Feed-Forward Artificial Neural Network Model for Air Pollutant Index Prediction in the Southern Region of Peninsular Malaysia

This paper describes the application of principal component analysis (PCA) and artificial neural network (ANN) to predict the air pollutant index (API) within the seven selected Malaysian air monitoring stations in the southern region of Peninsular Malaysia based on seven years database (2005-2011). Feed-forward ANN was used as a prediction method. The feed-forward ANN analysis demonstrated that the rotated principal component scores (RPCs) were the best input parameters to predict API. From the 4 RPCs, only 10 (CO, O3, PM10, NO2, CH4, NmHC, THC, wind direction, humidity and ambient temp) out of 12 prediction variables were the most significant parameters to predict API. The results proved that the ANN method can be applied successfully as tools for decision making and problem solving for better atmospheric management.

Statistical Air Pollution Index (API) for Trinidad and Tobago Based on Observed Data on Trinidad’s West Coast

Air pollution has been identified as the largest global environmental threat facing the world today, estimated to cause 7 - 10 million deaths worldwide annually (World Health Organisation, 2014, 2016;Yale University, 2018). Trinidad and Tobago, with a per capita GDP of USD$16310 (2019), is the most industrialised of the Caribbean islands, and like the rest of the Caribbean region is also affected by seasonal Sahara dust (PM2.5). Assessment of the air quality was done for over Trinidad’s west coast. Pollution was measured at four stations during March ‘15-May ‘16, representative of rural, urban, mixed background and industrial land uses. Annual mean PM2.5 and PM10 in ambient air exceeded the WHO guidelines for protection of public health (n = 522). PM2.5 and PM10 exceed the WHO (2006) safe limit guidelines (PM2.5 is 10 μg/m3;PM10 is 20 μg/m3) over 70% of the time sampled at urban and industrial sites. Gaseous pollutants found to be in exceedance were CO, NH3, NO2, N2O, C6H6. Nitrogen dioxide and benzene were the most prolific. A collated metric based on measurement of these pollutants yielded a statistically validated algorithm—An Air Pollution Index. The single metric can convey useful and easily understood information on air quality to the regulators and the general public.

Relationship between Air Pollution Index (API) and Crowd Health in Nanchang City

Objective: To explore the effect of Air Pollution Index (API) on people’s health. Methods: The data on air pollution index (API), NO2, SO2 and PM10 were based on the everyday monitoring information from environmental monitoring station of Nanchang City. The everyday outpatient service diseases information of 2005 related to air pollution from some First Level Hospitals in Nanchang city was collected, and was summarized and analyzed by statistics software of Excel 2003 and SPSS11.5. Results: The average concentrations of NO2, SO2 and PM10 in the air of Nanchang city from 2006-2009 were 19.70 ± 8.56 μg/m3, 44.60 ± 10.45 μg/m3, 62.30 ± 19.76 μg/m3 respectively. Tight relationship was detected between NO2, SO2 and PM10. Air pollution index (API) can better reflect the air pollution status of Nanchang city. There were positive correlations between API and number of outpatient service diseases, including cardiovascular disease, respiratory disease, ophthalmology disease and ear-nose-throat (ENT) disease in Nanchang city. Conclusion API was related to the number of outpatient service relative diseases.

Time Series Analysis and Forecasting of the Air Quality Index of Atmospheric Air Pollutants in Zahleh, Lebanon

During the last decades, air pollution has become a serious environmental hazard. Its impact on public health and safety, as well as on the ecosystem, has been dramatic. Forecasting the levels of air pollution to maintain the climatic conditions and environmental protection becomes crucial for government authorities to develop strategies for the prevention of pollution. This study aims to evaluate the atmospheric air pollution of the city of Zahleh located in the geographic zone of Bekaa. The study aims to determine a relationship between variations in ambient particulate concentrations during a short time. The data was collected from June 2017 to June 2018. In order to predict the Air Quality Index (AQI), Naïve, Exponential Smoothing, TBATS (a forecasting method to model time series data), and Seasonal Autoregressive Integrated Moving Average (SARIMA) models were implemented. The performance of these models for predicting air quality is measured using the Mean Absolute Error (MAE), the Root Mean Square Error (RMSE), and the Relative Error (RE). SARIMA model is the most accurate in prediction of AQI (RMSE = 38.04, MAE = 22.52 and RE = 0.16). The results reveal that SARIMA can be applied to cities like Zahleh to assess the level of air pollution and to prevent harmful impacts on health. Furthermore, the authorities responsible for controlling the air quality may use this model to measure the level of air pollution in the nearest future and establish a mechanism to identify the high peaks of air pollution.

The Establishment of a New Air Health Index Integrating the Mortality Risks Due to Ambient Air Pollution and Non-Optimum Temperature

A composite Air Health Index(AHI)is helpful for separately emphasizing the health risks of multiple stimuli and communicating the overall risks of an adverse atmospheric environment to the public.We aimed to establish a new AHI by integrating daily mortality risks due to air pollution with those due to non-optimum temperature in China.Based on the exposure-response(E-R)coefficients obtained from time-series models,the new AHI was constructed as the sum of excess mortality risk associated with air pollutants and non-optimum temperature in 272 Chinese cities from 2013 to 2015.We examined the association between the“total AHI”(based on total mortality)and total mortality,and further compared the ability of the“total AHI”to predict specific cardiopulmonary mortality with that of“specific AHIs”(based on specific mortalities).On average,air pollution and non-optimum temperature were associated with 28.23%of daily excess mortality,of which 23.47%was associated with non-optimum temperature while the remainder was associated with fine particulate matter(PM2.5)(1.12%),NO2(2.29%,),and O3(2.29%).The new AHI uses a 10-point scale and shows an average across all 272 cities of 6 points.The E-R curve for AHI and mortality is approximately linear,without any thresholds.Each one unit increase in“total AHI”is associated with a 0.84%increase in all-cause mortality and 1.01%,0.98%,1.02%,1.66%,and 1.71%increases in cardiovascular disease,coronary heart disease,stroke,respiratory diseases,and chronic obstructive pulmonary disease mortality,respectively.Cause-specific mortality risk estimates using the“total AHI”are similar to those predicted by“specific AHIs.”In conclusion,the“total AHI”proposed herein could be a promising tool for communicating health risks related to exposure to the ambient environment to the public.

Particulate Matter-Based Air Quality Index Estimate for Abuja, Nigeria: Implications for Health

In recent years, urban air quality in developing countries such as Nigeria has continued to degenerate and this has constituted a major environmental risk to human health. It has been shown that an increase in ambient particulate matter (PM10) load of 10 μg/m3 reduces life expectancy by 0.64 years. Air Quality Index (AQI) as demonstrated in this study shows how relatively clean or polluted the boundary layer environment of any location can be. The study was designed to measure the level of suspended particulate matter (PM2.5 and PM10) for dry and wet seasons, compute the prevalent air quality index of selected locations in Abuja with possible health implications. Suspended particulate matter (PM2.5 and PM10) was assessed using handheld aerosol particulate sampler. The US Oak Ridge National AQI was adopted for the eleven (11) locations sampled and monitored. The study results showed that the air quality of the selected areas in Abuja were generally good and healthy. Dry season, assessments, showed 15 - 95 μg/m3 and 12 - 80 μg/m3 for PM2.5 and PM10, respectively. While in wet season, 09 - 75 μg/m3 and 07 - 65 μg/m3 were recorded for PM2.5 and PM10. However at Jebi Central Motor Park, there was light air contamination with AQI of 42 for dry season and 31 for wet season. Other locations had clean air with AQI ≤ 11. It is revealed that clean air exists generally during the wet season. Comparing study outcome to other cities in Nigeria, residents of Abuja are likely not to be affected with health hazards of particulate matter pollution. Nonetheless, the high range of PM2.5 and PM10 (fine and coarse particles) ratio evaluated i.e., 1.06 - 1.79 was higher than the WHO recommended standard of 0.5 - 0.8. This ratio remains a health concerns for sensitive inhabitants like pregnant women and their foetus as well as infants below age five whose respiratory airways are noted to have high surface areas and absorption capacity for fine particulate matter. Vegetation known to absorb suspended particulate matter should be planted across Abuja metropolitan areas and air quality monitoring stations installed at strategic locations for continuous monitoring and evaluations.

Spatio-Temporal Air Pollutant Characterization for Urban Areas

Urban pollution has now become increasingly recognized as an important determinant of air pollution in developed countries. The effect of urban air pollution in developing countries, on the other hand, has not been adequately addressed in the data Spatio-temporal time series. Thus, this study was intended to characterize the effect of urbanization on air pollution for an urbanized Klang Valley, Malaysia using Spatio-temporal data from 2008 to 2017. The Air Pollution Index (API) data and local pollutant concentration were employed to establish the links between urban air pollution. The analysis will be supported by determining the source of pollutants during the study period using Principal Component Analysis (PCA). The study identified that Carbon monoxide (CO), Nitrogen Dioxide (NO2), and Ozone (O3) are the major air pollution that has contributed to degrading air quality in the Klang Valley due to the vehicles, combustion process, and industries.

Use of Ventilation-Index in the Development of Exposure Model for Indoor Air Pollution—A Review

In indoor environment, emission factor of the cooking fuel plays a vital role in determining correlation between exposure assessment and health effects. Both indoor and outdoor air pollution exposures are widely influenced by the ventilation status. An optimum control of the air change rate has also significant impact on the exposure pattern. A number of studies revealed that the indoor particulates and gaseous exposures, resulting from the combustion of various cooking fuels, are associated with significant adverse health effects on pregnant mothers and new born babies. The impacts of ventilation status on air pollution exposure in households’ kitchens or living rooms have not been explored enough. Except a few studies with concrete rooms, especially in industries, no other studies have been established on the correlation between the ventilation index and air pollution exposure. The intent of this review is to discuss reported findings focused on the ventilation and exposure to air pollution. This will obviously help better understanding to modulate exposure profile in household condition using simple tool of ventilation measurement.

An Evaluation of Air Pollution Tolerance Index and Anticipated Performance Index of Some Tree Species Considered for Green Belt Development: A Case Study of Nandesari Industrial Area, Vadodara, Gujarat, India

It is well renowned that trees have capacity to reduce the air pollution. It is mandatory to expand tree plantation in industrial area to minimize the threat of pollutants. For green belt development, it is necessary to use plants that are tolerant to air pollution. The present study includes Air pollution tolerance index (APTI) of selected plant species with the help of biochemical analysis. On the basis of APTI and some other socioeconomic and biological parameters of plants, Anticipated Performance Index (API) was calculated. Out of twelve species, Ficus benghalensis showed to be the most efficient among others. As per classification of API, Ficus religiosa tree species is classified into the moderate category. Based on the APTI and API, appropriate plant species for green belt development in industrial area were identified and recommended for mitigating the pollution.

Mapping Air Quality Using Remote Sensing Technology: A Case Study of Nairobi County

Nairobi County experiences rapid industrialization and urbanization that contributes to the deteriorating state of air quality, posing a potential health risk to its growing population. Currently, in Nairobi County, most air quality monitoring stations use low-cost, inaccurate monitors prone to defects. The study’s objective was to map Nairobi County’s air quality using freely available remotely sensed imagery. The Air Pollution Index (API) formula was used to characterize the air quality from cloud-free Landsat satellite images i.e., Landsat 5 TM, Landsat 7 ETM+, and Landsat 8 OLI from Google Earth Engine. The API values were computed based on vegetation indices namely NDVI, TVI, DVI, and the SWIR1 and NIR bands on the QGIS platform. Qualitative accuracy assessment was done using sample points drawn from residential, industrial, green spaces, and traffic hotspot categories, based on a passive-random sampling technique. In this study, Landsat 5 API imagery for 2010 provided a reliable representation of local conditions but indicated significant pollution in green spaces, with recorded values ranging from -143 to 334. The study found that Landsat 7 API imagery in 2002 showed expected results with the range of values being -55 to 287, while Landsat 8 indicated high pollution levels in Nairobi. The results emphasized the importance of air quality factors in API calibration and the unmatched spatial coverage of satellite observations over ground-based monitoring techniques. The study recommends the recalibration of the API formula for characteristic regions, exploring newer satellite sensors like those onboard Landsat 9 and Sentinel 2, and involving key stakeholders in a discourse to develop a suitable Kenyan air quality index.

API法在马鞍山市空气质量评价中的应用

The air environmental quality of Ma′anshan City in Anhui Province was investigated by using of the Air Pollution Index (API) method. The result showed that the air environmental quality at Ma’anshan City during 1997-2000 was Ⅱ-Ⅰ grade (the air quality is just good), and the critical pollutants were TSP or NOx. Compared with other methods, the usage of API method may accurately reveal and easily calculate the degree of air pollution, and let the local residences and environmental personnel clearly understand the circumstance of air pollution.

我国西北5省5城市API变化特征的对比分析

依据2001-2012年的空气污染指数(API)日报数据,从月(或季、年)平均和空气污染等级2个角度出发,研究西北5省5城市(西宁、兰州、银川、西安和乌鲁木齐)API和空气污染状况比例的变化特征和趋势分析,统计结果表明:(1)5城市空气质量等级以Ⅱ级良为主,首要污染物以可吸入颗粒物为主。在年、季节、采暖期和非采暖期API值有趋于同步的下降变化趋势,污染(优良)天数呈现明显的下降(上升)趋势,大气污染呈现一定的"区域化"的特征。(2)5城市API指数变化规律有明显的时间和空间差异。从多年API年均值来看,西安、兰州和乌鲁木齐较高,银川和西宁相对较低,且乌鲁木齐、兰州和西宁空气质量状况不稳定,而西安和银川变化相对比较平缓。5城市的年变化也呈现不同的变化特征,总体上夏秋季空气质量明显好于冬春季。(3)5城市谱峰区间逐渐向低浓度范围偏移且天数逐渐增加,高浓度事件逐渐减少,各城市向低浓度转变的年份不完全一致。

中国环保重点城市API指数的时空模态区域分异

从区域空气污染监测、分析、预报研究与综合管理需求出发，利用经验正交函数EOF方法，将全国47个环保重点城市2004年7月1日-2006年6月30日2年逐日API指数（Air Pollution Index）时空分布资料分解为模态特征向量和时间系数，并对模态间差异性进行了Morlet小波分析，研究其频谱差异．在此基础上，建立了全国环保重点城市API指数时空模态区域分异体系．结果表明：以API指数作为评价指标，中国主要城市空气污染存在明显的区域分异，全国47个重点城市可分为10个区域，分别代表不同的污染时空模态．EOF及Morlet小波方法将全国47个环保重点城市API指数的时空分布清晰地表达出来，为空气污染区域分异研究提供了新的方法与思路．由于城市空间分布稀疏，难以涵盖全国所有城市的空气污染信息，因此，区域划分体系合理性有待进一步验证．

2002-2011年乌鲁木齐市API指数变化特征

文章利用乌鲁木齐市2002-2011年之间的空气污染指数(API)日报和同期气象要素数据,研究了API指数的变化特征,讨论了与气象要素间的相关关系。结果表明,API指数在10 a中呈下降趋势,年变化系数为-3.2。大气质量良好率在59.1%~77.4%之间变化。API指数呈显著季节差异,冬季较高,夏季最低。API指数Ⅰ级天数在春季、夏季和秋季分布占总天数的9.34%~34.82%。Ⅲ级以上天数在冬季较高,达到82.97%。月均API指数与本站气压和相对湿度呈现正相关,与风速、气温、平均水汽压和日照时数呈现负相关。而季节平均API指数与气象要素有一致的相关关系,且相关系数都有显著增大。API指数与气象要素在不同污染级别下,相关性变化较大。西北气流往往带来较低的API指数,而偏东气流往往伴随着污染日。

近10a华北地区API变化及与气象要素的相关性

分析华北地区近年来大气颗粒物污染水平的变化规律,可为环境空气质量指数的科学评价提供对比参考,并为区域空气污染防治提供科学依据。该文基于国家环保部对外公布的城市空气质量日报,分析了华北地区空气污染指数(air pollution index,API)变化规律及其与气象要素的相关性。结果表明,2003-2012年华北地区年平均API大致呈波动下降趋势,轻度污染及以上级别出现天数减少,空气质量总体有转好趋势;API季节变化差异显著,冬、春季平均API较高且大致呈下降趋势,但API急剧增大的重污染事件发生频率增加。气象要素与API变化关系密切:月平均气温、相对湿度与API大致呈显著负相关;月平均气压与API则呈显著正相关。

我国霾日和API分布特征及典型大城市中它们与气象条件关系

利用全国756基准站1994—2013年MICAPS地面常规观测资料和47个城市2002—2012年国家环境保护总局公布的空气污染指数（the Air Pollution Index,API）数据,对北京、南京、重庆沙坪坝、广州4个大城市霾日和API的气象条件进行分析。结果表明：1）我国霾日和API的高值区主要分布在中东部地区,年霾日自1998年开始上升,并持续增长,到2013年达到最多。1月霾日最多,8月霾日最少。2002—2012年期间,与年霾日不同,年API呈下降趋势,12月API最高,8月API最低。四大城市的霾日和API的年际变化和月际变化均存在较大差异。2）一般情况下,霾发生时,北京、南京、重庆沙坪坝、广州对应的相对湿度较高;霾发生时,北京西南风占主导作用,南京和广州均东南风占主导作用,重庆沙坪坝西北风占主导作用,风速多集中在1~4 m/s,负变压及低层大气稳定时更易产生霾日。3）低层稳定度（γ850）对四大城市的API的影响各不相同,北京和重庆沙坪坝与γ850呈负相关,即越稳定,API值越高,南京和广州与γ850呈正相关,即越不稳定,API值越高。4）多元线性回归方程的结果表明：热力因子（相对湿度、γ850）和动力因子（地面风速、24 h变压）对四大城市冬季霾日能见度和冬季API各有贡献。

近10年中国主要城市空气API及与气象因子相关性分析

据2000年6月-2012年6月中国47个主要城市的空气污染指数(API)逐日监测数据,分析中国近年空气质量,并分析其与气温、露点、降水、风及温度露点差(T-T d)等气象要素的相关性。通过分析发现:我国空气污染西北重、东南低;空气质量变化呈现明显的季节变化,冬季最高,春季较高且变化幅度大,夏秋季节相对较低;主要污染物以可吸入颗粒物(PM10)为主;广西地区化学污染突出。随着污染治理工作的开展,近年API值呈下降趋势,由2001年的年均82.75下降至2011年的66.1。分析API与气象要素的相关性,发现降水对空气污染的净化作用明显;风在沿海地区能稀释空气污染,而在西北内陆这一作用不明显;API与气温、露点均呈负相关;而与二者之差所表征的空气干燥程度呈较高的正相关。

API法及其在城市大气环境质量评价中的应用

采用空气污染指数API法对某城市2003年大气环境质量进行了评价。结果表明,2003年该市空气质量达到了国家二级标准,影响该市空气质量的主要污染物为可吸入颗粒物,主要污染时间为5、1、11、12月,影响因素为气象和人为活动;建议采取优化产业结构、改造锅炉和燃烧设备、大力发展和推广使用清洁能源、加快城市绿化和固化建设等污染防治对策;与其他评价方法相比,采用API法对大气环境质量进行评价可准确地揭示大气污染程度,是一种简便、直观且可靠的评价方法。

上海市空气污染指数API的时空分布特征

空气污染指数(API)是一种综合反应和评价空气质量的指标,分级表征空气污染程度和空气质量状况。利用上海市环境监测中心收集的上海市2006～2011年各个区的API指数,对API指数进行时间序列分析和空间分析,包括近6年来API的年变化、季节变化以及比较上海市市区和郊区的API值。结果表明:上海市的空气污染状况在2006～2011年期间得到改善;夏季的空气质量最好,春季最差;空间上存在城郊差异,郊区API指数低于市区,金山区空气质量最好,普陀区和宝山区质量较差。

杭州主城区大气臭氧对空气污染指数API的影响

利用2004年至2007年空气污染监测数据,比较现行API指数和修正后API指数的差异,分析修正后O3污染的变化状况,研究O3污染的季节变化。结果表明,O3作为一种新的空气污染指标,对修正后API指数的影响很大。与现行API指数相比,4年来修正后API指数的污染率大幅度增加,并且各季节的污染率越来越接近,2007年污染率在25%左右。2007年各季节修正后API指数污染天数中O3污染天数所占百分比分别是春季为52%、夏季91.6%、秋季20.8%、冬季O3,未出现污染。