PM2.5 concentration prediction based on temporal convolutional network

Abstract. The present work proposes a prediction model of significant wave height (SWH) and average wave period (APD) based on variational mode decomposition (VMD), temporal convolutional networks (TCNs), and long short-term memory (LSTM) networks. The wave sequence features were obtained using VMD technology based on the wave data from the National Data Buoy Center. Then the SWH and APD prediction models were established using TCNs, LSTM, and Bayesian hyperparameter optimization. The VMD–TCN–LSTM model was compared with the VMD–LSTM (without TCN cells) and LSTM (without VMD and TCN cells) models. The VMD–TCN–LSTM model has significant superiority and shows robustness and generality in different buoy prediction experiments. In the 3 h wave forecasts, VMD primarily improved the model performance, while the TCN had less of an influence. In the 12, 24, and 48 h wave forecasts, both VMD and TCNs improved the model performance. The contribution of the TCN to the improvement of the prediction result determination coefficient gradually increased as the forecasting length increased. In the 48 h SWH forecasts, the VMD and TCN improved the determination coefficient by 132.5 % and 36.8 %, respectively. In the 48 h APD forecasts, the VMD and TCN improved the determination coefficient by 119.7 % and 40.9 %, respectively.

AimTo investigate the effect of temperature, humidity and the concentration of ambient air pollution on the hospitalization of AECOPD.MethodHospitalization record was obtained from Shenyang Medical Insurance Bureau, concluding patient’s age, gender, income hospital time, outcome hospital; Generalized additive model was used to analyze the relationship between temperature, humidity, the concentration of ambient air pollution and the hospitalization of AECOPD.ResultThe effect of ozone on admission rate in male group was higher than that in female group. Ambient air pollution had a weak influence on age≤50 group. It was found that the optimal lag day for daily relative 40 humidity to age≤50 group, 50<age≤60, 60<age≤70 group and age>70 group was on lag5, lag4, lag4 and lag5, respectively.ConclusionAir pollution, relative humidity and temperature can increase the risk of admission for acute exacerbation of COPD, and in this process there was a lag effect.

This study aimed to explore the association between air pollutants and outpatient visits for influenza-like illnesses (ILI) under the coronavirus disease 2019 (COVID-19) stage in the subcenter of Beijing.The data on ILI in the subcenter of Beijing from January 1, 2018 to December 31, 2020 were obtained from the Beijing Influenza Surveillance Network. A generalized additive Poisson model was applied to examine the associations between the concentrations of air pollutants and daily outpatient visits for ILI when controlling meteorological factors and temporal trend.A total of 171 943 ILI patients were included. In the pre-coronavirus disease 2019(COVID-19) stage, an increased risk of ILI outpatient visits was associated to a high air quality index (AQI) and the high concentrations of particulate matter less than 2.5 (PM2.5 ), particulate matter 10 (PM10 ), sulphur dioxide (SO2 ), nitrogen dioxide (NO2 ), and carbon monoxide (CO), and a low concentration of ozone (O3 ) on lag0 day and lag1 day, while a higher increased risk of ILI outpatient visits was observed by the air pollutants in the COVID-19 stage on lag0 day. Except for PM10 , the concentrations of other air pollutants on lag1 day were not significantly associated with an increased risk of ILI outpatient visits during the COVID-19 stage.The findings that air pollutants had enhanced immediate effects and diminished lag-effects on the risk of ILI outpatient visits during the COVID-19 pandemic, which is important for the development of public health and environmental governance strategies.

In several European rural communities, woody biomass is counted among the most important energy sources for heating and cooking. However, the use of old-fashioned fireplaces may affect indoor and outdoor air quality. To depict this situation and to plan the necessary improvement interventions, a pilot action was implemented in a typical mountainous Mediterranean area (Anogeia, Crete). The action involved: (1) identification of the quantities, use and source of the woody biomass used in the community based on the analysis of data collected through a systematic survey; (2) on-site indoor and outdoor measurements of air quality (CO2, CO, NOX, PM), during winter and summer. Based on this survey, around 70% of the study area households in Anogeia using woody biomass for heating purposes in low energy efficiency systems resulted in high firewood consumption. Fifty-three per cent of occupants did not consider indoor air quality as a result of wood burning. The air quality analysis showed very high concentrations of indoor air pollutants in most old buildings with seniors using traditional heating systems. The type of main/supplementary heating system used in a dwelling depends on factors such as the size of the dwelling, year of construction, education level and age of occupants. The results also demonstrate a strong correlation between the heating season (summer/winter) and the concentrations of air pollutants in the sampling sites.

Accurate load forecasting is essential for ensuring safe, stable, and economical operation of energy internet. Temporal convolutional networks (TCNs) have demonstrated superior performance, when compared to recurrent neural network models, since their introduction in electrical load forecasting. However, the current TCN‐based models are unable to obtain a large receptive field and strong long‐time feature extraction capability owing to the specific kernel size of the 1D convolution structure. This paper proposes a temporal inception convolutional network based on multi‐head attention (TICN‐Att) for ultra‐short‐term load prediction. By introducing an inception structure into the TCN, the proposed model can extract multi‐dimensional information from the input features, through the multiple hidden convolutional kernels of different scales, without stacking layers depth‐wise. Simultaneously, by introducing a multi‐head attention mechanism, the TICN‐Att model has a long time‐dependent extraction capability, similar to that of the long short‐term memory network models. The generalization and validity of the model are tested using the global energy forecasting competition (GEFCOM2014) dataset, electrical load data of a city in Jiangsu (China), and PJM power system dataset. The experimental results demonstrated that the proposed model has the best prediction effect, compared to the other state‐of‐the‐art models.

Prenatal exposure to air pollution is associated with intrauterine growth restriction and low birth weight. Gene expression changes in newborns in relation to air pollution have not been sufficiently studied. We analyzed whole genome expression in cord blood leukocytes of 202 newborns from diverse localities of the Czech Republic, differing among other factors in levels of air pollution: the district of Karvina (characterized by higher concentration of air pollutants) and Ceske Budejovice (lower air pollution levels). We aimed to identify differentially expressed genes (DEGs) and pathways in relation to locality and concentration of air pollutants. We applied the linear model to identify the specific DEGs and the correlation analysis, to investigate the relationship between the concentrations of air pollutants and gene expression data. An analysis of biochemical pathways and gene set enrichment was also performed. In general, we observed modest changes of gene expression, mostly attributed to the effect of the locality. The highest number of DEGs was found in samples from the district of Karvina. A pathway analysis revealed a deregulation of processes associated with cell growth, apoptosis or cellular homeostasis, immune response-related processes or oxidative stress response. The association between concentrations of air pollutants and gene expression changes was weak, particularly for samples collected in Karvina. In summary, as we did not find a direct effect of exposure to air pollutants, we assume that the general differences in the environment, rather than actual concentrations of individual pollutants, represent a key factor affecting gene expression changes at delivery. Environ. Mol. Mutagen. 59:401-415, 2018. © 2018 Wiley Periodicals, Inc.

The article presents the results of the analysis of the cyclicity of changes in the concentrations of pollutants in the atmospheric air of Minsk. The purpose of this study was to establish the cyclicity of changes in the concentrations of pollutants in the atmospheric air of Minsk to develop a system of preventive measures. Materials and methods. The study materials were the concentrations of the main pollutants from the route monitoring posts of Minsk for 2009–2022. Methods: statistical, retrospective epidemiological analysis. Conclusion. The presence of seasonal fluctuations in the content of nitrogen dioxide and particulate matter (increased content in the summer), carbon monoxide and formaldehyde (in the summer-autumn period) was established, which can be used to develop a system of preventive measures.

Green infrastructure (GI) in urban areas may be adopted as a passive control system to reduce air pollutant concentrations. However, current dispersion models offer limited modelling options to evaluate its impact on ambient pollutant concentrations. The scope of this review revolves around the following question: how can GI be considered in readily available dispersion models to allow evaluation of its impacts on pollutant concentrations and health risk assessment? We examined the published literature on the parameterisation of deposition velocities and datasets for both particulate matter and gaseous pollutants that are required for deposition schemes. We evaluated the limitations of different air pollution dispersion models at two spatial scales – microscale (i.e. 10–500 m) and macroscale (i.e. 5–100 km) - in considering the effects of GI on air pollutant concentrations and exposure alteration. We conclude that the deposition schemes that represent GI impacts in detail are complex, resource-intensive, and involve an abundant volume of input data. An appropriate handling of GI characteristics (such as aerodynamic effect, deposition of air pollutants and surface roughness) in dispersion models is necessary for understanding the mechanism of air pollutant concentrations simulation in presence of GI at different spatial scales. The impacts of GI on air pollutant concentrations and health risk assessment (e.g., mortality, morbidity) are partly explored. The i-Tree tool with the BenMap model has been used to estimate the health outcomes of annually-averaged air pollutant removed by deposition over GI canopies at the macroscale. However, studies relating air pollution health risk assessments due to GI-related changes in short-term exposure, via pollutant concentrations redistribution at the microscale and enhanced atmospheric pollutant dilution by increased surface roughness at the macroscale, along with deposition, are rare. Suitable treatments of all physical and chemical processes in coupled dispersion-deposition models and assessments against real-world scenarios are vital for health risk assessments.

Abstract. To control severe air pollution in China, comprehensive pollution control strategies have been implemented throughout the country in recent years. To evaluate the effectiveness of these strategies, the influence of meteorological conditions on levels of air pollution needs to be determined. Using the intensive air pollution control strategies implemented during the Asia-Pacific Economic Cooperation Forum in 2014 (APEC 2014) and the 2015 China Victory Day Parade (Victory Parade 2015) as examples, we estimated the role of meteorological conditions and pollution control strategies in reducing air pollution levels in Beijing. Atmospheric particulate matter of aerodynamic diameter ≤ 2.5 µm (PM2.5) samples were collected and gaseous pollutants (SO2, NO, NOx, and O3) were measured online at a site in Peking University (PKU). To determine the influence of meteorological conditions on the levels of air pollution, we first compared the air pollutant concentrations during days with stable meteorological conditions. However, there were few days with stable meteorological conditions during the Victory Parade. As such, we were unable to estimate the level of emission reduction efforts during this period. Finally, a generalized linear regression model (GLM) based only on meteorological parameters was built to predict air pollutant concentrations, which could explain more than 70 % of the variation in air pollutant concentration levels, after incorporating the nonlinear relationships between certain meteorological parameters and the concentrations of air pollutants. Evaluation of the GLM performance revealed that the GLM, even based only on meteorological parameters, could be satisfactory to estimate the contribution of meteorological conditions in reducing air pollution and, hence, the contribution of control strategies in reducing air pollution. Using the GLM, we found that the meteorological conditions and pollution control strategies contributed 30 and 28 % to the reduction of the PM2.5 concentration during APEC and 38 and 25 % during the Victory Parade, respectively, based on the assumption that the concentrations of air pollutants are only determined by meteorological conditions and emission intensities. We also estimated the contribution of meteorological conditions and control strategies in reducing the concentrations of gaseous pollutants and PM2.5 components with the GLMs, revealing the effective control of anthropogenic emissions.

Hand, foot, and mouth disease (HFMD) is a major public health concern in the Asia–Pacific region. Previous studies have implied that ambient air pollution may affect the incidence of HFMD, but the results among different regions are inconsistent. We aimed to deepen the understanding of the associations between air pollutants and HFMD by conducting a multicity study. Daily data on childhood HFMD counts and meteorological and ambient air pollution (PM2.5, PM10, NO2, CO, O3, and SO2) concentrations in 21 cities in Sichuan Province from 2015 to 2017 were collected. A spatiotemporal Bayesian hierarchical model framework was established, and then a distributed lag nonlinear models (DLNMs) was constructed to reveal exposure-lag-response relationships between air pollutants and HFMD while controlling for spatiotemporal effects. Furthermore, given the differences in the levels and seasonal trends of air pollutants between the basin region and plateau region, we explored whether these associations varied between different areas (basin and plateau). The associations between air pollutants and HFMD were nonlinear, with different lag responses. Low NO2 concentrations and both low and high PM2.5 and PM10 concentrations were associated with a decreased risk of HFMD. No significant associations between CO, O3, and SO2 and HFMD were found. The associations between air pollutant concentrations and HFMD were different between the basin and plateau regions. Our study revealed associations between PM2.5, PM10, and NO2 concentrations and HFMD, deepening the understanding of the relationships between air pollutants and HFMD. These findings provide evidence to support the formulation of relevant prevention measures and the establishment of an early warning system.

도시의 무분별한 개발로 인해 수도권의 주요도시는 환경문제를 겪고 있다. 이 중 대기오염은 도시민들이 신체적 경제적 피해를 받고 살아가게 되는 원인으로 작용하고 있다. 이에 인간활동으로 인해 배출되는 대기오염물질을 도시환경이 어느 정도 수용가능한지 예측하고, 이를 통해 적정 도시개발 수준을 검토할 필요성이 제기되고 있다. 본 연구는 대기오염물질 배출량에 따라 대기오염의 양상이 다르게 나타날 것이란 전제 하에, 경기도 과천시를 대상으로 대기환경기준 하에서 허용가능한 대기오염물질 배출량을 산정하고, 이를 기반으로 적정 인구규모를 도출하였다. 분석 결과는 다음과 같다. 첫째, IDW 보간법을 통해 일산화탄소(CO), 이산화질소(<TEX>$NO_2$</TEX>), 아황산가스(<TEX>$SO_2$</TEX>) 농도를 추정한 결과 과천시 전체적으로는 대기환경기준을 초과하지 않는 것으로 나타났다. 둘째, 대기오염물질 배출량과 농도와의 상관분석 결과 일산화탄소(CO)와 이산화질소(<TEX>$NO_2$</TEX>) 농도는 이동오염원과 총오염원, 아황산가스(<TEX>$SO_2$</TEX>) 농도는 이동오염원과 상관관계가 높은 것으로 나타났다. 셋째, 회귀분석을 통해 대기환경기준 하에서 대기오염물질 배출량을 산정하고 이를 기반으로 지탱가능한 인구수를 산정한 결과, 일산화탄소(CO)의 경우 지탱가능인구수가 실제 인구수보다 높게 나타났고, 이산화질소(<TEX>$NO_2$</TEX>)와 아황산가스(<TEX>$SO_2$</TEX>)의 경우는 주거지와 상업시설이 밀집된 도심부와 경계부에서 지탱가능한 인구수를 초과하는 것으로 나타났다. 본 연구를 통해 시도된 환경용량 측정은 대기환경기준 하에서 어느 정도의 인간활동이 적절한 수준인지를 제시해 주었다는데 의의가 있다. 이를 통해 도시환경이 지니는 용량의 범위 내에서 개발행위를 관리함으로써 지속가능한 도시개발이 가능할 것이다. Indiscreet developments cause environmental problems in major cities of Seoul Metropolitan Area. Among the environmental problems, the air pollution leads the citizens' physical and economic damages. Therefore, it needs to predict how much air pollutant which is emitted from human activities can be carried by urban environment, then to examine the reasonable level of urban development This study assumed that the air pollution is represented differently by the amount of emission. With the assumption, the acceptable air pollutant emission which keeps the air quality under the environmental standard is estimated, then the proper population is calculated in the case of Gwacheon, Gyeonggi. The result is as follow: First, air pollution concentrations of CO, <TEX>$NO_2$</TEX>, <TEX>$SO_2$</TEX> which are estimated by using IDW interpolation of GIS don't excess the air environmental standard. Second, the result of correlation analysis between air pollutant emission and air pollution concentration shows that CO and <TEX>$NO_2$</TEX> has high correlationship with total source of pollution and linear source of pollution, and <TEX>$SO_2$</TEX> with linear source of pollution. Third, the results of regression analysis show that the acceptable population is bigger that the real population in the case of CO, and with the estimation of <TEX>$NO_2$</TEX> and <TEX>$SO_2$</TEX>, the current population in the urban center and boundaries where the residential and commerce land uses are concentrated is bigger than the acceptable population. The consequence of this study is that the estimation of carrying capacity can suggest the acceptable human activities which keep the air quality under the environmental standard. This can leads the sustainable urban development by control the human activities under the carrying capacity of urban environment.

Environmental air pollution has been linked to the pathogenesis of RA. Nevertheless, evidence linking higher concentrations of air pollutants with the risk of RA reactivations is missing. The objective of the present study was to determine the association between RA flares and air pollution. We collected longitudinal data of patients affected by RA and of the daily concentration of air pollutants in the Verona area. We designed a case-crossover study. We compared the exposure to pollutants in the 30-day and 60-day periods preceding an arthritic flare referent to the 30-day and 60-day preceding a low-disease activity visit. The study included 888 patients with RA with 3396 follow-up visits; 13636 daily air pollution records were retrieved. We found an exposure-response relationship between the concentration of air pollutants and the risk of having abnormal CRP levels. Patients exposed to greater concentrations of air pollutants were at higher risk of having CRP levels ≥5 mg/l. Concentrations of CO, NO, NO2, NOx, PM10, PM2.5 and O3 were higher in the 60-day period preceding a flare. We found a striking association between air pollution and RA disease severity and reactivations in a cohort of patients followed over a 5-year period. The exposure to high levels of air pollutants was associated with increased CRP levels and a higher risk of experiencing a flare of arthritis. This excessive risk was evident at very low levels of exposure.

Ambient air pollution and systemic inflammation are recognized as risk factors for cardiovascular-kidney-metabolic (CKM) syndrome. However, the joint effect on middle-aged and elderly people in China remains unclear. This research aimed to explore the association between the long-term effects of air pollution/C-reactive protein (CRP) and early CKM syndrome. This cross-sectional cohort involved 9293 participants from the China Health and Retirement Longitudinal Study (CHARLS) in 2015 (Wave 3). The concentrations of air pollutants, including fine particulate matter (PM2.5), inhalable particles (PM10), sulfur dioxide (SO2), nitrogen dioxide (NO2), ozone (O3) and carbonic oxide (CO), were obtained from the ChinaHighAirPollutants (CHAP), which contains estimates of the concentrations of these air pollutants in residences at the city level. CKM syndrome was diagnosed according to the American Heart Association (AHA) definition, and stages 1 and 2 were defined as early stages in this study. Generalized linear model (GLM) was employed to assess the relationship between air pollutants and CKM syndrome, while the interactions between CRP and air pollutants were also included to evaluate the modified impacts of CRP on the air pollution-CKM association. GLM results revealed that per-SD increases in the concentrations of PM2.5, PM10, SO2, NO2, O3 and CO were corresponded to elevated CKM prevalence, with ORs (95% CI) of 1.209 (1.085–1.346), 1.263 (1.134–1.406), 1.227 (1.098–1.372), 1.182 (1.060–1.317), 1.135 (1.019–1.265) and 1.160 (1.041–1.292), respectively. Stronger correlations were seen among individuals aged ≤ 65 years, males, urban residents and non-smokers. Moreover, CRP was significantly linked to a greater risk of CKM (OR = 1.207, 95% CI 1.126–1.295). Higher concentrations of air pollutants progressively amplified the risk of CKM syndrome associated with elevated CRP. And the adverse effects of air pollutants were most prominent among individuals with moderate, rather than minimal or severe levels of inflammation. Prolonged exposure to air pollutants has been linked to a greater risk of early CKM syndrome, potentially mediated by inflammatory responses. Particularly, CRP modified the air pollutant–CKM relationship in a complex manner, whereas air pollutants showed a more evident modification of the CRP–CKM association. Considering the ageing population and the health burden posed by CKM, interventions should aim to improve air quality and alleviate systemic inflammatory conditions.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-24690-5.

The accuracy of short-term electricity price forecasting has profound influence on the business decisions made by the participants in the electricity market. Thus, we propose a short-term electricity price combination prediction model based on Complete Ensemble Empirical Mode Decomposition(CEEMD) as well as Temporal Convolutional Attention-based Network(TCAN). First, we defined the correlations among the features according to the Pearson Correlation Analysis and selected the desired features for our model. We then defined the single prediction period to be 24 hours based on the Unit Root test. In addition, we decomposed and denoised the data based on CEEMD and built the attention mechanism into the temporal convolution network. Using the expansion cascade network to extract the relationship between the inputs, combined with the self-attention mechanism to extract the internal information and learn the position dependence, effectively improve the model training speed and prediction accuracy. In order to verify the validity of the model, the actual electricity price data of DK1 in the Nordic electricity market from April to May 2020 were forecasted. The results show that the proposed method can effectively improve the accuracy and reliability of electricity price forecasting, and can provide reliable decision-making basis.

Changes in air pollutants during the COVID-19 lockdown in Beijing: Insights from a machine-learning technique and implications for future control policy