHO AQG highlighting the urgent need for targeted interventions. The high-resolution RF model's superior performance for monthly average concentrations, compared to the Copernicus Atmosphere Monitoring Service (CAMS) dataset, renders it a reliable tool for long-term PM2.5 assessment in Greece that can support air quality management and health studies.

Spatiotemporal distribution prediction for PM2.5 based on STXGBoost model and high-density monitoring sensors in Zhengzhou High Tech Zone, China

The increasing demand for air pollution control has driven the application of low-cost sensors (LCS) in air quality monitoring, enabling higher observation density and improved air quality predictions. However, the inherent limitations in data quality from LCS necessitate the development of effective methodologies to optimize their application. This study established a hybrid framework to enhance the accuracy of spatiotemporal predictions of PM2.5, standard instrument measurements were employed as reference data for the remote calibration of LCS. To account for local emission characteristics, the calibration model was trained using statistical values from LCS during periods of reduced anthropogenic emissions. This calibration approach significantly improved data quality, increasing R2 values of LCS data from 0.60 to 0.85. Subsequently, an advanced predictive model, STXGBoost, was developed, combining Kriging interpolation technology with high-density LCS data to integrate temporal trends and geographic spatial correlations. The STXGBoost model effectively captured the spatiotemporal variability of PM2.5 data, producing accurate and high spatiotemporal resolution PM2.5 prediction maps, with R2 values of 0.96, 0.92, and 0.89 for 1-h, 4-h, and 48-h predictions, respectively. These findings demonstrate the feasibility of generating high-resolution urban air pollution maps by integrating high-density ground monitoring data with advanced computational approaches. This framework provides valuable support for precise management and informed decision-making in urban atmospheric environments.

Artificial intelligence in microplastic detection and pollution control

The rising prevalence of microplastics (MPs) in various ecosystems has increased the demand for advanced detection and mitigation strategies. This review examines the integration of artificial intelligence (AI) with environmental science to improve microplastic detection. Focusing on image processing, Fourier transform infrared spectroscopy (FTIR), Raman spectroscopy, and hyperspectral imaging (HSI), the review highlights how AI enhances the efficiency and accuracy of these techniques. AI-driven image processing automates the identification and quantification of MPs, significantly reducing the need for manual analysis. FTIR and Raman spectroscopy accurately distinguish MP types by analyzing their unique spectral features, while HSI captures extensive spatial and spectral data, facilitating detection in complex environmental matrices. Furthermore, AI algorithms integrate data from these methods, enabling real-time monitoring, traceability prediction, and pollution hotspot identification. The synergy between AI and spectral imaging technologies represents a transformative approach to environmental monitoring and emphasizes the need to adopt innovative tools for protecting ecosystem health.

Towards Cleaner Cities: Estimating Vehicle-Induced PM2.5 with Hybrid EBM-CMA-ES Modeling

In developing countries, vehicle emissions are a major source of atmospheric pollution, worsened by aging vehicle fleets and less stringent emissions regulations. This results in elevated levels of particulate matter, contributing to the degradation of urban air quality and increasing concerns over the broader effects of atmospheric emissions on human health. This study proposes a Hybrid Explainable Boosting Machine (EBM) framework, optimized using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), to predict vehicle-related PM2.5 concentrations and analyze contributing factors. Air quality data were collected from Open-Seneca sensors installed along the Nairobi Expressway, alongside meteorological and traffic data. The CMA-ES-tuned EBM model achieved a Mean Absolute Error (MAE) of 2.033 and an R2 of 0.843, outperforming other models. A key strength of the EBM is its interpretability, revealing that the location was the most critical factor influencing PM2.5 concentrations, followed by humidity and temperature. Elevated PM2.5 levels were observed near the Westlands roundabout, and medium to high humidity correlated with higher PM2.5 levels. Furthermore, the interaction between humidity and traffic volume played a significant role in determining PM2.5 concentrations. By combining CMA-ES for hyperparameter optimization and EBM for prediction and interpretation, this study provides both high predictive accuracy and valuable insights into the environmental drivers of urban air pollution, providing practical guidance for air quality management.

Accurate and efficient prediction of atmospheric PM1, PM2.5, PM10, and O3 concentrations using a customized software package based on a machine-learning algorithm

Particulate matter (PM) and ozone (O3) pollution have been attracting increasing attention recently due to their severe harm to human health. PM and O3 are secondary pollutants, and there remain significant challenges in accurately and efficiently predicting their concentrations in the atmosphere. In this study, one-year monitoring data of PM1, PM2.5, PM10, and O3 concentrations as well as meteorological parameters and concentrations of various precursors (i.e., nitrogen oxides, SO2, CO, alkanes, aldehydes, and ketones) are obtained at a monitoring site in central China's Hunan province. The eXtreme Gradient Boosting model is trained and tested to achieve efficient and accurate predictions of the concentrations of the four pollutants. The effects of different datasets, input features, and model parameters on the prediction accuracy are investigated. Principal component analysis is employed to further reduce the dimensions of features, increasing the prediction efficiency. Finally, all model training and prediction processes are incorporated in an executable application using the PyQt5 framework to build a user interface. The customized software supports user-defined modeling. The software can simultaneously predict PM1, PM2.5, PM10, and O3 concentrations, making the prediction process convenient.

Impact of COVID-19 restrictions liberalization on air quality: a case study of Chongqing, Southwest China

To mitigate the societal impact of the COVID-19 pandemic, China implemented long-term restrictive measures. The sudden liberalization at the end of 2022 disrupted residents' daily routines, making it scientifically intriguing to explore its effect on air quality. Taking Chongqing City in Southwest China as an example, we examined the impact of restriction liberalization on air quality, identified potential sources of pollutants, simulated the effects of abrupt anthropogenic control relaxation using a Random Forest Model, and applied an optimized model to predict the post-liberalization pollutant concentrations. The results showed increases in PM2.5 (72.3%), PM10 (67.7%), and NO2 (21.9%) concentrations, while O3 concentration decreased by 20.5%. Although potential pollution source areas contracted, pollution levels intensified with northeastern Sichuan, interior Chongqing, and northern Guizhou being major contributors to pollutant emissions. Anthropogenic emissions accounted for 26.7 ~ 33% changes in PM2.5 and PM10 concentrations while meteorological conditions contributed to 40.2 ~ 43.3% variations observed during the period. The optimized model demonstrated a correlation between predicted and observed values with R2 ranging from 0.70 to 0.89, enabling accurate prediction of post-liberalization pollutant concentrations. This study can enhance our understanding regarding the impact of sudden social lockdown relaxation events on air quality while providing support for urban air pollution prevention.

Features of extreme PM 2.5 pollution and its influencing factors: evidence from China

Extreme PM 2.5 pollution has become a significant environmental problem in China in recent years, which is hazardous to human health and daily life. Noticing the importance of investigating the causes of extreme PM 2.5 pollution, this paper classifies cities across China into eight categories (four groups plus two scenarios) based on the generalized extreme value (GEV) distribution using hourly station-level PM 2.5 concentration data, and a series of multi-choice models are employed to assess the probabilities that cities fall into different categories. Various factors such as precursor pollutants and socio-economic factors are considered after controlling for meteorological conditions in each model. It turns out that SO 2 concentration, NO 2 concentration, and population density are the top three factors contributing most to the log ratios. Moreover, in both left- and right-skewed cases, the influence of a one-unit increase of SO 2 concentration on the relative probability of cities falling into different groups shows an increasing trend, while those of NO 2 concentration show a decreasing trend. At the same time, the higher the extreme pollution level, the bigger the effect of SO 2 and NO 2 concentrations on the probability of cities falling into normalized scenarios. The multivariate logit model is used for prediction and policy simulations. In summary, by analyzing the influences of various factors and the heterogeneity of their influence patterns, this paper provides valuable insights in formulating effective emission reduction policies.

Elevating hourly PM2.5 forecasting in Istanbul, Türkiye: Leveraging ERA5 reanalysis and genetic algorithms in a comparative machine learning model analysis

Rapid urbanization and industrialization have intensified air pollution, posing severe health risks and necessitating accurate PM2.5 predictions for effective urban air quality management. This study distinguishes itself by utilizing high-resolution ERA5 reanalysis data for a grid-based spatial analysis of Istanbul, Türkiye, a densely populated city with diverse pollutant sources. It assesses the predictive accuracy of advanced machine learning (ML) models-Multiple Linear Regression (MLR), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting (LGB), Random Forest (RF), and Nonlinear Autoregressive with Exogenous Inputs (NARX). Notably, it introduces genetic algorithm optimization for the NARX model to enhance its performance. The models were trained on hourly PM2.5 concentrations from twenty monitoring stations across 2020-2021. Istanbul was divided into seven regions based on ERA5 grid distributions to examine PM2.5 spatial variability. Seventeen input variables from ERA5, including meteorological, land cover, and vegetation parameters, were analyzed using the Neighborhood Component Analysis (NCA) method to identify the most predictive variables. Comparative analysis showed that while all models provided valuable insights (RF > LGB > XGB > MLR), the NARX model outperformed them, particularly with the complex dataset used. The NARX model achieved a high R-value (0.89), low RMSE (5.24 μg/m³), and low MAE (2.94 μg/m³). It performed best in autumn and winter, with the highest accuracy in Region-1 (R-value 0.94) and the lowest in Region-5 (R-value 0.75). This study's success in a complex urban setting with limited monitoring underscores the robustness of the NARX model and the methodology's potential for global application in similar urban contexts. By addressing temporal and spatial variability in air quality predictions, this research sets a new benchmark and highlights the importance of advanced data analysis techniques for developing targeted pollution control strategies and public health policies.

Daily PM2.5 concentration prediction based on variational modal decomposition and deep learning for multi-site temporal and spatial fusion of meteorological factors

Air pollution, particularly PM2.5, has long been a critical concern for the atmospheric environment. Accurately predicting daily PM2.5 concentrations is crucial for both environmental protection and public health. This study introduces a new hybrid model within the "Decomposition-Prediction-Integration" (DPI) framework, which combines variational modal decomposition (VMD), causal convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), and attention mechanism (AM), named as VCBA, for spatio-temporal fusion of multi-site data to forecast daily PM2.5 concentrations in a city. The approach involves integrating air quality data from the target site with data from neighboring sites, applying mathematical techniques for dimensionality reduction, decomposing PM2.5 concentration data using VMD, and utilizing Causal CNN and BiLSTM models with an attention mechanism to enhance performance. The final prediction results are obtained through linear aggregation. Experimental results demonstrate that the VCBA model performs exceptionally well in predicting daily PM2.5 concentrations at various stations in Taiyuan City, Shanxi Province, China. Evaluation metrics such as RMSE, MAE, and R2 are reported as 2.556, 1.998, and 0.973, respectively. Compared to traditional methods, this approach offers higher prediction accuracy and stronger spatio-temporal modeling capabilities, providing an effective solution for accurate PM2.5 daily concentration prediction.

Predicting hospital admissions for upper respiratory tract complaints: An artificial neural network approach integrating air pollution and meteorological factors

This study uses artificial neural networks (ANNs) to examine the intricate relationship between air pollutants, meteorological factors, and respiratory disorders. The study investigates the correlation between hospital admissions for respiratory diseases and the levels of PM10 and SO2 pollutants, as well as local meteorological conditions, using data from 2017 to 2019. The objective of this study is to clarify the impact of air pollution on the well-being of the general population, specifically focusing on respiratory ailments. An ANN called a multilayer perceptron (MLP) was used. The network was trained using the Levenberg-Marquardt (LM) backpropagation algorithm. The data revealed a substantial increase in hospital admissions for upper respiratory tract diseases, amounting to a total of 11,746 cases. There were clear seasonal fluctuations, with fall having the highest number of cases of bronchitis (N = 181), sinusitis (N = 83), and upper respiratory infections (N = 194). The study also found demographic differences, with females and people aged 18 to 65 years having greater admission rates. The performance of the ANN model, measured using R2 values, demonstrated a high level of predictive accuracy. Specifically, the R2 value was 0.91675 during training, 0.99182 during testing, and 0.95287 for validating the prediction of asthma. The comparative analysis revealed that the ANN-MLP model provided the most optimal result. The results emphasize the effectiveness of ANNs in representing the complex relationships between air quality, climatic conditions, and respiratory health. The results offer crucial insights for formulating focused healthcare policies and treatments to alleviate the detrimental impact of air pollution and meteorological factors.

Understanding the Disparities of PM2.5 Air Pollution in Urban Areas via Deep Support Vector Regression

In densely populated urban areas, PM2.5 has a direct impact on the health and quality of residents' life. Thus, understanding the disparities of PM2.5 is crucial for ensuring urban sustainability and public health. Traditional prediction models often overlook the spillover effects within urban areas and the complexity of the data, leading to inaccurate spatial predictions of PM2.5. We propose Deep Support Vector Regression (DSVR) that models the urban areas as a graph, with grid center points as the nodes and the connections between grids as the edges. Nature and human activity features of each grid are initialized as the representation of each node. Based on the graph, DSVR uses random diffusion-based deep learning to quantify the spillover effects of PM2.5. It leverages random walk to uncover more extensive spillover relationships between nodes, thereby capturing both the local and nonlocal spillover effects of PM2.5. And then it engages in predictive learning using the feature vectors that encapsulate spillover effects, enhancing the understanding of PM2.5 disparities and connections across different regions. By applying our proposed model in the northern region of New York for predictive performance analysis, we found that DSVR consistently outperforms other models. During periods of PM2.5 surges, the R-square of DSVR reaches as high as 0.729, outperforming non-spillover models by 2.5 to 5.7 times and traditional spatial metric models by 2.2 to 4.6 times. Therefore, our proposed model holds significant importance for understanding disparities of PM2.5 air pollution in urban areas, taking the first steps toward a new method that considers both the spillover effects and nonlinear feature of data for prediction.

Machine learning and deep learning enabled age estimation on medial clavicle CT images

The medial clavicle epiphysis is a crucial indicator for bone age estimation (BAE) after hand maturation. This study aimed to develop machine learning (ML) and deep learning (DL) models for BAE based on medial clavicle CT images and evaluate the performance on normal and variant clavicles. This study retrospectively collected 1049 patients (mean± SD: 22.50±4.34 years) and split them into normal training and test sets, and variant training and test sets. An additional 53 variant clavicles were incorporated into the variant test set. The development stages of normal MCE were used to build a linear model and support vector machine (SVM) for BAE. The CT slices of MCE were automatically segmented and used to train DL models for automated BAE. Comparisons were performed by linear versus ML versus DL, and normal versus variant clavicles. Mean absolute error (MAE) and classification accuracy was the primary parameter of comparison. For BAE, the SVM had the best MAE of 1.73 years, followed by the commonly-used CNNs (1.77-1.93 years), the linear model (1.94 years), and the hybrid neural network CoAt Net (2.01 years). In DL models, SE Net 18 was the best-performing DL model with similar results to SVM in the normal test set and achieved an MAE of 2.08 years in the external variant test. For age classification, all the models exhibit superior performance in the classification of 18-, 20-, 21-, and 22-year thresholds with limited value in the 16-year threshold. Both ML and DL models produce desirable performance in BAE based on medial clavicle CT.

A study on identifying synergistic prevention and control regions for PM2.5 and O3 and exploring their spatiotemporal dynamic in China

Air pollutants, notably ozone (O3) and fine particulate matter (PM2.5) give rise to evident adverse impacts on public health and the ecotope, prompting extensive global apprehension. Though PM2.5 has been effectively mitigated in China, O3 has been emerging as a primary pollutant, especially in summer. Currently, alleviating PM2.5 and O3 synergistically faces huge challenges. The synergistic prevention and control (SPC) regions of PM2.5 and O3 and their spatiotemporal patterns were still unclear. To address the above issues, this study utilized ground monitoring station data, meteorological data, and auxiliary data to predict the China High-Resolution O3 Dataset (CHROD) via a two-stage model. Furthermore, SPC regions were identified based on a spatial overlay analysis using a Geographic Information System (GIS). The standard deviation ellipse was employed to investigate the spatiotemporal dynamic characteristics of SPC regions. Some outcomes were obtained. The two-stage model significantly improved the accuracy of O3 concentration prediction with acceptable R2 (0.86), and our CHROD presented higher spatiotemporal resolution compared with existing products. SPC regions exhibited significant spatiotemporal variations during the Blue Sky Protection Campaign (BSPC) in China. SPC regions were dominant in spring and autumn, and O3-controlled and PM2.5-dominated zones were detected in summer and winter, respectively. SPC regions were primarily located in the northwest, north, east, and central regions of China, specifically in the Beijing-Tianjin-Hebei urban agglomeration (BTH), Shanxi, Shaanxi, Shandong, Henan, Jiangsu, Xinjiang, and Anhui provinces. The gravity center of SPC regions was distributed in the BTH in winter, and in Xinjiang during spring, summer, and autumn. This study can supply scientific references for the collaborative management of PM2.5 and O3.

Long- and short-term health benefits attributable to PM2.5 constituents reductions from 2013 to 2021: A spatiotemporal analysis in China

Long- and short-term exposure to constituents of fine particulate matter (PM2.5) substantially affects human health. However, assessments of the health and economic benefits of reducing PM2.5 constituents are scarce. This study estimates the number of premature deaths from all-cause, cardiovascular (CVD), and respiratory diseases avoided due to reductions in daily and annual average concentrations of PM2.5 constituents. The Environmental Benefits Mapping and Analysis Program was used for two scenarios: we used yearly concentrations of PM2.5 constituents from 2013 to 2020 as the baseline concentration surface (Scenario I), and 2021 as the baseline year (Scenario II). With reductions in daily and annual average concentrations of PM2.5 constituents, 309,099 (95 % confidence interval [CI]: 37,265-571,485) and 195,297 (95 % CI: 178,192-211,914) premature deaths were avoided in Scenario I, respectively; meanwhile, 347,296 (95 % CI: 79,258-604,758) and 201,567 (95 % CI: 185,038-217,530) premature deaths were avoided in Scenario II, respectively. Moreover, economic benefits associated with the prevention of premature deaths were estimated using the willingness to pay (WTP) and modified human capital (AHC) methods. The total estimated economic benefits amounted to 563.32 billion RMB (WTP) and 322.03 billion RMB (AHC) in Scenario I. In Scenario II, the associated economic benefits were 751.48 billion RMB (WTP) and 427.56 billion RMB (AHC), accounting for 0.657 and 0.374 % of China's gross domestic product in 2021, respectively. Additionally, we analyzed the sensitivity of CVD-related premature deaths to the concentrations of PM2.5 constituents, and found that CVD-related premature deaths were more sensitive to black carbon.

Prediction of free radical reactions toward organic pollutants with easily accessible molecular descriptors

Machine learning (ML) is becoming an efficient tool for predicting the fate of aquatic contaminants owing to the preponderance of big data. However, whether ML can "learn" the differences in reactivity among different free radicals has not yet been tested. In this work, the effectiveness of combining ML algorithms with molecular fingerprints to predict the reactivity of three free radicals was evaluated. First, a dataset containing 211 organic pollutants and their respective rate constants with the carbonate radical (CO3•-) was used to develop predictive models using both linear regression and ML methods. The use of topological atomic alignment information, in the form of the molecular access system (MACCS) and Morgan Fingerprint, and the electronic structure features (energy levels of the lowest unoccupied and highest occupied molecular orbitals, ELUMO and EHOMO, and the energy gap between ELUMO and EHOMO) gave satisfactory predictive performances (ML model with Random Forest algorithm with MACCS: RMSEtest = 0.787; linear regression model with energy levels: RMSEtest = 0.641). Additionally, the model interpretation correctly described that the key reactivity features for CO3•- were relatively close to those for SO4•- rather than those for •OH. These results suggest that combination of ML algorithms with easily accessible molecular fingerprints would be a powerful tool to accurately predict the radical reactions towards organic compounds.

The application of strategy based on LSTM for the short-term prediction of PM2.5 in city

Many cities have long suffered from the events of fine particulate matter (PM2.5) pollutions. The Taiwanese Government has long strived to accurately predict the short-term hourly concentration of PM2.5 for the warnings on air pollution. Long Short-Term Memory neural network (LSTM) based on deep learning improves the prediction accuracy of daily PM2.5 concentration but PM2.5 prediction for next hours still needs to be improved. Therefore, this study proposes innovative Application-Strategy-based LSTM (ASLSTM) to accurately predict the short-term hourly PM2.5 concentrations, especially for the high PM2.5 predictions. First, this study identified better spatiotemporal input feature of a LSTM for obtaining this Better LSTM (BLSTM). In doing so, BLSTM trained by appropriate datasets could accurately predict the next hourly pollution concentration. Next, the application strategy was applied on BLSTM to construct ASLSTM. Specifically, from a timeline perspective, ASLSTM concatenates several BLSTMs to predict the concentration of PM2.5 at the following next several hours during which the predicted outputs of BLSTM at this time t was selected and included as the inputs of the next BLSTM at the next time t + 1, and the oldest input used as BLSTM at the time t was removed. The result demonstrated that BLSTM were trained by the dataset collected from 2008 to 2010 at Dali measurement station because there is a relatively large amount of data on high PM2.5 concentration in this dataset. Besides, a comparison of the performance of the ASLSTM with that of the LSTM was made to validate this proposed ASLSTM, especially for the range of higher PM2.5 concentration that people concerned. More importantly, the feasibility of this proposed application strategy and the necessity of optimizing the input parameters of LSTM were validated. In summary, this ASLSTM could accurately predict the short-term PM2.5 in Taichung city.

Spatio-temporal fusion of meteorological factors for multi-site PM2.5 prediction: A deep learning and time-variant graph approach

In the field of environmental science, traditional methods for predicting PM2.5 concentrations primarily focus on singular temporal or spatial dimensions. This approach presents certain limitations when it comes to deeply mining the joint influence of multiple monitoring sites and their inherent connections with meteorological factors. To address this issue, we introduce an innovative deep-learning-based multi-graph model using Beijing as the study case. This model consists of two key modules: firstly, the 'Meteorological Factor Spatio-Temporal Feature Extraction Module'. This module deeply integrates spatio-temporal features of hourly meteorological data by employing Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) for spatial and temporal encoding respectively. Subsequently, through an attention mechanism, it retrieves a feature tensor associated with air pollutants. Secondly, these features are amalgamated with PM2.5 concentration values, allowing the 'PM2.5 Concentration Prediction Module' to predict with enhanced accuracy the joint influence across multiple monitoring sites. Our model exhibits significant advantages over traditional methods in processing the joint impact of multiple sites and their associated meteorological factors. By providing new perspectives and tools for the in-depth understanding of urban air pollutant distribution and optimization of air quality management, this model propels us towards a more comprehensive approach in tackling air pollution issues.

Comparative analysis of the capability of the extended biotic ligand model and machine learning approaches to predict arsenate toxicity

Assessment of inorganic arsenate (As(V)) is critical for ensuring a sustainable environment because of its adverse effects on humans and ecosystems. This study is the first to attempt to predict As(V) toxicity to the bioluminescent bacterium Aliivibrio fischeri exposed to varying As(V) dosages and environmental factors (pH and phosphate concentration) using six machine learning (ML)-guided models. The predicted toxicity values were compared with those predicted using the extended biotic ligand model (BLM) we previously developed to evaluate the toxic effect of oxyanion (i.e., As(V)). The relationship between the variables (input features) and toxicity (output) was found to play an important role in the prediction accuracy of each ML-guided model. The results indicated that the extended BLM had the highest prediction accuracy, with a root mean square error (RMSE) of 12.997. However, with an RMSE of 14.361, the multilayer perceptron (MLP) model exhibited quasi-accurate prediction, despite having been trained with a relatively small dataset (n = 256). In view of simplicity, an MLP model is compatible with an extended BLM and does not require expert knowledge for the derivation of specific parameters, such as binding fraction and binding constant values. Furthermore, with the development and employment of reliable in-situ sensing techniques, monitoring data are expected to be augmented faster to provide sufficient training data for the improvement of prediction accuracy which may, thus, allow it to outperform the extended BLM after obtaining sufficient data.

Improving PM2.5 prediction in New Delhi using a hybrid extreme learning machine coupled with snake optimization algorithm

Fine particulate matter (PM2.5) is a significant air pollutant that drives the most chronic health problems and premature mortality in big metropolitans such as Delhi. In such a context, accurate prediction of PM2.5 concentration is critical for raising public awareness, allowing sensitive populations to plan ahead, and providing governments with information for public health alerts. This study applies a novel hybridization of extreme learning machine (ELM) with a snake optimization algorithm called the ELM-SO model to forecast PM2.5 concentrations. The model has been developed on air quality inputs and meteorological parameters. Furthermore, the ELM-SO hybrid model is compared with individual machine learning models, such as Support Vector Regression (SVR), Random Forest (RF), Extreme Learning Machines (ELM), Gradient Boosting Regressor (GBR), XGBoost, and a deep learning model known as Long Short-Term Memory networks (LSTM), in forecasting PM2.5 concentrations. The study results suggested that ELM-SO exhibited the highest level of predictive performance among the five models, with a testing value of squared correlation coefficient (R2) of 0.928, and root mean square error of 30.325 µg/m3. The study's findings suggest that the ELM-SO technique is a valuable tool for accurately forecasting PM2.5 concentrations and could help advance the field of air quality forecasting. By developing state-of-the-art air pollution prediction models that incorporate ELM-SO, it may be possible to understand better and anticipate the effects of air pollution on human health and the environment.

Machine learning algorithms for high-resolution prediction of spatiotemporal distribution of air pollution from meteorological and soil parameters

This study uses machine learning (ML) models for a high-resolution prediction (0.1°×0.1°) of air fine particular matter (PM_2.5) concentration, the most harmful to human health, from meteorological and soil data. Iraq was considered the study area to implement the method. Different lags and the changing patterns of four European Reanalysis (ERA5) meteorological variables, rainfall, mean temperature, wind speed and relative humidity, and one soil parameter, the soil moisture, were used to select the suitable set of predictors using a non-greedy algorithm known as simulated annealing (SA). The selected predictors were used to simulate the temporal and spatial variability of air PM_2.5 concentration over Iraq during the early summer (May-July), the most polluted months, using three advanced ML models, extremely randomized trees (ERT), stochastic gradient descent backpropagation (SGD-BP) and long short-term memory (LSTM) integrated with Bayesian optimizer. The spatial distribution of the annual average PM_2.5 revealed the population of the whole of Iraq is exposed to a pollution level above the standard limit. The changes in temperature and soil moisture and the mean wind speed and humidity of the month before the early summer can predict the temporal and spatial variability of PM_2.5 over Iraq during May-July. Results revealed the higher performance of LSTM with normalized root-mean-square error and Kling-Gupta efficiency of 13.4% and 0.89, compared to 16.02% and 0.81 for SDG-BP and 17.9% and 0.74 for ERT. The LSTM could also reconstruct the observed spatial distribution of PM_2.5 with MapCurve and Cramer's V values of 0.95 and 0.91, compared to 0.9 and 0.86 for SGD-BP and 0.83 and 0.76 for ERT. The study provided a methodology for forecasting spatial variability of PM_2.5 concentration at high resolution during the peak pollution months from freely available data, which can be replicated in other regions for generating high-resolution PM_2.5 forecasting maps.