Search

Over the last few years, there has been a noticeable increase in interest in air quality issues in Poland. Information on this subject is increasingly appearing in the media and in public debate. However, it seems that awareness of the existence and importance of this problem is still too low in our society. In particular, few people have sufficient knowledge of the impact of air pollutants on health. Consequently, the problem of air pollution is very often underestimated. The increase in risk of occurrence of specific adverse health effects associated with exposure to air pollutants is usually relatively low (except in cases of high pollutant concentrations or people in high-risk groups). However, the prevalence of exposure as well as the association with common diseases result in the fact that the impact of air pollutants on health status of the population is significant. This paper attempts to analyse the relationship between ambient air quality and the number of people who visited a local health care facility and were diagnosed with respiratory and cardiovascular diseases. The analysis was performed based on the town of Żory located in the Silesian Voivodeship in southern Poland. Air pollutant concentrations of PM2.5, PM10 and SO2 for the summer and heating seasons were obtained from the database of the monitoring station owned by the Chief Inspectorate for Environmental Protection. Information on the number of people who visited a physician on particular days and who were diagnosed with respiratory or cardiovascular diseases was obtained from the local health care facility "Medyk" in Żory. The analysis was conducted for the summer period from 01.06.2021 to 31.08.2021 and the heating season from 01.11.2021 to 15.01.2022. The analysis showed that the increased concentrations of particulate pollution did not result in an increase in the number of people who visited a physician with respiratory diseases. In the case of the heating period, incidents of above-normal concentrations of PM10 particulate matter may have had a noticeable impact on the increase in the number of patients who visited a physician with cardiovascular diseases. This increase in the number of patients occurred several days after the smog incidents which occurred in mid-December. However, no short-term link was observed between the increase in the number of patients with cardiovascular and respiratory diseases and the occurrence of elevated concentrations of sulphur dioxide in the air. Furthermore, higher concentrations of particulate and gaseous pollutants during the heating season resulted in more respiratory and cardiovascular diseases than during the summer season. [ABSTRACT FROM AUTHOR]

Accurate and fine-grained individual air quality index (IAQI) prediction is the basis of air quality index (AQI), which is of great significance for air quality control and human health. Traditional approaches, such as time series, recurrent neural network or graph convolutional network, cannot effectively integrate spatial-temporal and meteorological factors and manage the dynamic edge relationship among scattered monitoring stations. In this paper, a ST-CCN-IAQI model is proposed based on spatial-temporal causal convolution networks. Both the spatial effects of multi-source air pollutants and meteorological factors were considered via spatial attention mechanism. Time-dependent features in the causal convolution network were extracted by stacked dilated convolution and time attention. All the hyper-parameters in ST-CCN-IAQI were tuned by Bayesian optimization. Shanghai air monitoring station data were employed with a series of baselines (AR, MA, ARMA, ANN, SVR, GRU, LSTM and ST-GCN). Final results showed that: (1) For a single station, the RMSE and MAE values of ST-CCN-IAQI were 9.873 and 7.469, decreasing by 24.95% and 16.87% on average, respectively. R2 was 0.917, with an average 5.69% improvement; (2) For all nine stations, the mean RMSE and MAE of ST-CCN-IAQI were 9.849 and 7.527, respectively, and the R2 value was 0.906. (3) Shapley analysis showed PM10, humidity and NO2 were the most influencing factors in ST-CCN-IAQI. The Friedman test, under different resampling, further confirmed the advantage of ST-CCN-IAQI. The ST-CCN-IAQI provides a promising direction for fine-grained IAQI prediction. [ABSTRACT FROM AUTHOR]

A natural experiment conducted on the shrinking Salton Sea, a saline lake in California, showed that each one foot drop in lake elevation resulted in a 2.6% average increase in P M 2.5 concentrations. The shrinking has caused the asthma rate continues to increase among children, with one in five children being sent to the emergency department, which is related to asthma. In this paper, several data-driven machine learning (ML) models are developed for forecasting air quality and dust emission to study, evaluate and predict the impacts on human health due to the shrinkage of the sea, such as the Salton Sea. The paper presents an improved long short-term memory (LSTM) model to predict the hourly air quality ( O 3 and CO ) based on air pollutants and weather data in the previous 5 h. According to our experiment results, the model generates a very good R2 score of 0.924 and 0.835 for O 3 and CO , respectively. In addition, the paper proposes an ensemble model based on random forest (RF) and gradient boosting (GBoost) algorithms for forecasting hourly P M 2.5 and P M 10 using the air quality and weather data in the previous 5 h. Furthermore, the paper shares our research results for P M 2.5 and P M 10 prediction based on the proposed ensemble ML models using satellite remote sensing data. Daily P M 2.5 and P M 10 concentration maps in 2018 are created to display the regional air pollution density and severity. Finally, the paper reports Artificial Intelligence (AI) based research findings of measuring air pollution impact on asthma prevalence rate of local residents in the Salton Sea region. A stacked ensemble model based on support vector regression (SVR), elastic net regression (ENR), RF and GBoost is developed for asthma prediction with a good R2 score of 0.978. [ABSTRACT FROM AUTHOR]

This paper assesses the impact of transport infrastructure quality on economic competitiveness in the European Union (EU), context in which we argue that the quality of the different modal transport networks has a differentiated contribution on competitiveness. The purpose of our analysis aims to quantify the qualitative contribution of each modal transport network to economic competitiveness in the EU. The econometric quantification of the mentioned impact emphasizes a contributory hierarchy as follows: the quality of port and railroad infrastructure contributes most substantially to economic competitiveness, followed by the quality of the air transport infrastructure, the inland waterways and the road network. Based on the iterated results, we sequenced the EU member states with the lowest quality of networks with the highest impact on competitiveness. Thus, we identified the states for which the priority improvement of the quality of the port and railway infrastructures would significantly improve their economic competitiveness. [ABSTRACT FROM AUTHOR]

Introduction: This study aimed to develop a standard process and checklist for technical investigation of hookah diving equipment and apply it to Tasmanian hookah fatality investigations from the last 25 years. Methods: A literature search was undertaken to identify technical reports and equipment investigations associated with diving accidents. The information was assimilated to create a process and checklist for specifically assessing the hookah apparatus. The checklist was then applied in a gap analysis of Tasmanian hookah diving fatality technical reports from 1995 to 2019. Results: As no papers specifically describing technical evaluation of hookah equipment were identified, references evaluating scuba equipment were used to create a hookah technical assessment process incorporating unique features of the hookah. Features included: owner responsibility for air quality; maintenance, function; exhaust proximity to air intake; reservoir volume; output non-return valves; line pressure; sufficiency of supply; entanglement; hose severance risk; gas supply failure and hosing attachment to the diver. Seven hookah diving deaths occurred in Tasmania (1995−2019) of which three had documented technical assessment. Gap analysis identified inconsistent structure between reports with variability in the case descriptors. Missing technical data included: overview of the hookah systems; accessories; weights; how the apparatus was worn by the diver; compressor suitability; assessment of hookah function; breathing gas output and exhaust position relative to air intake. Conclusions: The study demonstrated a need to standardise technical reporting of hookah equipment after diving accidents. The checklist generated may serve as a resource for future hookah assessments and inform strategies for preventing future hookah accidents. [ABSTRACT FROM AUTHOR]

From the ensemble of stations that monitor surface air quality over the United States and Europe, we identify extreme ozone pollution events and find that they occur predominantly in clustered, multi-day episodes with spatial extents of more than 1000 km. Such scales are amenable to forecasting with current global atmospheric chemistry models. We develop an objective mapping algorithm that uses the heterogeneous observations of the individual surface sites to calculate surface ozone averaged over 1° by 1° grid cells, matching the resolution of a global model. Air quality extreme (AQX) events are identified locally as statistical extremes of the ozone climatology and not as air quality exceedances. With the University of California, Irvine chemistry-transport model (CTM) we find there is skill in hindcasting these extreme episodes, and thus identify a new diagnostic using global chemistry-climate models (CCM) to identify changes in the characteristics of extreme pollution episodes in a warming climate. [ABSTRACT FROM AUTHOR]

Emissions to air are reported by countries to EMEP. The emissions data are used for country compliance checking with EU emission ceilings and associated emission reductions. The emissions data are also necessary as input for air quality modelling. The quality of these "official" emissions varies across Europe. As alternative to these official emissions, a spatially explicit high resolution emission inventory (7km×7 km) for UNECE-Europe for all years between 2003 and 2009 for the main air pollutants was made. The primary goal was to supply air quality modellers with the input they need. The inventory was constructed by using the reported emission national totals by sector where the quality is sufficient. The reported data were analysed by sector in detail, and completed with alternative emission estimates as needed. This resulted in a complete emission inventory for all countries. For particulate matter, for each source emissions have been split in coarse and fine particulate matter, and further disaggregated to EC, OC, SO4, Na and others using fractions based on literature. Doing this at the most detailed sectoral level in the database implies that a consistent set was obtained across Europe. This allows better comparisons with observational data which can, through feedback, help to further identify uncertain sources and/or support emission inventory improvements for this highly uncertain pollutant. The resulting emission dataset was spatially distributed consistently across all countries by using proxy parameters. Point sources were spatially distributed using the specific location of the point source. The spatial distribution for the point sources was made year-specific. The TNO-MACC_II is an update of the TNO-MACC emission dataset. Major updates included the time extension towards 2009, use of the latest available reported data (including updates and corrections made until early 2012) and updates in distribution maps. [ABSTRACT FROM AUTHOR]

Vehicular emissions are one of the most important sources of pollution in China, and they can increase the ambient concentrations of air pollutants and degrade the air quality. Using data released by the National Bureau of Statistics, vehicular emissions in China in 2006 and 2010 were calculated at a high spatial resolution, by taking the emission standards into consideration. The results show that China's vehicular emissions of CO, NOx, VOCs, NH3, PM2.5, PM10, black carbon (BC), and organic carbon (OC) were 30113.9, 4593.7, 6838.0, 20.9, 400.2, 430.5, 285.6, and 105.1 Gg, respectively, in 2006 and 34175.2, 5167.5, 7029.4, 74.0, 386.4, 417.1, 270.9, and 106.2 Gg, respectively, in 2010. CO, VOCs, and NH3 emissions were mainly from motorcycles and light-duty gasoline vehicles, whereas NOx, PM2.5, PM10, and BC emissions were mainly from rural vehicles and heavy-duty diesel trucks. OC emissions were mainly from motorcycles and heavy-duty diesel trucks. Euro 0 and Euro I vehicles were the primary contributors to all of the pollutant emissions except NH3, which was mainly from Euro III and Euro IV vehicles. The spatial distribution of vehicular emissions in China in 2006 and 2010 were developed at a high resolution of 0.25° × 0.25°, by using the road traffic density to characterize the busyness of a road. This method could overcome the problem of getting traffic flow information and make the spatial allocation more closed to the actual road emissions. The results showed that vehicular emissions presented significant regional spatial distribution, and emissions in the eastern and southern parts of China were much higher than those in western and northern China in both years. The North China Plain, Yangtze River Delta, and Pearl River Delta regions jointly accounted for nearly half of the emissions. NH3 emissions increased greatly in big cities from 2006 to 2010. Emissions of CO, NOx, and VOCs could increase 52%, 9%, and 68%, if the emission standard and oil quality remained in the Euro I stage, so the policies on vehicular emissions implemented in China were demonstrated to be effective. Nevertheless, greater efforts are needed to improve the oil quality so that the new emission standard can implement timely and catch the international level quickly, especially the sulfur level because NOx emission is very sensitive to it. By comparing with coal consumption and NO2 column density observed by SCIA satellite, the increase of NOx emission in China from 2006 to 2010 was mainly caused by coal consumption. [ABSTRACT FROM AUTHOR]

Drawing on fine particulate matter (PM2.5) from satellite raster data and matching with the county-level socio-economic data from 2008 to 2015 in China, this paper investigates the impacts of the establishment of National Key Ecological Functional Zones (NKEFZ) on environmental quality by employing the difference-in-differences method, which was stablished in June 2011. The results indicate that the establishment of the NKEFZ significantly decreased the concentration values of PM2.5, a drop of about 20% during the study period, after the paper controls for other factors affecting air quality. The robustness tests using the maximum and medium concentration values of PM2.5 show similar results. Through further analysis, the paper finds that the establishment of NKEFZ can improve the ecological utilization efficiency of land. [ABSTRACT FROM AUTHOR]

Ozone, PM10 and PM2.5 concentrations over Paris, France and Stockholm, Sweden were modeled at 4 and 1 km horizontal resolutions respectively for the present and 2050 periods employing decade-long simulations.We account for large-scale global climate change (RCP-4.5) and fine resolution bottom-up emission projections developed by local experts and quantify their impact on future pollutant concentrations. Moreover, we identify biases related to the implementation of regional scale emission projections over the study areas by comparing modeled pollutant concentrations between the fine and coarse scale simulations. We show that over urban areas with major regional contribution (e.g., the city of Stockholm) the bias due to coarse emission inventory may be significant and lead to policy misclassification. Our results stress the need to better understand the mechanism of bias propagation across the modeling scales in order to design more successful local-scale strategies. We find that the impact of climate change is spatially homogeneous in both regions, implying strong regional influence. The climate benefit for ozone (daily average and maximum) is up to -5% for Paris and -2% for Stockholm city. The joined climate benefit on PM2.5 and PM10 in Paris is between -10 and -5% while for Stockholm we observe mixed trends up to 3% depending on season and size class. In Stockholm, emission mitigation leads to concentration reductions up to 15% for daily average and maximum ozone and 20% for PM and through a sensitivity analysis we show that this response is entirely due to changes in emissions at the regional scale. On the contrary, over the city of Paris (VOC-limited photochemical regime), local mitigation of NOx emissions increases future ozone concentrations due to ozone titration inhibition. This competing trend between the respective roles of emission and climate change, results in an increase in 2050 daily average ozone by 2.5% in Paris. Climate and not emission change appears to be the most influential factor for maximum ozone concentration over the city of Paris, which may be particularly interesting in a health impact perspective. [ABSTRACT FROM AUTHOR]

The negative impacts of fine particulate matter (PM2.5) exposure on human health are a primary motivator for air quality research. However, estimates of the air pollution health burden vary considerably and strongly depend on the datasets and methodology. Satellite observations of aerosol optical depth (AOD) have been widely used to overcome limited coverage from surface monitoring and to assess the global population exposure to PM2.5 and the associated premature mortality. Here we quantify the uncertainty in determining the burden of disease using this approach, discuss different methods and datasets, and explain sources of discrepancies among values in the literature. For this purpose we primarily use the MODIS satellite observations in concert with the GEOS-Chem chemical transport model. We contrast results in the United States and China for the years 2004-2011. We estimate that in the United States, exposure to PM2.5 accounts for approximately 4 % of total deaths compared to 22 % in China (using satellite-based exposure), which falls within the range of previous estimates. The difference in estimated mortality burden based solely on a global model vs. that derived from satellite is approximately 9 % for the US and 4 % for China on a nationwide basis, although regionally the differences can be much greater. This difference is overshadowed by the uncertainty in the methodology for deriving PM2.5 burden from satellite observations, which we quantify to be on order of 20 % due to uncertainties in the AOD-to-surface-PM2.5 relationship, 10 % due to the satellite observational uncertainty, and 30 % or greater uncertainty associated with the application of concentration response functions to estimated exposure. [ABSTRACT FROM AUTHOR]

A regional air-quality forecast system's model of surface ozone variability based on cloud coverage is evaluated using satellite-observed cloud fraction (CF) information and a surface air-quality monitoring system. We compared CF and daily maximum ozone from the National Oceanic and Atmospheric Administration's National Air Quality Forecast Capability (NOAA NAQFC) with CFs from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the U.S. Environmental Protection Agency's AirNow surface ozone measurements during May to October 2014. We found that observed surface ozone shows a clear (negative) correlation with the MODIS CFs, showing around 1 ppb decrease for 10% MODIS CF change over the Contiguous United States, while the correlation of modeled surface ozone with the model CFs is much weaker, showing only -0.5 ppb per 10% NAQFC CF change. Further, daytime CF differences between MODIS and NAQFC are correlated with modeled surface-ozone biases between AirNow and NAQFC, showing -1.05 ppb per 10% CF change, implying that spatial- and temporal-misplacement of the modeled cloud field might have biased modeled surface ozone-level. Current NAQFC cloud fields seem to be too bright compared to MODIS cloud fields (mean NAQFC CF = 0.38 and mean MODIS CF = 0.55), contributing up to 35% of surface-ozone bias in the current NAQFC system. [ABSTRACT FROM AUTHOR]

Although numerous spatiotemporal approaches have been presented to address the problem of missing spatiotemporal data, there are still limitations in concurrently capturing the underlying spatiotemporal dependence of spatiotemporal graph data. Furthermore, most imputation methods miss the hidden dynamic connection associations that exist between graph nodes over time. To address the aforementioned spatiotemporal data imputation challenge, we present an attention-based message passing and dynamic graph convolution network (ADGCN). Specifically, this paper uses attention mechanisms to unify temporal and spatial continuity and aggregate node neighbor information in multiple directions. Furthermore, a dynamic graph convolution module is designed to capture constantly changing spatial correlations in sensors utilizing a new dynamic graph generation method with gating to transmit node information. Extensive imputation tests in the air quality and traffic flow domains were carried out on four real missing data sets. Experiments show that the ADGCN outperforms the state-of-the-art baseline. [ABSTRACT FROM AUTHOR]

Copyright of Advances in Atmospheric Sciences is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, air pollutants have become an important issue in meteorological research and an indispensable part of air quality forecasting. To improve the accuracy of the Chinese Unified Atmospheric Chemistry Environment (CUACE) model's air pollutant forecasts, this paper proposes a solution based on ensemble learning. Firstly, the forecast results of the CUACE model and the corresponding monitoring data are extracted. Then, using feature analysis, we screen the correction factors that affect air quality. The random forest algorithm, XGBoost algorithm, and GBDT algorithm are employed to correct the prediction results of PM2.5, PM10, and O3. To further optimize the model, we introduce the grid search method. Finally, we compare and analyze the correction effect and determine the best correction model for the three air pollutants. This approach enhances the precision of the CUACE model's forecast and improves our understanding of the factors that affect air quality. The experimental results show that the model has a better prediction error correction effect than the traditional machine learning statistical model. After the algorithm correction, the prediction accuracy of PM2.5 and PM10 is increased by 60%, and the prediction accuracy of O3 is increased by 70%. [ABSTRACT FROM AUTHOR]

A novel economic impact model is proposed by this paper to analyze the impact of economic downturn on the air quality in Wuhan during the epidemic period, and to explore the effective solutions to improve the urban air pollution. The Space Optimal Aggregation Model (SOAM) is used to evaluate the air quality of Wuhan from January to April in 2019 and 2020. The analysis results show that the air quality of Wuhan from January to April 2020 is better than that of the same period in 2019, and it shows a gradually better trend. This shows that although the measures of household isolation, shutdown and production stoppage adopted during the epidemic period in Wuhan caused economic downturn, it objectively improved the air quality of the city. In addition, the impact of economic factors on PM2.5, SO2 and NO2 is 19%, 12% and 49% respectively calculated by the SOMA. This shows that industrial adjustment and technology upgrading for enterprises that emit a large amount of NO2 can greatly improve the air pollution situation in Wuhan. The SOMA can be extended to any city to analyze the impact of the economy on the composition of air pollutants, and it has extremely important application value at the level of industrial adjustment and transformation policy formulation. [ABSTRACT FROM AUTHOR]

Diwali has become an occasion of air and noise pollution, and the release of particulate matter and toxic gases has chronic and acute effects on people and their environment. Thus, an air quality assessment study was done by CSIR-CSMCRI covering the pre-to-post Diwali 2021 period (5 days) in the three locations (traffic, residential, and control) of Bhavnagar. The average 24-h concentration of PM10 (380 µg/m3), PM2.5 (182.2 µg/m3), and SPM (403 µg/m3) was significantly higher during Diwali, exceeding the National Ambient Air Quality Standards (NAAQS). The concentrations of SO2 and NO2 were 121.8 µg/m3 and 102.1 µg/m3. Metals like Zn, Al, Pb, and Mn were found in higher concentrations during the study. The air quality index (AQI) was maximum on Diwali, resembling very poor air quality. More elements and oxides were detected in PM2.5 (S, Al, Mg, Ba, and Zn and their oxides) than in PM10 (Fe and S) through WDXRF. Water-soluble anions like SO42−, Cl−, and NO3− were observed during the study, with a higher SO42− (64%) on Diwali. The PM10 morphology and mapping of elements were done using SEM–EDX. Emerging contaminants, specifically phthalate groups, were detected through GCMS. The enrichment factor (EF) showed Zn and Pb originating from anthropogenic activities. The air quality data was validated using a variance test, least significance difference (LSD), correlation, and principal component analysis (PCA). This paper is the first to highlight the air quality assessment during Diwali for a western coastal place in India. It is time to implement regulations on burning firecrackers for pollution reduction, aiming to achieve a sustainable atmosphere. [ABSTRACT FROM AUTHOR]

This paper examines the effects of interventions to reduce air pollution during two international events on air quality in Beijing and its neighbor cities. Air quality data were gathered from China's Ministry of Environmental Protection, meteorological data from the China Meteorological Administration and economic data from the China Statistical Yearbook. The paper uses fixed-effect panel data models to empirically evaluate air quality improvement in Beijing and other affected cities before, during, and after the 2008 Olympic Games and the 2014 Asia-Pacific Economic Cooperation summit. Results show substantial improvement in air quality in Beijing and neighboring cities during the two events. However, some of the air quality improvement achieved reverted within a year after the games and within a week after the summit. Furthermore, the improvement achieved during the summit completely reverted and air quality deteriorated severely five days after the summit. It is also found that air quality in China, at least in the cities included in this study, gradually improved over the past 15 years or so. The findings suggest that sustainable interventions and incentive-based programs to reduce emissions from industry production and traffic are the key to maintaining the air pollution reduction achieved during the events. [ABSTRACT FROM AUTHOR]

Public air quality monitoring relies on expensive monitoring stations which are highly reliable and accurate but require significant maintenance and cannot be used to form a high spatial resolution measurement grid. Recent technological advances have enabled air quality monitoring that uses low-cost sensors. Being inexpensive and mobile, with wireless transfer support, such devices represent a very promising solution for hybrid sensor networks comprising public monitoring stations supported by many low-cost devices for complementary measurements. However, low-cost sensors can be influenced by weather and degradation, and considering that a spatially dense network would include them in large numbers, logistically adept solutions for low-cost device calibration are essential. In this paper, we investigate the possibility of a data-driven machine learning calibration propagation in a hybrid sensor network consisting of One public monitoring station and ten low-cost devices equipped with NO2, PM10, relative humidity, and temperature sensors. Our proposed solution relies on calibration propagation through a network of low-cost devices where a calibrated low-cost device is used to calibrate an uncalibrated device. This method has shown an improvement of up to 0.35/0.14 for the Pearson correlation coefficient and a reduction of 6.82 µg/m3/20.56 µg/m3 for the RMSE, for NO2 and PM10, respectively, showing promise for efficient and inexpensive hybrid sensor air quality monitoring deployments. [ABSTRACT FROM AUTHOR]

Air quality plays a vital role in people's health, and air quality forecasting can assist in decision making for government planning and sustainable development. In contrast, it is challenging to multi-step forecast accurately due to its complex and nonlinear caused by both temporal and spatial dimensions. Deep models, with their ability to model strong nonlinearities, have become the primary methods for air quality forecasting. However, because of the lack of mechanism-based analysis, uninterpretability forecasting makes decisions risky, especially when the government makes decisions. This paper proposes an interpretable variational Bayesian deep learning model with information self-screening for PM2.5 forecasting. Firstly, based on factors related to PM2.5 concentration, e.g., temperature, humidity, wind speed, spatial distribution, etc., an interpretable multivariate data screening structure for PM2.5 forecasting was established to catch as much helpful information as possible. Secondly, the self-screening layer was implanted in the deep learning network to optimize the selection of input variables. Further, following implantation of the screening layer, a variational Bayesian gated recurrent unit (GRU) network was constructed to overcome the complex distribution of PM2.5 and achieve accurate multi-step forecasting. The high accuracy of the proposed method is verified by PM2.5 data in Beijing, China, which provides an effective way, with multiple factors for PM2.5 forecasting determined using deep learning technology. [ABSTRACT FROM AUTHOR]

With rapid urbanization, hazardous environmental exposures such as air, noise, plastic, soil and water pollution have emerged as a major threat to urban health. Recent studies show that 9 out of 10 people worldwide breathe contaminated air contributing to over 7 million premature deaths annually. Internet of Things (IoT) and Artificial Intelligence (AI)-based environmental sensing and modelling systems have potential for contributing low-cost and effective solutions by providing timely data and insights to inform mitigation and management actions. While low and middleincome countries are among those most affected by environmental health risks, the appropriateness and deployment of IoT and AI systems in low-resource settings is least understood. Motivated by this knowledge gap, this paper presents a design space for a custom environmental sensing and management system designed and developed to fill the data gaps in low-resource urban settings with a particular focus on African cities. The paper presents the AirQo system, which is the first instance of the design space requirements. The AirQo system includes: (1) autonomous AirQo sensors designed and customised to be deployed in resource constrained environments (2) a distributed sensor network that includes over 120 static and mobile nodes for air quality sensing (3) AirQo network manager tool for tracking and management of installation and maintenance of nodes, (4) AirQo platform that provides calibration, data access and analytics tools to support usage among policy makers and citizens. Case studies from African cities that are using the data and insights for education, awareness and policy are presented. The paper provides a template for designing and deploying a technology-driven solution for cities in low resource settings. [ABSTRACT FROM AUTHOR]

Background: Air pollution is an important factor affecting residents' health. Methods: Based on the health data of 9959 residents from 28 provinces in China in the 2017 Chinese General Social Survey (CGSS), this paper uses a hierarchical linear model (HLM) to scientifically analyze the impact of air pollution on residents' health and to explore the moderating role of air pollution in various factors influencing residents' health. Results: Air pollution has significant negative effects on residents' health (coef. −0.103, p < 0.01), while frequency of exercise (coef. 0.070, p < 0.01), education level (coef. 0.012, p < 0.1) and income level (coef. 0.383, p < 0.01) have positive effects on residents' health. Air pollution has a negative moderating effect on the positive impact of exercise frequency on residents' health (coef. −0.015, p = 0.004). Conclusions: Air pollution causes serious damage to residents' health and it is necessary to control air pollution. Increasing residents' income, education level and exercise frequency can help improve residents' health level. Air pollution significantly reduce the positive impact of exercise frequency on residents' health. In order to effectively improve their own health, it is a better choice for residents to exercise when the air quality is good. [ABSTRACT FROM AUTHOR]

The Euro 7 legislation and the Zero-Impact Emissions concept aim at significantly improving air quality. Technologies that reduce pollutant emissions beyond current gasoline passenger cars have already been intensively investigated, but a holistic system layout considering extended boundary conditions is missing so far. This paper therefore develops technical solutions to achieve a Euro 7 scenario and Zero-Impact Emissions for a 2030+ vehicle. First, challenging test scenarios are identified to develop compliant vehicles. The scenarios cover extreme conditions in real-world driving, such as hot and cold ambient conditions, stop-and-go in rural areas or high speed and steep gradients on highways. Different technology options are discussed and selected for the investigations. An empirical–physical simulation model for the exhaust gas aftertreatment system is extended with new technologies, such as an electrical heater disc in front of the catalyst or a burner in the exhaust system. In addition to stoichiometric engine operation and increased catalyst volume, the results show that the expected Euro 7 regulations can be achieved in all extreme scenarios by combining additional exhaust gas heating with engine power limitation or pre-heating. Moreover, even Zero-Impact Emissions are achieved in most cases with the same technology options. [ABSTRACT FROM AUTHOR]

This paper investigates the effect of the architectural design of deep learning models in combination with a feature engineering approach considering the temporal variation in the features in the case of tropospheric ozone forecasting. Although deep neural network models have shown successful results by extracting features automatically from raw data, their performance in the domain of air quality forecasting is influenced by different feature analysis approaches and model architectures. This paper proposes a simple but effective analysis of tropospheric ozone time series data that can reveal temporal phases of the ozone evolution process and assist neural network models to reflect these temporal variations. We demonstrate that addressing the ozone evolution phases when developing the model architecture improves the performance of deep neural network models. As a result, we evaluated our approach on the CNN model and showed that not only does it improve the performance of the CNN model, but also that the CNN model in combination with our approach boosts the performance of the other deep neural network models such as LSTM. The development of the CNN, LSTM-CNN, and CNN-LSTM models using the proposed approach improved the prediction performance of the models by 3.58%, 1.68%, and 3.37%, respectively. [ABSTRACT FROM AUTHOR]

In China, blue sky defense is a crucial part of ecological environment governance. Objective environmental governance performance needs to be perceived by the public to more truly affect the public's evaluation of the government's environmental governance. This paper focuses on the public's subjective perception of air pollution and evaluation of the local government's environmental governance. Based on the Chinese General Social Survey data, the matched economic indicators, and air pollution data, we conduct a diachronic study on the public's evaluation of local governments' environmental protection work, and we analyze the relationship between the subjective perception of air pollution, the objective air pollution data, and the evaluation of local governments' environmental protection work. The results showed the following: (1) People's evaluation of local governments' environmental protection work significantly improved from 2013 to 2021. The objective indicator improved, while the subjective perception declined. (2) The subjective perception of air pollution has a significant negative impact on the evaluation of local governments' environmental protection work and needs to be better considered to improve air quality. At the same time, the effect of the objective indicator is insignificant. [ABSTRACT FROM AUTHOR]

Air pollution is one of the most important topics as it can cause various reactions of the organisms, such as mental health disorders, respiratory problems or various cardiovascular despises. Many of the side effects of pollution are caused by particulate matter (PM). Therefore air pollution, especially the concentration of PM is monitored in many European countries. In the past years, Skopje has been one of the top-ranked cities in the world concerning the concentration of PM. This paper investigates the effect of the pandemic with COVID-19 and the restriction measures on air quality. The data collected before the pandemic (May 2018), during the global pandemic (May 2020 and May 2021), and after the period with restriction measures (May 2022) are analyzed. The measurement parameters are collected at the technical campus of the Ss Cyril and Methodius University in Skopje, North Macedonia, in May 2018, May 2020, May 2021, and May 2022. In this research, it can be confirmed that the restriction measures had a significant positive impact on air pollution. [ABSTRACT FROM AUTHOR]

As attention to indoor environmental quality (IEQ) grows, a systematic strategy for assessing IEQ in schools needs to be developed. For this purpose, this paper presents a summary of parameters measured in school classrooms to characterize the quality of thermal, acoustic, and visual environments and indoor air quality (IAQ). The summary is based on a review of published literature reporting measurements in schools in Europe and North America in the past ten years. It also summarizes the measurement protocols and measured concentrations. Eighty-eight papers describing measurements in schools were identified and analyzed. No unique standardized measuring method was used in the reviewed studies and different parameters were measured. The most often measured parameters were those describing the thermal environment and IAQ. The former mainly comprised air temperature and relative humidity. The latter mainly comprised concentrations of carbon dioxide, particulate matter, radon, formaldehyde, and some volatile organic compounds. The measured parameters describing acoustic and visual environments mainly comprised noise level, reverberation time, and illuminance. A few studies reported additional measurements of radiant temperature, operative temperature, and speech intelligibility. Measurement protocols from different studies show inconsistency in sampling duration and location and expressed results. Measured concentrations also show high variation between studies, with some pollutants exceeding the threshold values proposed by local and/or international organizations such as the World Health Organization (WHO). This review provides the reference for developing a rating scheme and protocols for uniform characterization of classroom IEQ. [ABSTRACT FROM AUTHOR]

In this paper, based on the traditional grey multivariate convolutional model, the concept of a buffer operator is introduced to construct a single-indicator buffered grey multivariate convolutional model applicable to air quality prediction research. The construction steps of the model are described in detail in this paper, and the stability of the model is analyzed based on perturbation theory. Furthermore, the model was applied to predict the air quality composite index of the "2 + 26" Chinese air pollution transmission corridor cities based on different socioeconomic development scenarios in a multidimensional manner. The results show that the single-indicator buffered grey multivariate convolutional model constructed in this paper has better stability in predicting with a small amount of sample data. From 2020 to 2025, the air quality of the target cities selected in this paper follows an improving trend. The population density, secondary industry, and urbanization will not have a significant negative impact on the improvement of air quality if they are kept stable. In the case of steady development of secondary industry, air quality maintained a stable improvement in 96.4% of the "2 + 26" cities. The growth rate of population density will have an inverted U-shaped relationship with the decline in the city air quality composite index. In addition, with the steady development of urbanization, air quality would keep improving steadily in 71.4% of the "2 + 26" cities. [ABSTRACT FROM AUTHOR]

Biological aerosol is one of the most important pollutants in the air, not only influencing public health, and air quality, but also playing an important role in climate change and both chemical and physical processing regulations in the atmosphere. Therefore, the quantification of biological aerosols in the air needs to be more accurate. This article reviews the progress on quantitative assessment methods of biological aerosols in the atmosphere as well as those related merits that each method used. [ABSTRACT FROM AUTHOR]

The article presents a study on high-order decoupled direct method in three dimensions for particulate matter (HDDM-3D/PM) development. It mentions its enforcement towards advanced sensitivity analysis in the Community Multiscale Air Quality (CMAQ) model. It also notes its creation for investigating the inorganic aerosol module of the model, ISORROPIA.

Reactive volatile organic compounds (VOCs) are known to affect atmospheric chemistry, especially biogenic VOCs (BVOCs) which have a significant impact on regional air quality due to their large emission rates and high reactivities. Diterpenes (Kaur-16-ene and a diterpene likely to be Hibaene) were detected in all of the 205 enclosure air samples collected over multiple seasons at two different sites from Cryptomeria japonica and Chamaecyparis obtusa trees, the dominant coniferous trees in Japan. The emission rate of Kaur-16-ene, was determined to be from 0.01 to 7.1 µg dwg-1 h-1 (average: 0.61 µg dwg-1 h-1) by branch enclosure measurements and solid phase -- liquid extraction techniques. The emission rate was an order of magnitude higher than that of monoterpenes which are known to comprise a major portion of total BVOC emissions. In addition, total emission of Kaur-16-ene at 30 °C was estimated to be comparable to that of total anthropogenic VOC emissions. To our knowledge, this is the first report of volatile diterpene emissions from trees. [ABSTRACT FROM AUTHOR]

The article presents a study to measure gas phase compounds from ambient air using ion mobility spectrometer (IMS) in Finland. The study evaluates the suitability of the technique for on-line atmospheric measurements. It reveals the potential of IMS for atmospheric studies to monitor cleanness of prevailing atmospheric conditions and the detection of the changes of the conditions. Moreover, IMS could be tuned to respond to measurement needs in atmospheric studies.

The article discusses the combination of two multi-pollutant air quality and watershed models, the Advanced Modeling System for Transport, Emissions, Reactions and Deposition of Atmospheric Matter (AMSTERDAM) and the Watershed Analysis Risk Management Framework (WARMF). It notes that the linkage is used to obtain meteorological fields such as precipitation and air temperature. It adds that it traces the path of pollutants emitted into the air and their deposition to the Earth and watersheds.

The article presents abstracts on health science topics which include a research concerning the HIV-related education and infection control policies in Alabama, several perceptions about domestic violence (DV), and the impact of poor air quality to asthmatic patients.

Asia is one of the continents that is the most affected by the impacts of climate change. Asian countries need to take climate actions and mitigate emissions from the urban passenger transport sector. Despite some progress in improving urban mobility in Asian cities, greenhouse gas emissions from the transport sector continue to rise. Policy makers who are responsible for managing mobilities must play a major role in decarbonizing the transport sector. In this context, this paper reviews the efforts of selected Asian countries and cities towards reducing greenhouse gas emissions from the urban transport sector. It will analyze their pledges in the Nationally Determined Contributions submitted to the United Nations Framework Convention on Climate Change and will review their relevant transport sector strategies, policies, and practices. It will also look at trends in transport sector emissions and air pollution in different cities, including the short-term impacts of COVID-19. Lastly, it reviews governance issues and the roles that institutions should play to implement polices to decarbonize transport. Based on this analysis, this paper offers policy suggestions to accelerate actions, enhance cross-sectoral coordination, and move towards carbon neutrality in the transport sector in Asia. [ABSTRACT FROM AUTHOR]

Over the past four decades, China have experienced rapid economic growth but also a widening urban-rural income gap and deteriorating air quality. Based on the panel data of 30 provinces in China from 2006 to 2017, this paper investigates the effect of narrowing the urban-rural income gap on carbon emission reduction and pollution control by using OLS method. The empirical results indicate that: the narrowing of the urban-rural income gap has a positive impact on pollution control, while there are regional differences in the impact on carbon emission reduction. In the perspective of the whole country and central and western regions, the narrowing of the urban-rural income gap is conducive to carbon emission reduction. However, the narrowing of the urban-rural income gap increases carbon emissions in the eastern regions where economic development is at high level. This paper provides a theoretical basis and policy reference for promoting urban-rural integration and construction of ecological civilization. [ABSTRACT FROM AUTHOR]

This document is a response to a letter regarding a recently published paper titled "Effectiveness of Asthma Home Management Manual and Low-Cost Air Filter on Quality of Life Among Asthma Adults: A 3-Arm Randomized Controlled Trial." The authors address concerns raised by the letter writer and explain their choices in the study design and analysis. They acknowledge that some keywords may not strictly adhere to MeSH guidelines but defend their inclusion based on their relevance to the research. The authors also discuss the impact of asthma duration on the study results and clarify that certain data were considered baseline rather than outcome measures. The authors report no conflicts of interest. [Extracted from the article]

As air pollution is regarded as the single largest environmental health risk in Europe it is important that communication to the public is up to date and accurate and provides means to avoid exposure to high air pollution levels. Long- and short-term exposure to outdoor air pollution is associated with increased risks of mortality and morbidity. Up-to-date information on present and coming days' air quality helps people avoid exposure during episodes with high levels of air pollution. Air quality forecasts can be based on deterministic dispersion modelling, but to be accurate this requires detailed information on future emissions, meteorological conditions and process-oriented dispersion modelling. In this paper, we apply different machine learning (ML) algorithms – random forest (RF), extreme gradient boosting (XGB), and long short-term memory (LSTM) – to improve 1, 2, and 3 d deterministic forecasts of PM 10 , NOx , and O 3 at different sites in Greater Stockholm, Sweden. It is shown that the deterministic forecasts can be significantly improved using the ML models but that the degree of improvement of the deterministic forecasts depends more on pollutant and site than on what ML algorithm is applied. Also, four feature importance methods, namely the mean decrease in impurity (MDI) method, permutation method, gradient-based method, and Shapley additive explanations (SHAP) method, are utilized to identify significant features that are common and robust across all models and methods for a pollutant. Deterministic forecasts of PM 10 are improved by the ML models through the input of lagged measurements and Julian day partly reflecting seasonal variations not properly parameterized in the deterministic forecasts. A systematic discrepancy by the deterministic forecasts in the diurnal cycle of NOx is removed by the ML models considering lagged measurements and calendar data like hour and weekday, reflecting the influence of local traffic emissions. For O 3 at the urban background site, the local photochemistry is not properly accounted for by the relatively coarse Copernicus Atmosphere Monitoring Service ensemble model (CAMS) used here for forecasting O 3 but is compensated for using the ML models by taking lagged measurements into account. Through multiple repetitions of the training process, the resulting ML models achieved improvements for all sites and pollutants. For NOx at street canyon sites, mean squared error (MSE) decreased by up to 60 %, and seven metrics, such as R2 and mean absolute percentage error (MAPE), exhibited consistent results. The prediction of PM 10 is improved significantly at the urban background site, whereas the ML models at street sites have difficulty capturing more information. The prediction accuracy of O 3 also modestly increased, with differences between metrics. Further work is needed to reduce deviations between model results and measurements for short periods with relatively high concentrations (peaks) at the street canyon sites. Such peaks can be due to a combination of non-typical emissions and unfavourable meteorological conditions, which are rather difficult to forecast. Furthermore, we show that general models trained using data from selected street sites can improve the deterministic forecasts of NOx at the station not involved in model training. For PM 10 this was only possible using more complex LSTM models. An important aspect to consider when choosing ML algorithms is the computational requirements for training the models in the deployment of the system. Tree-based models (RF and XGB) require fewer computational resources and yield comparable performance in comparison to LSTM. Therefore, tree-based models are now implemented operationally in the forecasts of air pollution and health risks in Stockholm. Nevertheless, there is big potential to develop generic models using advanced ML to take into account not only local temporal variation but also spatial variation at different stations. [ABSTRACT FROM AUTHOR]

Declining air quality is highly ignored and very common form of degradation of the environment in nations that are both developed and developing. There are several contaminants in the air that have been identified in various studies on air pollution. The crucial parameters of all air pollutants are gaseous and particle pollution. The present study was undertaken to estimate the quality of ambient air in Chandrapur district, Maharashtra state of India. In this paper, an effort has been made to study the standing and trend of Sulphur dioxide (SO2), Oxides of Nitrogen (NOx), Carbon Monoxide (CO), Ozone (O3), Ammonia (NH3), Respirable Suspended Particulate Matter i.e.; PM10, PM2.5, toxic pollutants i.e.; lead, arsenic, nickel, benzo [a] pyarene and benzene and hydrocarbons. The results clearly show that, all parameters of ambient air quality monitoring values were some shown slightly below permissible limit. The ambient air quality monitoring data show that the Chandrapur district has substantial air pollution concerns in terms of SO2, NOx, PM, and other air pollutants. However, after comparing these values with NAAQS levels, the yearly averages of these air pollutants have been found to be below than the NAAQS levels. However, without effective mitigation measures, the concentrations of these pollutants will rise at quite alarming rate. [ABSTRACT FROM AUTHOR]

Hybrid approaches combining machine learning with traditional inverse problem solution methods represent a promising direction for the further development of inverse modeling algorithms. The paper proposes an approach to emission source identification from measurement data for advection–diffusion–reaction models. The approach combines general-type source identification and post-processing refinement: first, emission source identification by measurement data is carried out by a sensitivity operator-based algorithm, and then refinement is done by incorporating a priori information about unknown sources. A general-type distributed emission source identified at the first stage is transformed into a localized source consisting of multiple point-wise sources. The second, refinement stage consists of two steps: point-wise source localization and emission rate estimation. Emission source localization is carried out using deep learning with convolutional neural networks. Training samples are generated using a sensitivity operator obtained at the source identification stage. The algorithm was tested in regional remote sensing emission source identification scenarios for the Lake Baikal region and was able to refine the emission source reconstruction results. Hence, the aggregates used in traditional inverse problem solution algorithms can be successfully applied within machine learning frameworks to produce hybrid algorithms. [ABSTRACT FROM AUTHOR]

Despite significant improvements in air quality during and after COVID-19 restrictions, haze continued to occur in Zhengzhou afterwards. This paper compares ionic compositions and sources of PM2.5 before (2019), during (2020), and after (2021) the restrictions to explore the reasons for the haze. The average concentration of PM2.5 decreased by 28.5% in 2020 and 27.9% in 2021, respectively, from 102.49 μg m−3 in 2019. The concentration of secondary inorganic aerosols (SIAs) was 51.87 μg m−3 in 2019, which decreased by 3.1% in 2020 and 12.8% in 2021. In contrast, the contributions of SIAs to PM2.5 increased from 50.61% (2019) to 68.6% (2020) and 61.2% (2021). SIAs contributed significantly to PM2.5 levels in 2020–2021. Despite a 22~62% decline in NOx levels in 2020–2021, the increased O3 caused a similar NO3− concentration (20.69~23.00 μg m−3) in 2020–2021 to that (22.93 μg m−3) in 2019, hindering PM2.5 reduction in Zhengzhou. Six PM2.5 sources, including secondary inorganic aerosols, industrial emissions, coal combustion, biomass burning, soil dust, and traffic emissions, were identified by the positive matrix factorization model in 2019–2021. Compared to 2019, the reduction in PM2.5 from the secondary aerosol source in 2020 and 2021 was small, and the contribution of secondary aerosol to PM2.5 increased by 13.32% in 2020 and 12.94% in 2021. In comparison, the primary emissions, including biomass burning, traffic, and dust, were reduced by 29.71% in 2020 and 27.7% in 2021. The results indicated that the secondary production did not significantly contribute to the PM2.5 decrease during and after the COVID-19 restrictions. Therefore, it is essential to understand the formation of secondary aerosols under high O3 and low precursor gases to mitigate air pollution in the future. [ABSTRACT FROM AUTHOR]

This paper highlights the advantages of an affordable multi-wavelength ground-based camera, called WaltRCam, for monitoring Aerosol Optical Depth (AOD) in a clear case over a peri-urban area. To simulate the performance of this low-cost camera, for which data are not yet available, we use data from an expensive hyperspectral camera (HSI) to mimic its characteristics. Our methodology is based on the construction of look-up tables using the DART (Discrete Anisotropic Radiative Transfer) 3D radiative transfer model. DART simulates the different spectra observed by the WaltRCam camera, which then provides the AODs for all image pixels in near-real-time. Moreover, DART is coupled to a 3D scale-model of the city of Toulouse (dating from 2014) to model complex urban geometries and to associate specific optical properties to the various objects that make up the environment. Moreover, we use a neural-network-based method to recognize the various objects in the image in order to take into account only pixels common between the observations. In this way, we take account of changes to the peri-urban area, such as vegetation growth, construction, demolition of buildings, etc. The results of this study show that the WaltRCam camera, by capturing eight wavelengths, can deliver convincing results compared with ground and satellite reference data, with a correlation coefficient of 0.9 and an average RMSE of less than 0.02. [ABSTRACT FROM AUTHOR]

The profound impacts of severe air pollution on human health, ecological balance, and economic stability are undeniable. Precise air quality forecasting stands as a crucial necessity, enabling governmental bodies and vulnerable communities to proactively take essential measures to reduce exposure to detrimental pollutants. Previous research has primarily focused on predicting air quality using only time-series data. However, the importance of remote-sensing image data has received limited attention. This paper proposes a new multi-modal deep-learning model, Res-GCN, which integrates high spatial resolution remote-sensing images and time-series air quality data from multiple stations to forecast future air quality. Res-GCN employs two deep-learning networks, one utilizing the residual network to extract hidden visual information from remote-sensing images, and another using a dynamic spatio-temporal graph convolution network to capture spatio-temporal information from time-series data. By extracting features from two different modalities, improved predictive performance can be achieved. To demonstrate the effectiveness of the proposed model, experiments were conducted on two real-world datasets. The results show that the Res-GCN model effectively extracts multi-modal features, significantly enhancing the accuracy of multi-step predictions. Compared to the best-performing baseline model, the multi-step prediction's mean absolute error, root mean square error, and mean absolute percentage error increased by approximately 6%, 7%, and 7%, respectively. [ABSTRACT FROM AUTHOR]

This review article delves into the multifaceted relationship between climate change, air quality, and respiratory health, placing a special focus on the process of particle deposition in the lungs. We discuss the capability of climate change to intensify air pollution and alter particulate matter physicochemical properties such as size, dispersion, and chemical composition. These alterations play a significant role in influencing the deposition of particles in the lungs, leading to consequential respiratory health effects. The review paper provides a broad exploration of climate change's direct and indirect role in modifying particulate air pollution features and its interaction with other air pollutants, which may change the ability of particle deposition in the lungs. In conclusion, climate change may play an important role in regulating particle deposition in the lungs by changing physicochemistry of particulate air pollution, therefore, increasing the risk of respiratory disease development. Climate change influences particle deposition in the lungs by modifying the physicochemical properties of particulate air pollution, thereby escalating the risk of respiratory disease development. It is crucial for healthcare providers to educate patients about the relationship between climate change and respiratory health. People with conditions such as asthma, COPD, and allergies must understand how changes in weather, air pollution, and allergens can exacerbate their symptoms. Instruction on understanding air quality indices and pollen predictions, along with recommendations on adapting everyday activities and medication regimens in response, is essential. [ABSTRACT FROM AUTHOR]

Urban activities, particularly vehicle traffic, are contributing significantly to environmental pollution with detrimental effects on public health. The ability to anticipate air quality in advance is critical for public authorities and the general public to plan and manage these activities, which ultimately help in minimizing the adverse impact on the environment and public health effectively. Thanks to recent advancements in Artificial Intelligence and sensor technology, forecasting air quality is possible through the consideration of various environmental factors. This paper presents our novel solution for air quality prediction and its correlation with different environmental factors and urban activities, such as traffic density. To this aim, we propose a multi-modal framework by integrating real-time data from different environmental sensors and traffic density extracted from Closed Circuit Television footage. The framework effectively addresses data inconsistencies arising from sensor and camera malfunctions within a streaming dataset. The dataset exhibits real-world complexities, including abrupt camera or station activations/deactivations, noise interference, and outliers. The proposed system tackles the challenge of predicting air quality at locations having no sensors or experiencing sensor failures by training a joint model on the data obtained from nearby stations/sensors using a Particle Swarm Optimization (PSO)-based merit fusion of the sensor data. The proposed methodology is evaluated using various variants of the LSTM model including Bi-directional LSTM, CNN-LSTM, and Convolutions LSTM (ConvLSTM) obtaining an improvement of 48%, 67%, and 173% for short-term, medium-term, and long-term periods, respectively, over the ARIMA model. [ABSTRACT FROM AUTHOR]