Hybrid Model for Urban Air Pollution Forecasting: A Stochastic Spatio-Temporal Approach

Air pollution is usually driven by a complex combination of factors in which meteorology, physical obstacles, and interactions between pollutants play significant roles. Considering the characteristics of urban atmospheric pollution and its consequent impacts on human health and quality of life, forecasting models have emerged as an effective tool to identify and forecast air pollution episodes. The overall objective of the present work is to produce forecasts of pollutant concentrations with high spatio-temporal resolution and to quantify the uncertainty in those forecasts. Therefore, a new approach was developed based on a two-step methodology. Firstly, neural network models were used to generate short-term temporal forecasts based on air pollution and meteorology data. The accuracy of those forecasts was then evaluated against an independent set of historical data. Secondly, local conditional distributions of the observed values with respect to the predicted values were used to perform spatial stochastic simulations for the entire geographic area of interest. With this approach the spatio-temporal dispersion of a pollutant can be predicted, while accounting for both the temporal uncertainty in the forecast (reflecting the neural networks efficiency at each monitoring station) and the spatial uncertainty as revealed by the spatial variograms. Based on an analysis of the results, our proposed method offers a highly promising alternative for the characterization of urban air quality.     

Design of an environmental assessment model on the effect of vehicle emission in greater Tehran on air pollution with economic sensitivity

Air pollution is the presence of pollutants in the atmosphere from anthropogenic or natural substances in quantities likely to harm human, plant or animal life; to damage human-made materials and structures; to bring about changes in weather or climate; or to interfere with enjoyment of life or property. With regard to the quality of air in most of the megacities of the world, vehicular air pollution plays an important role in deteriorating air quality. Air pollution in Tehran (Capital of the Islamic Republic of Iran) occurs in highly urbanized areas due to mobile anthropogenic sources which in-turn is hastened by unfavorable tohion sector is responsible for much of urban air pollution and can result in high ambient concentrations that harm people, structures, and environment. This paper examines and estimates the tonnage, concentrations and impacts of air pollutants along with control measures aimed at reducing the effect of pollutants released by transportation navigation, in Tehran.     

Impacts of climate change on stream flow and water quality in a drinking water source area,Northern China

Understanding the impacts of climate change on water quality and stream flow is important for management of water resources and environment. Miyun Reservoir is the only surface drinking water source in Beijing, which is currently experiencing a serious water shortage. Therefore, it is vital to identify the impacts of climate change on water quality and quantity of the Miyun Reservoir watershed. Based on long-time-series data of meteorological observation, future climate change scenarios for this study area were predicted using global climate models (GCMs), the statistical downscaling model (SDSM), and the National Climate Centre/Gothenburg University—Weather Generator (NWG). Future trends of nonpoint source pollution load were estimated and the response of nonpoint pollution to climate change was determined using the Soil and Water Assessment Tool (SWAT) model. Results showed that the simulation results of SWAT model were reasonable in this study area. The comparative analysis of precipitation and air temperature simulated using the SDSM and NWG separately showed that both tools have similar results, but the former had a larger variability of simulation results than the latter. With respect to simulation variance, the NWG has certain advantages in the numerical simulation of precipitation, but the SDSM is superior in simulating precipitation and air temperature changes. The changes in future precipitation and air temperature under different climate scenarios occur basically in the same way, that is, an overall increase is estimated. Particularly, future precipitation will increase significantly as predicted. Due to the influence of climate change, discharge, total nitrogen (TN) and total phosphorus (TP) loads from the study area will increase over the next 30 years by model evaluation. Compared to average value of 1961?~?1990, discharge will experience the highest increase (15%), whereas TN and TP loads will experience a smaller increase with a greater range of annual fluctuations of 2021 ~ 2050.     

Air Quality as a Meteorological Hazard

Meteorological hazards are usually considered to be tropical cyclones, droughts, hail-storms, severe storms and their effects such as tsunamis, storm surges, wildfire, and floods. Urban air pollution is not normally considered to be a meteorological hazard. This view has arisen because the causes of urban air pollution – industrial and motor vehicleemissions – are not meteorological in nature. Air pollution episodes, however, are sporadic in nature and their occurrence depends on a particular combination of meteorological factors. This is true even in megacities such as Mexico City, Manila, and Los Angeles that have acquired a reputation for polluted air. Analyses of air pollution episodes and hospital admissions from many countries indicate that thereis a significant increase in morbidity and mortality as a result of such episodes.Time-series studies undertaken in Sydney have shown that particulate matter, ozone and nitrogen dioxide are the pollutants that are primarily responsible for adverse health effects in that city.Air pollution, and in particular particulate matter, is believed to be responsible for just under 400 premature deaths per year in Sydney alone. This death rate is over twenty times larger than deaths due to other meteorological hazards. Part of the reason for the low death rate for the more traditional meteorological hazards is that the provision of high quality numerical weather prediction, coupled with modern communications technology, has enabled emergency service personnel to take appropriate action.Air quality forecasting systems can play an important role in mitigating the adverse effects of air pollution. The forecasts will affect the behaviour of susceptible individuals, and thus reduce adverse health effects. The outputs from forecasting systems can also be used to provide improved estimates of the total exposure to air pollutants of the inhabitants who areat risk. Such improved estimates can then be used in conjunction with longitudinal studies ofhealth effects to obtain better understanding of the complex interaction between air quality and health.     

Predicting twenty-first century recession of architectural limestone in European cities

Cities of the twenty-first century will expose buildings to environments that are quite different from those experienced over preceding periods. The recent reduction in sulfur dioxide in cities and continued pressure to lower the emissions of combustion generated pollutants creates a potential for climate induced deterioration, by contrast, to be more important. Given that climate will likely change over the next hundred years, recession rates of calcareous stones have been predicted for Oviedo (Spain), Paris and Prague over the period 1981–2099. This can give guidance as to the likely change in balance of future threat. The Lipfert, ICP, and MULTI-ASSESS functions were used to calculate recession from estimates of climate and air quality. It is likely that under a continued decline or stable levels of pollution, recession rates having reached low values will remain largely unchanged over the coming century, despite likely changes in climate. Although the functions adopted disagree in a quantitative sense, there is evidence that they were reasonably concordant in the last decades of the twentieth century. In a cleaner future their different underlying assumptions lead to poorer agreement.     

基于改进的数量化理论和RBF神经网络组合方法的地下水水质预测

文中首先运用了一种改进的数量化理论I模型作为预处理工具,对影响地下水水质的20个因子进行定性数据转换、数据降维,随后将8个重要特征因子作为RBF（径向基函数）神经网络模型的输入,进一步对监测井的采样数据进行学习、训练,揭示地下水污染质迁移转化规律。尝试用经过改进的数量化理论与RBF神经网络方法二者结合,对沈阳李官水源地研究区监测井地下水水质变化进行模拟与预测,其仿真结果覆盖了现有的绝大部分实测数据,适用范围广泛,具有一定的推广价值。     

二维随机场下边坡稳定性的径向基函数神经网络分析法

岩土参数的随机性会直接影响边坡稳定性评价结果的精度。首先,依据边坡参数的常用分布特征,利用拉丁超立方抽样法生成若干组边坡土性参数和几何参数的随机样本,用有限元强度折减法求解各组样本对应的边坡安全系数。再考虑土性参数的空间变异性,在二维随机场模型下将蒙特卡罗模拟和有限元强度折减法相结合求解各组样本对应的边坡失效概率。然后,利用样本数据及其安全系数和失效概率对径向基函数（RBF）神经网络进行训练和测试,从而建立边坡安全系数和失效概率的预测模型。算例表明,二维随机场模型能相对精确地考虑参数的空间变异性;在此基础上建立的神经网络模型对边坡的安全系数和失效概率具有较高的预测精度,且能极大地节省边坡稳定性分析的时间。     

Understanding the spatial representativeness of air quality monitoring network and its application to PM2.5 in the mainland China

Air pollution has seriously endangered human health and the natural ecosystem during the last decades. Air quality monitoring stations (AQMS) have played a critical role in providing valuable data sets for recording regional air pollutants. The spatial representativeness of AQMS is a critical parameter when choosing the location of stations and assessing effects on the population to long-term exposure to air pollution. In this paper, we proposed a methodological framework for assessing the spatial representativeness of the regional air quality monitoring network and applied it to ground-based PM_2.5 observation in the mainland of China. Weighted multidimensional Euclidean distance between each pixel and the stations was used to determine the representativeness of the existing monitoring network. In addition, the K-means clustering method was adopted to improve the spatial representativeness of the existing AQMS. The results showed that there were obvious differences among the representative area of 1820 stations in the mainland of China. The monitoring stations could well represent the PM_2.5 spatial distribution of the entire region, and the effectively represented area (i.e. the area where the Euclidean distance between the pixels and the stations was lower than the average value) accounted for 67.32% of the total area and covered 93.12% of the population. Forty additional stations were identified in the Northwest, North China, and Northeast regions, which could improve the spatial representativeness by 14.31%.     

Spatial and temporal analyses of air pollutants and meteorological driving forces in Beijing–Tianjin–Hebei region,China

Due to its negative impact on the living environment of human beings, ambient air pollution has become a global challenge to human health. In this study, surface observations of six criteria air pollutants, including PM_2.5, PM₁₀, SO₂, NO₂, CO and O₃, were collected to investigate the spatial and temporal variation in the Beijing–Tianjin–Hebei (BTH) region during 2013–2016 and to explore the relationships between atmospheric pollutants and meteorological variables using quantile regression model (QRM) and multiple linear regression model (MLRM). The results show that BTH region has experienced significant air pollution, and the southern part generally has more severe conditions. The annual average indicates clear decreasing trends of the particulate matters, SO₂ and CO concentrations over the last 4 years and slight increasing trends of NO₂ and O₃ in several cities. The seasonal and monthly characteristics indicate that the concentrations of five species reach their maxima in the winter and their minima in the summer, whereas O₃ has the opposite behaviour. Finally, the pseudo R² values show that the QRMs have the best performance in the winter, followed by spring, fall, and summer. Specifically, all the meteorological factors have significant impacts on air pollution but change with pollutants and seasons. The MLRM results are generally consistent with the QRM results in all seasons, and the inconsistencies are more common in the fall and winter. The results of this research provide foundational knowledge for predicting the response of air quality to climate change in the BTH region.     

典型降水预报ANN多指标优选——以太湖湖西区为例

为提高多种典型人工神经网络应用于降水预报的精度与稳定性并做出优选,对太湖流域湖西区丹徒、丹阳、金坛、溧阳、宜兴5站的年降水量时间序列建立基于组成成分分析的人工神经网络模型,并通过平均相对误差、平均绝对误差、均方根误差及合格率4项评价指标对比分析预报效果。该模型采用Mann-Kendall法、秩和检验法、谱分析法进行组成成分分析;建立BP网络、小波神经网络、RBF网络、GRNN网络及Elman网络模拟并预测随机成分,与确定性成分叠加得年降水量预报结果。在湖西区的研究结果表明,基于组成成分分析的人工神经网络模型的拟合及预测精度高于原始人工神经网络和线性自回归模型,GRNN网络的预测精度与稳定性高于其他4类神经网络。     

径向基神经网络在地面沉降预测中的应用

基于MATLAB6.5平台编程,利用前四年的沉降量作为输入神经元,后一年的沉降量作为输出神经元,重复此过程,构建了上海高桥地区地面沉降预测径向基神经网络.以历史沉降数据为训练样本,并对其进行归一化处理,在此基础上,采用未归一化及归一化后的训练样本进行网络训练与检验.结果表明,归一化后的训练样本训练得到的径向基网络具有良好的预测性能.最后利用该网络对1990-2010年的地面沉降量进行了预测.     

Assessment of spatial variations of particulate matter (PM<Subscript>10</Subscript> and PM<Subscript>2.5</Subscript>) in Bahrain identified by air quality index (AQI)

The rapid urbanization, industrialization, modernization, and the frequent Middle Eastern dust storms have negatively impacted the ambient air quality in Bahrain. The objective of this study is to identify the most critical atmospheric air pollutants with emphasis on their potential risk to health based on calculated AQI (air quality index) values using EPA approach. The air quality datasets of particulate matters (PM₁₀ and PM_2.5), ozone (O₃), sulfur dioxide (SO₂), nitrogen dioxide (NO₂), and carbon monoxide (CO) were measured in January 2012 and August 2012 using five mobile air quality monitoring stations located at different governorates. The results of this study demonstrated that PM₁₀ and PM_2.5 are the most critical air pollutants in Bahrain with PM_2.5 prevailing during January 2012 and PM₁₀ prevailing during August 2012. The corresponding AQI categories were utilized to evaluate spatial variability of particulate matters in five governorates. The impact of meteorological factors such as ambient air temperature, wind speed, relative humidity, and total precipitation on ambient air quality were discussed. The analysis demonstrated that the highest PM₁₀ concentrations were observed in the Northern Governorate while the highest PM_2.5 concentrations were observed in the Capital, Central, and Northern Governorates during August 2012. It was observed that the levels of PM_2.5 pollution were higher within proximity of the industrial zone. The results suggested that the average PM_2.5/PM₁₀ ratio in August 2012 was lower than in January 2012 due to the Aeolian processes. This study concludes that higher wind speed, total precipitation, relative humidity rates, and lower ambient air temperature in January 2012 assisted with the dissipation of particulate matter thus lowering the pollution levels of both PM₁₀ and PM_2.5 in comparison to August 2012.     

Influence of transboundary air pollution on air quality in southwestern China

Air pollution is a grand challenge of our time due to its multitude of adverse impacts on environment and society,with the scale of impacts more severe in developing countries,including China.Thus,China has initiated and implemented strict air pollution control measures over last several years to reduce impacts of air pollution.Monitoring data from Jan 2015 to Dec 2019 on six criteria air pollutants(SO2,NO2,CO,O3,PM2.5,and PM1o)at eight sites in southwestern China were investigated to understand the situation and analyze the impacts of transboundary air pollutants in this region.In terms of seasonal variation,the maximum concentrations of air pollutants at these sites were observed in winter or spring season depending on individual site.For diurnal variation,surface ozone peaked in the afternoon while the other pollutants had a bimodal pattern with peaks in the morning and late afternoon.There was limited trans-port of domestic emissions of air pollutants in China to these sites.Local emissions enhanced the concen-trations of air pollutants during some pollution events.Mostly,the transboundary transport of air pollution from South Asia and Southeast Asia was associated with high concentrations of most air pollu-tants observed in southwestern China.Since air pollutants can be transported to southwestern China over long distances from the source regions,it is necessary to conduct more research to properly attribute and quantify transboundary transport of air pollutants,which will provide more solid scientific guidance for air pollution management in southwestern China.     

Nowcasting visibility during wintertime fog over the airport of a metropolis of India: decision tree algorithm and artificial neural network approach

Natural Hazards - The endeavor of the present research is to nowcast the spatial visibility during fog over the airport of Kolkata (22.6°N; 88.4°E), India, with artificial neural network...     

Assessing the possible impacts of temperature change on air quality and public health in Beijing, 2008–2012

Understanding the impact of temperature fluctuations on air quality and public health has gained popularity among environmental and epidemiological researchers. Potentially, increase and decrease in temperature between neighboring days have increased the environmental and health risk worldwide. Based on ordinary least-squares method, this paper aims to examine the impact of temperature fluctuations on air quality index (AQI) and respiratory health outcomes (RHOs) during 2008–2012 in Beijing. Our results show that a drop of more than 3 °C results in the increased impact on AQI and RHO in the heating period. At the same time, a raise of more than 3 °C results in the similar increased impact on AQI in the whole study period and heating period. Furthermore, for a raise of more than 3 °C, a larger impact on RHO is observed in the heating period compared with the whole study period. Additionally, an increase in temperature also results in the increased influence of health risk on females during the heating period. Our results suggest that the air quality and public health in Beijing are significantly influenced by decrease and increase in temperature in the heating period.

     

Medium-range forecast of cyclogenesis over North Indian Ocean with multilayer perceptron model using satellite data

An attempt is made in this study to develop a model to forecast the cyclonic depressions leading to cyclonic storms over North Indian Ocean (NIO) with 3 days lead time. A multilayer perceptron (MLP) model is developed for the purpose and the forecast quality of the model is compared with other neural network and multiple linear regression models to assess the forecast skill and performances of the MLP model. The input matrix of the model is prepared with the data of cloud coverage, cloud top temperature, cloud top pressure, cloud optical depth, cloud water path collected from remotely sensed moderate resolution imaging spectro-radiometer (MODIS), and sea surface temperature. The input data are collected 3 days before the cyclogenesis over NIO. The target output is the central pressure, pressure drop, wind speed, and sea surface temperature associated with cyclogenesis over NIO. The models are trained with the data and records from 1998 to 2008. The result of the study reveals that the forecast error with MLP model varies between 0 and 7.2 % for target outputs. The errors with MLP are less than radial basis function network, generalized regression neural network, linear neural network where the errors vary between 0 and 8.4 %, 0.3 and 24.8 %, and 0.3 and 32.4 %, respectively. The forecast with conventional statistical multiple linear regression model, on the other hand, generates error values between 15.9 and 32.4 %. The performances of the models are validated for the cyclonic storms of 2009, 2010, and 2011. The forecast errors with MLP model during validation are also observed to be minimum.     

焦作地区浅层地下水铬(Ⅵ)污染机理及迁移预测

通过对焦作地区浅层地下水中铬(Ⅵ)污染物分布特征进行调查,分析了研究区浅层地下水中铬(Ⅵ)的污染机理,并运用Visual MODFLOW建立地下水流模型及溶质运移模型,模拟预测了浅层地下水中铬(Ⅵ)的迁移规律。结果表明:研究区浅层地下水铬(Ⅵ)污染严重,污染源是位于老君庙西南方向的焦作某电厂堆灰场,主要原因是露天堆放的粉煤灰中的铬(Ⅵ)污染物在长期淋滤作用下下渗污染含水层。气候条件、包气带岩性、地下水化学环境以及人为因素等也间接使浅层地下水铬(Ⅵ)浓度升高;模拟结果显示在未来的五年时间内,受地形和地下水动力场的影响,浅层地下水中铬(Ⅵ)的迁移方向与地下径流方向一致,沿大沙河水流方向上扩散速度更快,污染区域面积逐渐增大。      

COVID-19 strict lockdown impact on urban air quality and atmospheric temperature in four megacities of India

COVID-19 pandemic has forced to lockdown entire India starting from 24th March 2020 to 14th April 2020 (first phase), extended up to 3rd May 2020 (second phase), and further extended up to 17th May 2020 (third phase) with limited relaxation in non-hotspot areas. This strict lockdown has severely curtailed human activity across India. Here, aerosol concentrations of particular matters (PM) i.e., PM₁₀, PM_2.5, carbon monoxide (CO), nitrogen dioxide (NO₂), sulphur dioxide (SO₂), ammonia (NH₃) and ozone (O₃), and associated temperature fluctuation in four megacities (Delhi, Mumbai, Kolkata, and Chennai) from different regions of India were investigated. In this pandemic period, air temperature of Delhi, Kolkata, Mumbai and Chennai has decreased about 3 °C, 2.5 °C, 2 °C and 2 °C respectively. Compared to previous years and pre-lockdown period, air pollutants level and aerosol concentration (?41.91%, ?37.13%, ?54.94% and ?46.79% respectively for Delhi, Mumbai, Kolkata and Chennai) in these four megacities has improved drastically during this lockdown period. Emission of PM_2.5 has experienced the highest decrease in these megacities, which directly shows the positive impact of restricted vehicular movement. Restricted emissions produce encouraging results in terms of urban air quality and temperature, which may encourage policymakers to consider it in terms of environmental sustainability.     

A comparative analysis among computational intelligence techniques for dissolved oxygen prediction in Delaware River

Most of the water quality models previously developed and used in dissolved oxygen (DO) prediction are complex. Moreover, reliable data available to develop/calibrate new DO models is scarce. Therefore, there is a need to study and develop models that can handle easily measurable parameters of a particular site, even with short length. In recent decades, computational intelligence techniques, as effective approaches for predicting complicated and significant indicator of the state of aquatic ecosystems such as DO, have created a great change in predictions. In this study, three different AI methods comprising: (1) two types of artificial neural networks (ANN) namely multi linear perceptron (MLP) and radial based function (RBF); (2) an advancement of genetic programming namely linear genetic programming (LGP); and (3) a support vector machine (SVM) technique were used for DO prediction in Delaware River located at Trenton, USA. For evaluating the performance of the proposed models, root mean square error (RMSE), Nash–Sutcliffe efficiency coefficient (NS), mean absolute relative error (MARE) and, correlation coefficient statistics (R) were used to choose the best predictive model. The comparison of estimation accuracies of various intelligence models illustrated that the SVM was able to develop the most accurate model in DO estimation in comparison to other models. Also, it was found that the LGP model performs better than the both ANNs models. For example, the determination coefficient was 0.99 for the best SVM model, while it was 0.96, 0.91 and 0.81 for the best LGP, MLP and RBF models, respectively. In general, the results indicated that an SVM model could be employed satisfactorily in DO estimation.     

Surface air temperature changes over the Tibetan Plateau: Historical evaluation and future projection based on CMIP6 models

With its amplification simultaneously emerging in cryospheric regions, especially in the Tibetan Plateau, global warming is undoubtedly occurring. In this study, we utilized 28 global climate models to assess model performance regarding surface air temperature over the Tibetan Plateau from 1961 to 2014, reported spatiotemporal variability in surface air temperature in the future under four scenarios (SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5), and further quantified the timing of warming levels (1.5, 2, and 3 °C) in the region. The results show that the multimodel ensemble means depicted the spatiotemporal patterns of surface air temperature for the past decades well, although with differences across individual models. The projected surface air temperature, by 2099, would warm by 1.9, 3.2, 5.2, and 6.3 °C relative to the reference period (1981–2010), with increasing rates of 0.11, 0.31, 0.53, and 0.70 °C/decade under the SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5 scenarios for the period 2015–2099, respectively. Compared with the preindustrial periods (1850–1900), the mean annual surface air temperature over the Tibetan Plateau has hit the 1.5 °C threshold and will break 2 °C in the next decade, but there is still a chance to limit the temperature below 3 °C in this century. Our study provides a new understanding of climate warming in high mountain areas and implies the urgent need to achieve carbon neutrality.