Performance Of PM2 Research Articles

Appraising machine learning algorithms in predicting noise level and emissions from gasoline-powered household backup generators

AbstractMachine learning is presently receiving great attention. However, machine learning applications to gasoline engine research are limited. This paper investigated the implementation of various machine learning models in predicting the emissions (CO2, CO, and PM2.5) and noise levels of gasoline-powered household generators for the first time. Data of operating and installed capacity, efficiency (input) and emissions, and noise level (output) obtained from 166 generators were used in extreme gradient boosting, artificial neural network (ANN), decision tree (DT), random forest (RF), and polynomial regression (PNR) algorithms to develop predictive models. Results revealed high prediction performance (R2 = 0.9377–1.0000) of these algorithms marked with very low errors. The implementation of PNR followed by the RF exhibited the best models for predicting CO2, CO, PM2.5, and the noise level of generators. R2 of 1.000 and 0.9979–0.9994, mean squared error of < 10−6 and 2 × 10−5–8.6 × 10−5, mean absolute percentage error of 9.15 × 10−16–1.3 × 10−15 and 7.1 × 10−3–8.1 × 10−2, and root mean squared error of 3.3 × 10−16–5.4 × 10−16 and 4.4 × 10−3–9.3 × 10−2 were recorded for all the output parameters using PNR and RF respectively. DT models had the least prediction capacity for CO, CO2, and noise levels (R2 = 0.9493–0.9592) while ANN produced the least performance for PM2.5 (R2 = 0.9377). This study further strengthens machine learning applications in engine research for the prediction of various output parameters.

Long-term prediction method for PM2.5 concentration using edge channel graph attention network and gating closed-form continuous-time neural networks

Fine particulate matter such as PM2.5 threatens significantly to the environment and human health, so it is essential to design a reliable long-term prediction method for PM2.5 concentrations. Existing long-term PM2.5 prediction models inadequately utilize urban spatial features, fail to consider the role of meteorological factors in PM2.5 levels, and overlook the interaction between PM2.5 concentrations in different cities. To tackle this issue, we propose two new models and integrate them. Firstly, we develop a spatial feature model (ECGAT) for extracting PM2.5 concentration among regions based on Graph Neural Networks (GNN), edge-channel mechanisms, and Graph Attention Convolution (GATConv). This model utilizes GNN to extract urban adjacency relationships and meteorological features, employs edge-channel mechanisms to recalculate weights for interactions between cities, and outputs spatial correlations through GATConv. Secondly, we propose Gating Closed-form Continuous-time Neural Networks (GCFC) as a temporal model to extract the PM2.5 concentration's temporal features. The fusion of these two models, named ECGAT-GCFC (EGCFC), enhances the model's capability to capture spatiotemporal features and improves performance in PM2.5 long-term predictions. Results from real-world data analysis show that the proposed algorithm outperforms state-of-the-art existing prediction models in predicting PM2.5 levels over long durations. Compared to baseline models, EGCFC reduces RMSE by an average of 3.39 %, decreases MAE by 4.83 %, increases R2 by 4.89 %, CSI by 3.13 %, and lowers FAR by 11.39 %. These indicate that EGCFC is an effective method for predicting trends in urban PM2.5 concentrations.

Estimation of PM2.5 and PM10 Mass Concentrations in Beijing Using Gaofen-1 Data at 100 m Resolution

Due to the advantage of high spatial coverage, using satellite-retrieved aerosol optical depth (AOD) data to estimate PM2.5 and PM10 mass concentrations is a current research priority. Statistical models are the common method of PM estimation currently, which do not require the knowledge of complex chemical and physical interactions. However, the statistical models rely on station data, which results in less accurate PM estimation concentrations in areas where station data are missing. Hence, a new hybrid model, with low dependency on on-site data, was proposed for PM2.5 and PM10 mass concentration estimation. The Gaofen-1 satellite and MODIS data were employed to estimate PM2.5 and PM10 concentrations with 100 m spatial resolution in Beijing, China. Then, the estimated PM2.5/10 mass concentration data in 2020 were employed to conduct a spatio-temporal analysis for the investigation of the particulate matter characteristic in Beijing. The estimation result of PM2.5 was validated by the ground stations with R2 ranging from 0.91 to 0.98 and the root mean square error (RMSE) ranging from 4.51 μg/m3 to 17.04 μg/m3, and that for PM10 was validated by the ground stations with R2 ranging from 0.85 to 0.98 and the RMSE ranging from 6.98 µg/m3 to 29.00 µg/m3. The results showed that the hybrid model has a good performance in PM2.5/10 estimation and can improve the coverage of the results without sacrificing the effectiveness of the model, providing more detailed spatial information for urban-scale studies.

Real-time AIoT platform for monitoring and prediction of air quality in Southwestern Morocco.

Urbanization and industrialization have led to a significant increase in air pollution, posing a severe environmental and public health threat. Accurate forecasting of air quality is crucial for policymakers to implement effective interventions. This study presents a novel AIoT platform specifically designed for PM2.5 monitoring in Southwestern Morocco. The platform utilizes low-cost sensors to collect air quality data, transmitted via WiFi/3G for analysis and prediction on a central server. We focused on identifying optimal features for PM2.5 prediction using Minimum Redundancy Maximum Relevance (mRMR) and LightGBM Recursive Feature Elimination (LightGBM-RFE) techniques. Furthermore, Bayesian optimization was employed to fine-tune hyperparameters of popular machine learning models for the most accurate PM2.5 concentration forecasts. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R2). Our results demonstrate that the LightGBM model achieved superior performance in PM2.5 prediction, with a significant reduction in RMSE compared to other evaluated models. This study highlights the potential of AIoT platforms coupled with advanced feature selection and hyperparameter optimization for effective air quality monitoring and forecasting.

Multi-source variational mode transfer learning for enhanced PM2.5 concentration forecasting at data-limited monitoring stations

Hybrid methods combining data decomposition with deep learning have recently exhibited remarkable performance in PM2.5 concentration forecasting. However, these methods still encounter limitations when confronted with monitoring sites lacking adequate historical data. To overcome this challenge, this study proposes a novel methodological framework named as Multi-source Variational Mode Transfer Learning (MSVMTL) that integrates data decomposition, deep learning, and multi-source transfer learning strategies. The framework consists of four stages: source domain selection, data decomposition by Variational Mode Decomposition (VMD), mode sequence clustering, and multi-source mode transfer learning. The source domain selection stage utilizes EMS (Euclidean Distance and Maximum Mean Discrepancy Distance) to identify the most suitable source domain for knowledge transfer. The mode sequence clustering employs the LDDK algorithm (Largest Triangle Three Buckets, Dynamic Time Warping, Dynamic Time Warping Barycenter Averaging, and K-means) to cluster modes from VMD-derived domains. The multi-source mode transfer stage combines VMD with pre-training and fine-tuning, leveraging source domain knowledge for target domain prediction. To validate the proposed framework, a case study, including multiple sets of comparative experiments and ablation study, was conducted using data from 12 air quality monitoring sites in Beijing, China. The experimental results demonstrate that EMS, LDDK, and multi-source mode transfer learning strategy all achieved excellent performance, and the presented MSVMTL significantly enhances the prediction accuracy of PM2.5 concentrations at monitoring sites with limited historical data.

Importance of meteorological conditions to the prediction of surface PM2.5 using satellite-based observations in Sichuan basin, southwest China

Air pollutants are of great global concern due to their effects on peoples health. Consequently, timely predictions of surface PM2.5/PM10 can help implement preventive interventions. Machine learning algorithms are commonly used to predict or retrieve PM2.5/PM10 concentrations based on satellite-derived observations. But these algorithms often ignore the interpretability of PM2.5/PM10 predictions and generally improve their performance by adding meteorological conditions derived from numerical weather predictions (NWP) reanalysis data. This paper explores the predictive ability of different meteorological conditions, such as wind speed, wind direction, temperature, and humidity derived from NWP data at different pressure levels, and their ability to improve the PM2.5 retrieval accuracy of a random forest model in comparison with using only satellite data. Adding meteorological conditions to satellite data raised the coefficient of determination (R2) from 0.533 to 0.722 (with data at 500hPa) and 0.752 (with data at both 500hPa and 975hPa), indicating that meteorological conditions could improve PM2.5 model predictions compared with experiments using only satellite observations. In the experiment where meteorological conditions were added to satellite observations, performance of PM2.5 retrieval improved. Other experiments have shown that the performance is better when meteorological conditions are used alone compared with the case when satellite observations are used alone. In addition, feature importance of these experiments has revealed that meteorological parameters are relatively higher, and there lies a gap between satellite observations and meteorological parameters. In the experiment using both satellite observations and meteorological data, the feature with the highest importance is the temperature (0.12 for those at 975hPa and 0.12 for those at 500hPa), while those of satellite observations are less than 0.04. And the R^(2 ) using only the meteorological condition (both 500hPa and 975hPa) decreased only by 0.012 compared with the experiment using all data, while RMSE and MAE increased by 0.34, 0.207, respectively. The last experiment reduced input features to 9 parameters based on feature importance, but its R2 decreased by only 0.026. It seems evident that meteorological conditions (such as temperature, humidity and wind) are crucial to surface PM2.5 retrieval, even when satellite observations are available in RF based PM2.5 retrieval.

Prediction of PM2.5 time series by seasonal trend decomposition-based dendritic neuron model.

The rapid industrial development in the human society has brought about the air pollution, which seriously affects human health. PM2.5 concentration is one of the main factors causing the air pollution. To accurately predict PM2.5 microns, we propose a dendritic neuron model (DNM) trained by an improved state-of-matter heuristic algorithm (DSMS) based on STL-LOESS, namely DS-DNM. Firstly, DS-DNM adopts STL-LOESS for the data preprocessing to obtain three characteristic quantities from original data: seasonal, trend, and residual components. Then, DNM trained by DSMS predicts the residual values. Finally, three sets of feature quantities are summed to obtain the predicted values. In the performance test experiments, five real-world PM2.5 concentration data are used to test DS-DNM. On the other hand, four training algorithms and seven prediction models were selected for comparison to verify the rationality of the training algorithms and the accuracy of the prediction models, respectively. The experimental results show that DS-DNM has the more competitive performance in PM2.5 concentration prediction problem.

The Ground-Level Particulate Matter Concentration Estimation Based on the New Generation of FengYun Geostationary Meteorological Satellite

The new-generation FengYun geostationary meteorological satellite has a high spatial and temporal resolution, which is advantageous in environmental assessments and air pollution monitoring. This study researched the ground-level particulate matter concentration estimation, based on satellite-observed radiations. The radiation of ground-level particulate matter is separate from the apparent radiation observed by satellites. The positive correlation between PM2.5 and PM10 is also considered to improve the accuracy of inversion results and the interpretability of the estimation model. Then, PM2.5 and PM10 concentrations were estimated synchronously every 5 min in mainland China based on FY-4A satellite directly observed radiations. The validation results showed that the improved model estimated results were close to the ground site measured results, with a high determination coefficient (R2) (0.89 for PM2.5, and 0.90 for PM10), and a small Root Mean Squared Error (RMSE) (4.69 μg/m3 for PM2.5 concentrations, and 13.77 μg/m3 for PM10 concentrations). The estimation model presented a good performance in PM2.5 and PM10 concentrations during typical haze and dust storm cases, indicating that it is applicable in different weather conditions and regions.

Quantification of SO2 Emission Variations and the Corresponding Prediction Improvements Made by Assimilating Ground-Based Observations

In this research, a new time-resolved emission inversion system was developed to investigate variations in SO2 emission in China during the COVID-19 (Corona Virus Disease 2019) lockdown period based on a four-dimensional variational (4DVar) inversion method to dynamically optimize the SO2 inventory by assimilating the ground-based hourly observation data. The inversion results obtained were validated in the North China Plain (NCP). Two sets of experiments were carried out based on the original and optimized inventories during the pre-lockdown and lockdown period to quantify the SO2 emission variations and the corresponding prediction improvement. The SO2 emission changes due to the lockdown in the NCP were quantified by the differences in the averaged optimized inventories between the pre-lockdown and lockdown period. As a response to the lockdown control, the SO2 emissions were reduced by 20.1% on average in the NCP, with ratios of 20.7% in Beijing, 20.2% in Tianjin, 26.1% in Hebei, 18.3% in Shanxi, 19.1% in Shandong, and 25.9% in Henan, respectively. These were mainly attributed to the changes caused by the heavy industry lockdown in these areas. Compared to the model performance based on the original inventory, the optimized daily SO2 emission inventory significantly improved the model SO2 predictions during the lockdown period, with the correlation coefficient (R) value increasing from 0.28 to 0.79 and the root-mean-square error (RMSE) being reduced by more than 30%. Correspondingly, the performance of PM2.5 was slightly improved, with R-value increasing from 0.67 to 0.74 and the RMSE being reduced by 8% in the meantime. These statistics indicate the good optimization ability of the time-resolved emission inversion system.

Source Analysis of Ambient PM2.5 in Wuhan City Based on Random Forest Model

Based on the online monitoring data of fine particle(PM2.5) mass concentration, carbonaceous components, ionic constituents, and elemental components in an urban site of Wuhan from December 2019 to November 2020, the chemical characteristics of PM2.5 were analyzed. In addition, seasonal source apportionment of PM2.5 was conducted using the principal component analysis(PCA) method and random forest(RF) algorithm model. The results indicated that ρ(PM2.5) was the highest in winter[(61.33±35.32) μg·m-3] and the lowest in summer[(17.87±10.06) μg·m-3]. Furthermore, organic carbon(OC), with a concentration of(7.27±3.51) μg·m-3, accounted for the major proportion compared with that of elemental carbon(EC) in the carbonaceous component of PM2.5. NO3-, SO42-, and NH4+ had the highest proportion in ionic components, with concentrations of (11.55±3.86),(7.55±1.53), and (7.34±1.99) μg·m-3, respectively. K, Fe, and Ca were the main elements in elemental components, with concentrations of (752.80±183.98),(542.34±142.55), and (459.70±141.99) ng·m-3, respectively. Relying on main factor extraction by PCA and quantitative analysis by RF, five emission sources were ultimately confirmed. The seasonal concentration distribution of these emission sources was as follows:coal burning and secondary sources(46%, 39%, 41%, and 52% for spring, summer, autumn, and winter, respectively) made the highest contribution to PM2.5, followed by vehicle emission sources(22%, 28%, 27%, and 21%), industrial emission sources (14%, 18%, 17%, and 13%), dust sources (10%, 8%, 6%, and 6%), and biomass burning sources (8%, 7%, 9%, and 8%). The valuation of the RF model was evaluated using multiple indicators, including RMSE, MSE, and R2. The evaluation results showed that the model for winter had the best performance (R2=0.974, RMSE=3.795 μg·m-3, MAE=2.801 μg·m-3), the models for spring (R2=0.936, RMSE=3.512 μg·m-3, MAE=2.503 μg·m-3) and autumn (R2=0.937, RMSE=4.114 μg·m-3, MAE=3.034 μg·m-3) performed with moderate-fitting goodness, and the summer model showed a relatively weak-fitting performance (R2=0.866, RMSE=5.665 μg·m-3, MAE=3.889 μg·m-3). The RF model had a satisfactory performance in PM2.5 source apportionment and had excellent prospects in analyzing massive historical data of air pollutants.

Deep Ensemble Machine Learning Framework for the Estimation of Concentrations.

Background:Accurate estimation of historical (particle matter with an aerodynamic diameter of less than ) is critical and essential for environmental health risk assessment.Objectives:The aim of this study was to develop a multiple-level stacked ensemble machine learning framework for improving the estimation of the daily ground-level concentrations.Methods:An innovative deep ensemble machine learning framework (DEML) was developed to estimate the daily concentrations. The framework has a three-stage structure: At the first stage, four base models [gradient boosting machine (GBM), support vector machine (SVM), random forest (RF), and eXtreme gradient boosting (XGBoost)] were used to generate a new data set of concentrations for training the next-stage learners. At the second stage, three meta-models [RF, XGBoost, and Generalized Linear Model (GLM)] were used to estimate concentrations using a combination of the original data set and the predictions from the first-stage models. At the third stage, a nonnegative least squares (NNLS) algorithm was employed to obtain the optimal weights for estimation. We took the data from 133 monitoring stations in Italy as an example to implement the DEML to predict daily at each grid cell from 2015 to 2019 across Italy. We evaluated the model performance by performing 10-fold cross-validation (CV) and compared it with five benchmark algorithms [GBM, SVM, RF, XGBoost, and Super Learner (SL)].Results:The results revealed that the prediction performance of DEML [coefficients of determination and root mean square error ] was superior to any benchmark models (with of 0.51, 0.76, 0.83, 0.70, and 0.83 for GBM, SVM, RF, XGBoost, and SL approach, respectively). DEML displayed reliable performance in capturing the spatiotemporal variations of in Italy.Discussion: The proposed DEML framework achieved an outstanding performance in estimation, which could be used as a tool for more accurate environmental exposure assessment. https://doi.org/10.1289/EHP9752

Air Pollution Prediction Via Graph Attention Network and Gated Recurrent Unit

PM2.5 concentration prediction is of great significance to environmental protection and human health. Achieving accurate prediction of PM2.5 concentration has become an important research task. However, PM2.5 pollutants can spread in the earth’s atmosphere, causing mutual influence between different cities. To effectively capture the air pollution relationship between cities, this paper proposes a novel spatiotemporal model combining graph attention neural network (GAT) and gated recurrent unit (GRU), named GAT-GRU for PM2.5 concentration prediction. Specifically, GAT is used to learn the spatial dependence of PM2.5 concentration data in different cities, and GRU is to extract the temporal dependence of the long-term data series. The proposed model integrates the learned spatio-temporal dependencies to capture long-term complex spatio-temporal features. Considering that air pollution is related to the meteorological conditions of the city, the knowledge acquired from meteorological data is used in the model to enhance PM2.5 prediction performance. The input of the GAT-GRU model consists of PM2.5 concentration data and meteorological data. In order to verify the effectiveness of the proposed GAT-GRU prediction model, this paper designs experiments on real-world datasets compared with other baselines. Experimental results prove that our model achieves excellent performance in PM2.5 concentration prediction.

Heterogeneous spatiotemporal copula‐based kriging for air pollution prediction

AbstractAir pollutants have a significant negative impact on human health, especially cardiovascular and respiratory. An efficient and effective spatiotemporal model for air pollution prediction is urgently needed to help strengthen air pollution control and improve air quality. Empirical statistical models have been widely applied for spatiotemporal prediction. However, they are not capable of dealing well with space‐time heterogeneity and dependency, thereby achieving lower accuracy. Here, a hybrid frame named heterogeneous spatiotemporal copula‐based kriging is proposed for fine particulate matter (PM2.5) concentration prediction; it is a multi‐time, multi‐site kriging model based on spatiotemporal clustering. The proposed model is capable of addressing spatiotemporal heterogeneity effectively and accounting for the spatiotemporal dependence by copula‐based covariance functions. To evaluate the effectiveness of the proposed approach, an experiment on daily PM2.5 data in China in 2016 was carried out. The results (MAE = 6.48, RMSE = 10.68, = 0.919) show that the proposed model can achieve good performance in PM2.5 prediction, which is of great significance in regional air quality management.

Regional modeling of secondary organic aerosol formation over eastern China: The impact of uptake coefficients of dicarbonyls and semivolatile process of primary organic aerosol

Capturing the secondary organic aerosol (SOA) concentration using the chemical transport model is difficult due to a large knowledge gap of its formation mechanism. Previous studies demonstrated the uptake of dicarbonyls and semivolatile process of primary organic aerosol (POA) emissions are the significant sources of SOA. However, the uptake coefficients of dicarbonyls have large uncertainties and the SOA from the semivolatile process of POA emission remains unclear. We applied the revised reactive uptake parameterization, with “salting effects” for dicarbonyls, and updated approaches for POA to the Community Multiscale Air Quality Modeling System (CMAQ) simulations for October 2014 to study their impacts on modeling the SOA formation over eastern China. We introduce a method of quantifying crystalized or deliquescent aerosols to further improve the parameterization. The revised glyoxal uptake coefficients results in higher glyoxal SOA in the Beijing-Tianjin-Hebei region, where is typically under low relative humidity (RH) and high aerosol pH conditions. It gives lower glyoxal SOA in the Pearl River Delta region, where is typically under high RH and low pH conditions. The updated parameterization gives negligible methylglyoxal SOA due to the low uptake coefficients. The implementation of semivolatile process of POA and the approach for potential SOA from combustion sources will largely decrease the predicted POA and increase the modeled SOA concentrations over eastern China. The increased SOA from POA emissions could improve the model performance for organic carbon and SOA. It slightly improves the performance in PM2.5 modeling by compensating the reduction of modeled POA. This study indicates the mixed impact of a parameterization considering “salting effects” on modeling the dicarbonyls SOA in key regions of eastern China. It also demonstrates the improved performance by implementing the POA approaches in aerosol modeling using CMAQ. Meanwhile, the uncertainty in the revised reactive uptake parameterization and POA approaches is discussed.

A Novel Recursive Model Based on a Convolutional Long Short-Term Memory Neural Network for Air Pollution Prediction

Deep learning provides a promising approach for air pollution prediction. The existing deep learning-based predicted models generally consider either the temporal correlations of air quality monitoring stations or the nonlinear relationship between the PM2.5 (particulate matter with an aerodynamic diameter of less than 2.5 μm) concentrations and explanatory variables. Spatial correlation has not been effectively incorporated into prediction models, therefore exhibiting poor performance in PM2.5 prediction tasks. Additionally, determining the manner by which to expand longer-term prediction tasks is still challenging. In this paper, to allow for spatiotemporal correlations, a spatiotemporal convolutional recursive long short-term memory (CR-LSTM) neural network model is proposed for predicting the PM2.5 concentrations in long-term prediction tasks by combining a convolutional long short-term memory (ConvLSTM) neural network and a recursive strategy. Herein, the ConvLSTM network was used to capture the complex spatiotemporal correlations and to predict the future PM2.5 concentrations; the recursive strategy was used for expanding the long-term prediction tasks. The CR-LSTM model was used to realize the prediction of the future 24 h of PM2.5 concentrations for 12 air quality monitoring stations in Beijing by configuring both the appropriate time lag derived from the temporal correlations and the spatial neighborhood, including the hourly historical PM2.5 concentrations, the daily mean meteorological data, and the annual nighttime light and normalized difference vegetation index (NDVI). The results showed that the proposed CR-LSTM model achieved better performance (coefficient of determination (R2) = 0.74; root mean square error (RMSE) = 18.96 μg/m3) than other common models, such as multiple linear regression (MLR), support vector regression (SVR), the conventional LSTM model, the LSTM extended (LSTME) model, and the temporal sliding LSTM extended (TS-LSTME) model. The proposed CR-LSTM model, implementing a combination of geographical rules, recursive strategy, and deep learning, shows improved performance in longer-term prediction tasks.

Numerical study of the effects of initial conditions and emissions on PM<sub>2.5</sub> concentration simulations with CAMx v6.1: a Xi'an case study

Abstract. A series of model sensitivity experiments was designed to explore the effects of different initial conditions and emissions in Xi'an in December 2016; Xi'an is a major city in the Fenwei Plain, which is a key area with respect to air pollution control in China. Three methods were applied for the initial condition tests: a clean initial simulation, a restart simulation, and a continuous simulation. In the clean initial simulation test, the C00, C06, C12, C18, and C24 sensitivity experiments were conducted to explore the effect of the intercepted time periods used. The results of these experiments showed that the fine particulate matter (PM2.5) model performance was better when the start time of the intercepted time periods was delayed. For experiments C00 to C24, the absolute mean bias (MB) decreased from 51.07 to 3.72 µg m−3, and the index of agreement (IOA) increased from 0.49 to 0.86, which illustrates that the model performance of C24 is much better than that of C00. The R1120 and R1124 sensitivity experiments were used to explore the restart simulation and, in turn, the effect of the date of the first day of the model simulation. While the start times of the simulations were different, the simulation results with different start times were nearly consistent after a spin-up time period, and the results revealed that the spin-up time was approximately 27 h. For the continuous simulation test, the CT12 and CT24 sensitivity experiments were conducted. The start times of the intercepted time periods for CT12 and R1120 were the same, and the simulation results were almost identical. Based on the simulation results, CT24 showed the best performance of all of the sensitivity experiments, with the correlation coefficient (R), MB, and IOA reaching 0.81, 6.29 µg m−3, and 0.90 respectively. For the emission tests, an updated local emission inventory with construction fugitive dust emissions was added and was compared with the simulation results from the original emission inventory. The simulation with the updated local emissions showed much better performance for PM2.5 modelling. Therefore, combining the CT24 method and the updated local emission inventory can satisfactorily improve the PM2.5 model performance in Xi'an: the absolute MB decreased from 35.16 to 6.29 µg m−3, and the IOA reached 0.90.

Numerical calculation and analysis of filtration performance of an effective novel structural fiber for PM2.5.

In this study, a novel fiber with slit-crescent-shaped cross-section is proposed to enhance the filtration performance of PM2.5 in fibrous filtration. The collection efficiency of this fiber is simulated by using a Brownian dynamics simulation technique, and its filtration pressure drop is obtained by numerically solving Navier-Stokes equation with Fluent software. A parametric study is performed to improve the optimum filtration performance of the slit-crescent-shaped fiber via adjusting its structural parameters (dimensionless center-to-center spacing and slit width). Results indicate that at the optimal condition, i.e., when dimensionless slit width ranges from 0.2 to 0.4, collection efficiency is enhanced by 13.1%–101.1% relative to the circular fiber for particles ranging from 0.1μm to 2.5μm for the slit-crescent-shaped fiber under various dimensionless center-to-center spacing, and filtration pressure drop is reduced by up to 14.4%. In addition, quality factor is introduced to evaluate the comprehensive filtration performance of the slit-crescent-shaped fiber with different structural parameters, and results show that large dimensionless slit width and small dimensionless center-to-center spacing lead to a much higher quality factor than the circular fiber, especially for particles lager than 0.5μm. The numerical results obtained in this work are conducive to designing high efficiency fibrous filters.

Robust polyimide nano/microfibre aerogels welded by solvent-vapour for environmental applications.

Due to the high porosity, resilience and ultra-low density, polymer nanofibre-derived aerogels (NFAs) have been widely investigated in recent years. However, welding of the fibrous networks of NFAs, which has been proved extremely essential to their structural performance, still remains a major challenge. Herein, electrospun polyimide (PI) nano/microfibres were used as building blocks to construct hierarchically porous aerogels through a solid-templating technique. By further welding the adjacent nano/microfibres at their cross-points in a controllable fashion by solvent-vapour, super elasticity was achieved for the aerogels, with a recoverable ultimate strain of 80%. It is noteworthy that this process is free from cross-linking, heating and significant structure changing (i.e. chemical structure, crystallinity and fibrous network). Additionally, the porous structure of PI nano/microfibre aerogels (PI-N/MFAs) could be tuned by adjusting the organization of microfibres from a disordered/ordered cellular to a uniform structure. The as-obtained aerogels showed ultra-low density (4.81 mg cm−3), high porosity (99.66%), and comparable or higher recoverable compressive strain and stress relative to the other nanofibre-based aerogels. Furthermore, we showed the potential of such an aerogel for particle or aerosol filtration. PI nanofibre aerogels composite filters (PI-NFACFs) manifested excellent performance in PM2.0 filtration (99.6% filtration efficiency with 115 Pa pressure drop). Therefore, this study brought a new perspective on the simple preparation of nanofibre-based aerogels for air filtration.

Air PM2.5 concentration multi-step forecasting using a new hybrid modeling method: Comparing cases for four cities in China

Exposure to particulate matter (PM2.5) with high concentrations can increase the risk of human illness and mortality. Consequently, it is meaningful to build an accurate model for PM2.5 forecasting and provide reference for air pollution management and short-term warning. This paper develops a novel hybrid model called WPD-PSO-BP-Adaboost, based on WPD (Wavelet Packet Decomposition), the PSO (Particle Swarm Optimization) algorithm, BPNN (Back Propagation Neural Network) and Adaboost algorithm. In the proposed structure, to obtain better performance of PM2.5 forecasting, the novel hybrid model can be describe as: the WPD is utilized to decompose the raw PM2.5 data into several sub-layers with low frequency and high frequency; optimized by PSO and Adaboost algorithm, the BPNN is employed to compete the three-step prediction for every single subseries. To investigate the three-step forecasting performance of the proposed models, there are three experiments involving eleven models for the comparisons, including the BP model, BP-Adaboost model, WPD-BP model, PSO-BP model, WPD-BP-Adaboost model, WPD-PSO-BP model, PSO-BP-Adaboost model, WPD-PSO -BP-Adaboost model, EEMD-GRNN model, CEEMDAN-ICA-ELM model and WPD-CEEMD-PSOGSA -SVM model. The experiments results show that: (1) the WPD is useful in improving the forecasting performance; (2) the PSO and Adaboost algorithm can enhance the precision of forecasting significantly; (3) in all models, the WPD-PSO-BP-Adaboost model performs best in multi-step forecasting.

To what extent can the below-cloud washout effect influence the PM2.5? A combined observational and modeling study

The below-cloud washout (BCW) effect on PM2.5 concentration during periods of rain is still a subject of debate. Existing BCW schemes for PM2.5 have large deficiencies that influence its simulation in 3D chemical transport models (CTMs). In this study, a 7-year dataset with high temporal resolution (in minutes) sampled from a pristine rural site is used to calculate the BCW coefficient during the rain events. The data used for the BCW coefficient calculation cover a wide range of rain intensity from 2 mm h-1 to 60 mm h-1. The BCW coefficient linearly correlates with the rain intensity, with a correlation coefficient of 0.82. The coefficient has a magnitude of 10-5 to 10-4 s-1 when the rain intensity ranges from 1 to 40 mm h-1. After implementing the updated BCW scheme into the Comprehensive Air Quality Model with Extensions (CAMx) model, the performance of PM2.5 simulation improves for the two months of heavy rain. Apart from the CAMx model, our scheme can be easily implemented into other 3D CTMs to improve PM2.5 simulation during rainy days. The BCW effect can clean around 10-40% of the PM2.5 over our study region, which can help to reduce the PM2.5 exposure level for residents, and the health burdens caused by this pollutant can thus be reduced. Rainmaking is a potential way to decrease PM2.5 concentration, but it cannot be the key method to reduce the PM2.5 level to the standard during episodic cases (e.g., >200 μg/m3).