Using improved neural network model to analyze RSP,NOx and NO2 levels in urban air in Mong Kok,Hong Kong

As the health impact of air pollutants existing in ambient addresses much attention in recent years, forecasting of airpollutant parameters becomes an important and popular topic inenvironmental science. Airborne pollution is a serious, and willbe a major problem in Hong Kong within the next few years. InHong Kong, Respirable Suspended Particulate (RSP) and NitrogenOxides NO_x and NO₂ are major air pollutants due to thedominant diesel fuel usage by public transportation and heavyvehicles. Hence, the investigation and prediction of the influence and the tendency of these pollutants are ofsignificance to public and the city image. The multi-layerperceptron (MLP) neural network is regarded as a reliable andcost-effective method to achieve such tasks. The works presentedhere involve developing an improved neural network model, whichcombines the principal component analysis (PCA) technique and theradial basis function (RBF) network, and forecasting thepollutant levels and tendencies based in the recorded data. Inthe study, the PCA is firstly used to reduce and orthogonalizethe original input variables (data), these treated variables arethen used as new input vectors in RBF neural network modelestablished for forecasting the pollutant tendencies. Comparingwith the general neural network models, the proposed modelpossesses simpler network architecture, faster training speed,and more satisfactory predicting performance. This improvedmodel is evaluated by using hourly time series of RSP, NO_x and NO₂ concentrations collected at Mong Kok Roadside Gaseous Monitory Station in Hong Kong during the year 2000. By comparing the predicted RSP, NO_x and NO₂ concentrationswith the actual data of these pollutants recorded at the monitorystation, the effectiveness of the proposed model has been proven.Therefore, in authors' opinion, the model presented in the paper is a potential tool in forecasting air quality parameters and hasadvantages over the traditional neural network methods.     

Spatial analysis and land use regression of VOCs and NO2 in Dallas, Texas during two seasons

Passive air sampling for nitrogen dioxide (NO(2)) and select volatile organic compounds (VOCs) was conducted at 24 fire stations and a compliance monitoring site in Dallas, Texas, USA during summer 2006 and winter 2008. This ambient air monitoring network was established to assess intra-urban gradients of air pollutants to evaluate the impact of traffic and urban emissions on air quality. Ambient air monitoring and GIS data from spatially representative fire station sites were collected to assess spatial variability. Pairwise comparisons were conducted on the ambient data from the selected sites based on city section. These weeklong samples yielded NO(2) and benzene levels that were generally higher during the winter than the summer. With respect to the location within the city, the central section of Dallas was generally higher for NO(2) and benzene than north and south. Land use regression (LUR) results revealed spatial gradients in NO(2) and selected VOCs in the central and some northern areas. The process used to select spatially representative sites for air sampling and the results of analyses of coarse- and fine-scale spatial variability of air pollutants on a seasonal basis provide insights to guide future ambient air exposure studies in assessing intra-urban gradients and traffic impacts.     

基于决策树技术及在线监测的水质预测

利用北方某城市水源的水质在线监测系统,建立了基于决策树技术,具有较强可视性和实际应用,以及能预测次日源水中叶绿素水平的决策树模型.该模型将某城市水源在线监测的溶解氧和太阳辐射照度数据转换计算为每日平均标准偏差及均值,并与每日定时取样测定的叶绿素含量一起作为预测因子,通过将115组数据的前100组数据作为训练集建立预测次日叶绿素水平决策树模型,并采用后15组数据进行模型的仿真预测检验,结果只有3 d的预测出错,预测准确率达80%.并讨论了模型建立对数据的要求及解读预测规则等问题.     

Spatial variability of air pollutants in the city of Taranto, Italy and its potential impact on exposure assessment

Epidemiological studies typically use monitored air pollution data from a single station or as averaged data from several stations to estimate population exposure. In industrialized urban areas, this approach may present critical issues due to the spatial complexities of air pollutants which are emitted by different sources. This study focused on the city of Taranto, which is one of the most highly industrialized cities in southern Italy. Epidemiological studies have revealed several critical situations in this area, in terms of mortality excess and short-term health effects of air pollution. The aims of this paper are to study the variability of air pollutants in the city of Taranto and to interpret the results in relation to the applicability of the data in assessing population exposure. Meteorological and pollution data (SO2, NO2, PM10), measured simultaneously and continuously during the period 2006–2010 in five air quality stations, were analyzed. Relative and absolute spatial concentration variations were investigated by means of statistical indexes. Results show significant differences among stations. The highest correlation between stations was observed for PM10 concentrations, while critical values were found for NO2. The worst values were observed for the SO2 series. The high values of 90th percentile of differences between pairs of monitoring sites for the three pollutants index suggest that mean concentrations differ by large amounts from site to site. The overall analysis supports the hypothesis that various parts of the city are differently affected by the different emission sources, depending on meteorological conditions. In particular, analysis revealed that the influence of the industrial site may be primarily identified with the series of SO2 data which exhibit higher mean concentration values and positive correlations with wind intensity when the monitoring station is downwind from the industrial site. Results suggest evaluating the population exposure to air pollutants in industrialized cities by taking into account the possible zones of influence of different emission sources. More research is needed to identify an indicator, which ought to be a synthesis of several pollutants, and take into account the meteorological variables.     

A Wavelet-based Neural Network Model to Predict Ambient Air Pollutants’ Concentration

The present paper proposes a wavelet based recurrent neural network model to forecast one step ahead hourly, daily mean and daily maximum concentrations of ambient CO, NO₂, NO, O₃, SO₂ and PM_2.5 — the most prevalent air pollutants in urban atmosphere. The time series of each air pollutant has been decomposed into different time-scale components using maximum overlap wavelet transform (MODWT). These time-scale components were made to pass through Elman network. The number of nodes in the network was decided on the basis of the strength (power) of the corresponding input signals. The wavelet network model was then used to obtain one-step ahead forecasts for a period extending from January 2009 to June 2010. The model results for out of sample forecast are reasonably good in terms of model performance parameters such as mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), normalized mean absolute error (NMSE), index of agreement (IOA) and standard average error (SAE). The MAPE values for daily maximum concentrations of CO, NO₂, NO, O₃, SO₂ and PM2.5 were found to be 9.5%, 17.37%, 21.20%, 13.79%, 17.77% and 11.94%, respectively, at ITO, Delhi, India. Bearing in mind that the forecasts are for daily maximum concentrations tested over a long validation period, the forecast performance of the model may be considered as reasonably good. The model results demonstrate that a judicious selection of wavelet network design may be employed successfully for air quality forecasting.     

新疆绿洲城市夏季农田区对流层NO_2垂直柱浓度特征分析

2014年夏季6~8月利用地基多轴差分吸收光谱仪(MAX DOAS)在新疆绿洲城市乌鲁木齐市三道坝镇、库尔勒市西尼尔镇及博乐市84团农田区观测的NO_2垂直柱浓度(VCD)数据,结合同期的气象数据分析了NO_2VCD的变化特征。研究表明:1NO_2气体的日变化规律在乌鲁木齐市和库尔勒市农田区呈波浪式多峰特征,博乐市农田区呈明显的双峰形式,且峰值除了库尔勒市在午后外,乌鲁木齐市和博乐市均出现在早晚时段;2新疆绿洲城市农田区在夏季6月(3.327×1015molec/cm~2)的NO_2VCD最高,其次是7月(2.002×1015molec/cm~2),最低是8月(1.656×1015molec/cm2);3NO_2VCD与气温、水汽压气象要素密切相关;由于城市间地势、格局的差异,库尔勒市的NO_2浓度与风速呈显著正相关,乌鲁木齐市、博乐市的NO_2浓度与风速相关性不显著。     

集合数值预报系统在上海市空气质量预测预报中的应用研究

介绍了上海市世博环境空气质量集合数值预报系统的框架,分析了各模式在上海市空气质量预报及排放源污染贡献测算中的应用情况,提出开发多种预报手段、实施集合预报是提高城市空气质量预报准确率的发展方向。     

Air Quality Status of Visakhapatnam (India) – Indices Basis

Industrial development in Visakhapatnam is conspicuous to urban agglomeration and the city is located in a topographical bowl formed by two-hill ranges. A major portion of the city is within the bowl area wherein most of the industrial and commercial activities are existing and lies within a distance of 10 km from the shore of the Bay of Bengal. Due to the peculiar geographic location of city, wind movement is either eastern or western and is engulfed within the hill ranges. Hence, there is a possibility of buildup of air pollution levels within the city. Due to gravity of prevailing situation, air quality status of Visakhapatnam on indices basis is analyzed using a non-linear equation for variable parameters i.e. Suspended particulate matter (SPM). Sulfur dioxide (SO2) and Oxides of nitrogen (NO(x)), which are main criteria pollutants in India. For current analysis seasonal air quality data is used, which indicates SPM values in winter at most of the sites and in summer at few sites are exceeding the prescribed standards. Calculated indices reveal that, in winter as well as in summer, most of the locations experienced poor or bad air quality, which is mainly due to higher concentration of SPM and certain extent of SO2 values. Application of Oak Ridge Air Quality Index (ORAQI) type equations (non-linear) are helpful for air quality management plan in the region on long-term basis and it has been also observed that there are certain lapses of weightage assignment for individual pollutant in application.     

Estimation of the global evolution of atmospheric pollution in Salamanca (Spain) during the 1993-2001 period according to one global index (ORAQI)

The aim of this study has been to use a global index to measure the air quality in the city, apart from individual assessment of the values of the concentrations of the different pollutants. We calculated the ORAQI with the data obtained at four air-pollution monitoring stations located in the city of Salamanca over the period between 1993 and 2001. For the calculations, SO2, PM10, NO2, CO and O3 were used as the most significant pollutants for the surroundings of the monitoring stations. The evolution of this index over 9 years is reported, and the repercussion of the most characteristic pollutants of each season of the year on the ORAQI along the whole period analysed is studied. The importance of the summer pollution in the characterisation of the least polluted surroundings was observed. At the most polluted sites, a decrease in the values corresponding to winter occurs, leading the ORAQI to take similar values along the whole year. In general, taking into account the surroundings of all the monitoring stations, the quality of the air to which the inhabitants of the city of Salamanca are exposed to can be said to be good.     

Temporal and Spatial Variations in Nitrogen Dioxide Concentrations Across an Urban Landscape: Cambridge, UK

The acquisition of a comprehensive air quality dataset for a small city environment is described for use in statistical modelling of dispersion processes and micro-scale assessment of polluted zones. The dataset is based on a nitrogen dioxide diffusion tube survey for Cambridge where up to 80 roadside and background sites have been monitored continuously over two years, using a two week exposure period. Site categories are defined by their function within the urban landscape. Spatial and temporal features of the data set are explained in terms of urban location, street geometry, meteorology and traffic behaviour. The highest levels of NO2 are found in central canyon streets which are narrow with enclosing architecture and slow-moving traffic. In contrast lower levels are found for the wider, more open radial routes where traffic is free-flowing. The influence of street geometry on NO2 levels for central streets is demonstrated, where canyon sections adjacent to open sections having the same traffic flow record higher concentrations. Whilst all roadside sites are affected by a photochemical pollution 'episode', the greater potential for elevated NO2 concentrations within the canyon sections is significant. The close proximity of low background levels of NO2 to roadside 'hot-spots' is important for public exposure assessment. The variation in background levels across the urban landscape is very small and unrelated to location; whether central, suburban or outer city. Seasonal variation, not seen in roadside data, is clearly apparent in background data with a winter maximum and summer minimum.     

Minimax Statistical Models for Air Pollution Time Series. Application to Ozone Time Series Data Measured in Bordeaux

This paper deals with the application of l(infinity) (or minimax) optimization techniques to statistical modelling of high frequency air pollution data. The method was applied to ground-level ozone time-series data measured in Bordeaux over 4 years from 1998 to 2001. The aim of model building was to develop predictive models in order to provide forecasts of the maximal daily ground-level ozone concentration. Experimental results from this case study indicate that such techniques could be more appropriate than the commonly used l2 setting if only good estimation of high levels is of interest. When the free parameters are fitted by means of l(infinity) optimization techniques, the forecasting errors are more evenly distributed amongst the data points, resulting in a better estimation of high values. The paper compares the quality of forecasts produced by both a linear and a nonlinear model, using l2 and l(infinity) parameter optimization.     

Analysis of the air pollution climate at a background site in the Po valley

The Po valley in northern Italy is renowned for its high air pollutant concentrations. Measurements of air pollutants from a background site in Modena, a town of 200 thousand inhabitants within the Po valley, are analysed. These comprise hourly data for CO, NO, NO(2), NO(x), and O(3), and daily gravimetric equivalent data for PM(10) from 1998-2010. The data are analysed in terms of long-term trends, annual, weekly and diurnal cycles, and auto-correlation and cross-correlation functions. CO, NO and NO(2) exhibit a strongly traffic-related pattern, with daily peaks at morning and evening rush hour and lower concentrations over the weekend. Ozone shows an annual cycle with a peak in July due to local production; notwithstanding the diurnal cycle dominated by titration by nitrogen oxide, the decreasing long term trend in NO concentration did not affect the long term trend in O(3), whose mean concentration remained steady over the sampling period. PM(10) shows a strong seasonality with higher concentration in winter and lower concentration in summer and spring. Both PM(10) and ozone show a marked weekly cycle in summer and winter respectively. Regressions of PM(10) upon NO(x) show a consistently greater intercept in winter, representing higher secondary PM(10) in the cooler months of the year. There is a seasonal pattern in primary PM(10) to NO(x) ratios, with lower values in winter and higher values in summer, but the reasons are unclear.     

Can we document if regulation and Best Available Techniques (BAT) have any positive impact on the marine environment? A case based on a steel mill in Greece

In order to document the impact of Best Available Techniques (BAT) and implementation of regulation on the improvement of the coastal marine environment state, we examined the case of a representative steel mill located at the Gulf of Elefsis (Greece). The evaluation of metal pollution was based on the analysis of major and trace elements, organic carbon, magnetic properties, and sediment accumulation rates, in sediment cores obtained from the vicinity of the plant. The analytical data are discussed in relation to steel production, changes of production routes, and adoption of BAT introduced in order to fulfill EU and national legislation. The results show that the input of pollutants to sediments and the degree of contamination were reduced by approximately 40–70% in the decade 2003–2015 in comparison to the periods of high discharges (1963–2002), whereas the toxicity risks from “high-to-extremely high” were reduced to “medium-to-high.”     

Spatial concentration distributions of sulfur dioxide and nitrogen oxides in Patras, Greece, in a winter period

An economic and quick methodology for performing a preliminary spatial assessment of a city air quality with the purpose to identify locations and zones susceptible to high pollution levels is proposed. A Patras case-study is selected, regarding the air pollutants of sulfur dioxide (SO₂) and oxides of nitrogen (NO_x). A total number of 451 samples of short duration, of which 225 were randomly picked in morning rush hours and 226 within evening rush hours, were collected from 50 locations of the major Patras area during a year period, when peaks of primary air pollutants usually occur. Concentration measurements at prescribed locations used to statistically calculate spatial average concentrations approximating 1-h mean values with mean probable errors less than 25.9% for SO₂, NO and NO_x and less than 15.5% for NO₂. Then iso-concentration contour diagrams plotted indicate high pollution zones and possibly appropriate locations for continuous or random monitoring according to the European Community (EC) Directives. The 1-h mean concentrations were in good correlation to the corresponding traffic rates and useful relationships are given (0.54 ≤ r ≤ 0.63). In addition, comparisons with data available for other cities, as well as with the limit and guide values provided by the EC and the World Health Organization (WHO) were given. The present data could be useful for the design and optimization of a city network of stations for monitoring air quality, for environmental impact assessments, future reference and comparisons due to city development needs, as well as for validating dispersion models.     

Sixteen-year air quality data analysis of a high environmental risk area in Southern Italy

The Brindisi area is characterized by the presence of industries with high environmental impact, located along its eastern border. Epidemiological studies have revealed several critical situations: two short-term (2003-2005) epidemiological studies have shown that PM(10) and NO(2) are adversely associated with daily hospital admissions: one of the two pointed to the associations with wind blowing from the southern, eastern and western sectors. This study aims to expand the time span of available air quality data in order to provide a more complete and extensive epidemiological study. Multi-year series (from 1992 to 2007) of SO(2), NO(2), and TSP concentration data are presented and analyzed. Data show a significant downward trend of SO(2) from 1992 to 2007, while for the TSP series, the downward trend is limited to the period 1992-1994. Marked seasonal trends are evident for all three pollutants, especially for NO(2) and TSP. The NO(2) series shows higher levels in winter. Inversely, the TSP series shows its maximum values during the summer months, associated with a moderate correlation with temperature and a poor correlation with other pollutants. Analysis of the series for wind sectors revealed the influence of the industrial site and of the harbor. The concentration series exhibit high concentration values and stronger correlations between them and with meteorology for wind blowing from the eastern sectors. Overall analysis supports the hypothesis of a different origin for TSP during the year and for different wind regimes and therefore possible size and chemical differences in TSP, which should be further investigated due to their health implications.     

2016年秋季新乡市空气质量模式预报效果评估

基于新乡市空气质量数值预报平台,采用相关系数（r）、标准化平均偏差（NMB）等统计指标,系统评估2016年秋季新乡市嵌套网格空气质量预报模式（NAQPMS）和通用多尺度空气质量模式（CMAQ）的预报效果,对比分析2套模式不同预报时效和不同水平分辨率的空气质量等级预报准确率。结果显示：2套模式均较好地表征了各主要污染物的浓度变化特征,2套模式的等级预报准确率高于60%,其中CMAQ对中度及重度的预报等级准确率达到70%。对比模式24、48、72 h 3种预报时效效果,24 h预报时效的统计数据最优,说明24 h预报时效模拟结果可作为业务预报重要的支撑。     

Artificial neural network based carbon monoxide persistence models for episodic urban air quality management

This paper describes the development of artificial neural network (ANN) based carbon monoxide (CO) persistence (ANNCOP) models to forecast 8-h average CO concentration using 1-h maximum predicted CO data for the critical (winter) period (November–March). The models have been developed for three 8-h groupings of 10 p.m. to 6 a.m., 6 a.m. to 2 p.m. and 2–10 p.m., at two air quality control regions (AQCRs) in Delhi city, representing an urban intersection and an arterial road consisting heterogeneous traffic flows. The result indicates that time grouping of 2–10 pm is dominantly affected by inversion conditions and peak traffic flow. The ANNCOP model corresponding to this grouping predicts the 8-h average CO concentrations within the accuracy range of 68–71%. The CO persistence values derived from ANNCOP model are comparable with the persistence values as suggested by the Environmental Protection Agency (EPA), USA. This work demonstrates that ANN based model is capable of describing winter period CO persistence phenomena.     

基于深度学习的空气质量预报方法新进展

空气质量预报与人们的日常生活密切相关,其基本思想是分析历史空气质量数据,发现其内在的时空相关性,结合未来气象信息以及污染源排放量,对未来的空气质量进行预测。目前,环境管理和社会公众服务对空气质量预报提出了长时间、多维度、高精度的预测要求,一些新型的空气质量预测方法仍处于起步探索阶段。近年来,随着人工智能的普及与推广(特别是云计算与大数据的发展),深度学习这项基于传统人工神经网络的技术被国内外研究者所重视。笔者对现有典型的空气质量预报方法进行了阐述,包括数值预测模型方法、统计预报模型方法、基于机器学习模型的预测方法等,并重点介绍了该领域最新进展:基于深度学习模型的预测方法,并在此基础上进行了总结与展望。     

Development of low-cost ammonia gas sensors and data analysis algorithms to implement a monitoring grid of urban environmental pollutants

The present study is focused on the implementation of a novel, low cost, urban grid of nanostructured chemresistor gas sensors for ammonia concentration ([NH(3)]) monitoring, with NH(3) being one of the main precursors of secondary fine particulate. Low-cost chemresistor gas sensors based on carbon nanotubes have been developed, their response to [NH(3)] in the 0.17-5.0 ppm range has been tested, and the devices have been properly calibrated under different relative humidity conditions in the 33-63% range. In order to improve the chemresistor selectivity towards [NH(3)], an Expert System, based on fuzzy logic and genetic algorithms, has been developed to extract the atmospheric [NH(3)] (with a sensitivity of a few ppb) from the output signal of a model chemresistor gas sensor exposed to an NO(2), NO(X) and O(3) gas mixture. The concentration of these pollutants that are known to be the most significant interfering compounds during ammonia detection with carbon nanotube gas sensors has been tracked by the ARPA monitoring network in the city of Milan and the historical dataset collected over one year has been used to train the Expert System.     

Water quality monitoring and assessment of an urban Mediterranean lake facilitated by remote sensing applications

Degradation of water quality is a major problem worldwide and often leads to serious environmental impacts and concerns about public health. In this study, the water quality monitoring and assessment of the Koumoundourou Lake, a brackish urban shallow lake located in the northeastern part of Elefsis Bay (Greece), were evaluated. A number of water quality parameters (pH, temperature, dissolved oxygen concentration, electrical conductivity, turbidity, nutrients, and chlorophyll-a concentration) were analyzed in water samples collected bimonthly over a 1-year period from five stations throughout the lake. Moreover, biological quality elements were analysed seasonally over the 1-year period (benthic fauna). Statistical analysis was performed in order to evaluate the water quality of the lake and distinguish sources of variation measured in the samples. Furthermore, the chemical and trophic status of the lake was evaluated according to the most widely applicable classification schemes. Satellite images of Landsat 5 Thematic Mapper were used in order for algorithms to be developed and calculate the concentration of chlorophyll-a (Chl-a). The trophic status of the lake was characterized as oligotrophic based on phosphorus and as mesotrophic–eutrophic based on Chl-a concentrations. The results of the remote sensing application indicated a relatively high coefficient of determination (R ²) among point sampling results and the remotely sensed data, which implies that the selected algorithm is reliable and could be used for the monitoring of Chl-a concentration in the particular water body when no field data are available.