Neuropsychological Assessment of Community-Dwelling Older Adults in Almaty, Kazakhstan.

Cognitive impairment in older adults is a major public concern for Kazakhstan's aging population. We aimed to (1) administer a neuropsychological test battery (NTB) in domains relevant to aging-associated cognitive impairment in a sample of adults aged 60+ without dementia in Almaty, Kazakhstan; (2) investigate the associations between demographic factors and test performance; and (3) provide information on the distribution of NTB scores as preliminary local normative data relevant for this population. A cross-sectional evaluation of 276 participants aged 60+ in Almaty, Kazakhstan, was conducted using cognitive instruments including tests of memory, attention, language, executive functions, visuospatial abilities, and processing speed. Multiple linear regression analyses were used to examine the association of demographic factors with neuropsychological test performance. The results from the regression analysis showed that those who are younger, have more years of education, are women, and are of Russian ethnicity had significantly better performance. The current study illustrated (1) the feasibility of administering the NTB to older adults in the general population in Kazakhstan; (2) the preliminary local normative neuropsychological measures; and (3) their independent associations with age, education, gender, and ethnicity. The findings are a platform for future research on dementia and cognitive impairment in older adults in Kazakhstan.

Which qualities should built environment possess to ensure satisfaction of higher-education students with remote education during pandemics?

The COVID-19 pandemic has suddenly switched most education processes from face-to-face to remote mode, obliging millions of students to utilize their residences as study spaces. However, the characteristics of their residential built environments differ in terms of regional, social, cultural, and technological aspects. These differences should impact the students' performance and satisfaction which needs to be measured and studied. The present study aims to identify the effect of the residential built environment on students' satisfaction and academic performance during the COVID-19 pandemic. It was conducted in two countries, Kazakhstan (KZ) and Norway (NO), using a comprehensive online survey to gather data. An empirical assessment based on the structural equation model was employed to identify links between health, safety, and comfort of students' facilities and academic performance and satisfaction. We conclude that the built environment affects both satisfaction for remote education and their learning performance. Significant differences in readiness for remote education have been observed between urban and non-urban living areas: (1) The role of health-and-safety convenience seems to increase with the urbanization level of the respondents' living spaces; (2) in contrast, for non-urban residents, the provision of comfort facilities is dominant. In the meantime, an analysis "by regions" revealed that health-and-safety-related facilities in residences are more critical for remote education in Central Asia (KZ). In contrast, the comfort features of residences being more important for the students studying remotely in Northern Europe (NO). These results provide an understanding that would assist in improving remote education and preparing pandemic-ready living areas.

Effects of the residential built environment on remote work productivity and satisfaction during COVID-19 lockdowns: An analysis of workers' perceptions.

COVID-19 pandemic has forced people to stay home and switch to the remote working mode, which - reportedly - affect job satisfaction and productivity. The present study investigates the relationship between the residential environment and worker's job satisfaction and productivity in the remote working mode during the COVID-19 pandemic. A hypothetical structural equation model (SEM) of the influencing factors is constructed based on a literature review and experts' opinions. A survey-based respondents' opinions (n = 2276) were then used to test and analyze the model. The model results reveal that a residential built environment has an indirect effect on both remote work satisfaction and productivity. However, among all the factors, comfortable space (separate space and ergonomic furniture) is found to be the most important. This study presents the importance of adopting a residential built environment to respond to a crisis like a pandemic in achieving the desired comfort level of remote work. Although this study provides a holistic approach, it also proposes a base for the future country-specific analysis by providing some possible countries' differences.

Assessment of the association between dust storms and COVID-19 infection rate in southwest Iran.

This study assesses a plausible correlation between a dust intrusion episode and a daily increase in COVID-19 cases. A surge in COVID-19 cases was observed a few days after a Middle East Dust (MED) event that peaked on 25th April 2020 in southwest Iran. To investigate potential causal factors for the spike in number of cases, cross-correlations between daily combined aerosol optical depths (AODs) and confirmed cases were computed for Khuzestan, Iran. Additionally, atmospheric stability data time series were assessed by covering before, during, and after dust intrusion, producing four statistically clustered distinct city groups. Groups 1 and 2 had different peak lag times of 10 and 4-5 days, respectively. Since there were statistically significant associations between AOD levels and confirmed cases in both groups, dust incursion may have increased population susceptibility to COVID-19 disease. Group 3 was utilized as a control group with neither a significant level of dust incursion during the episodic period nor any significant associations. Group 4 cities, which experienced high dust incursion levels, showed no significant correlation with confirmed case count increases. Random Forest Analysis assessed the influence of wind speed and AOD, showing relative importance of 0.31 and 0.23 on the daily increase percent of confirmed cases, respectively. This study may serve as a reference for better understanding and predicting factors affecting COVID-19 transmission and diffusion routes, focusing on the role of MED intrusions.

Assessment of potential benefits of traffic and urban mobility reductions during COVID-19 lockdowns: dose-response calculations for material corrosions on built cultural heritage.

Air pollution, particularly in urban areas, puts human health in danger and has adverse impacts on the built environment. It can accelerate the natural corrosion rate of cultural heritages and monuments, leading to premature aging and lowering their aesthetic value. Globally, at the beginning of 2020, to tackle the spread of novel COVID-19, the lockdown was enforced in the most hard-hit countries. Therefore, this study assesses, as a first time, the plausible benefits of traffic and urban mobility reductions on the natural process of deterioration of materials during COVID-19 lockdown in twenty-four major cities on five continents. The potential risk is estimated based on exceeding the tolerable degradation limits for each material. The notable impact of COVID-19 mobility restrictions on air quality was evidenced in 2020 compared to 2019. The introduced mobility restrictions in 2020 could decrease the surface recession rate of materials. Extremely randomized trees analysis showed that PM10 was the main influencing factor for corrosion of portland, copper, cast bronze, and carbon steel with a relative importance of 0.60, 0.32, 0.90, and 0.64, respectively, while SO2 and HNO3 were mainly responsible for corrosion of sandstone and zinc with a relative importance of 0.60 and 0.40, respectively. The globally adverse governed meteorological conditions in 2020 could not positively influence the movement restrictions around the world in air quality improvements. Our findings can highlight the need for additional policies and measures for reducing ambient pollution in cities and the proximity of sensitive cultural heritage to avoid further damage.

Stakeholder based weights of new sustainability indicators providing pandemic resilience for residential buildings.

During COVID-19, the building and service characteristics of residential buildings turned out to be more critical due to lockdowns. The present research assesses the importance of new sustainability indicators for residential buildings in three categories (e.g., Health and Safety, Environmental Resources Consumption, and Comfort) that provide resilience for pandemic periods. The opinions of stakeholders on the identified indicators were collected and then analyzed. 'Health and Safety' category is found to be the most critical among the others. The prevention of virus propagation, mental health, and building air quality are three crucial indicators playing essential roles in the health and safety category. In more detail, innovative smart technologies, including touchless technologies, are identified as a priority in preventing virus propagation. Outdoor spaces and safe indoor places for socialization are weighted as essential in supporting the well-being and mental health of the resident. Finally, air filtration and segregation of medical waste indicators are considered critical in preventing the spread of viruses. There was a consensus among the local and international experts since they did not significantly report differing opinions for the majority of the indicators. However, there was a shift in experts' opinions towards pandemic-oriented indicators compared to conventional sustainability indicators.

Assessment method for new sustainability indicators providing pandemic resilience for residential buildings.

The method presented in this paper aims to support the sustainability assessment methods of residential buildings under pandemic conditions. The main purpose of the study is to review existing criteria of the well-known assessment tools and then to suggest a set of assessment measures for the emerging pandemic-resilient indicators. Current sustainability assessment methodologies mostly focus on the conventional sustainability pillars (Environmental, Social, Economic), whereas the proposed emerging sustainability assessment indicators include changes in sustainability requirements brought by the current pandemic. Firstly, a set of indicators with possible measures was identified; then, we reviewed several existing green building certification systems to identify their gaps and developed a foundation for each indicator. Finally, several round table discussions involving various stakeholders (e.g., engineers, designers, health care experts, academics) were conducted to consolidate the identified measures. The findings of the present study indicate that certain pandemic-resilient indicators are not fully addressed by existing assessment tools, pointing out the importance of the development of new measures to make them more suitable to use under pandemic conditions. Thus, the present study contributes to the building assessment methods by proposing a set of emerging assessment indicators with measures, which can be used by various professionals that would contribute to more sustainable buildings in upcoming pandemics.•A 5-point scale was used to assess the indicators, and various stakeholders in a previous study identified their weights.•The methodology introduces new pandemic-related indicators into the conventional sustainability concept.•The assessment measures are rapid and economically efficient to apply for any residential building.

Mercury (Hg) Contaminated Sites in Kazakhstan: Review of Current Cases and Site Remediation Responses.

Mercury (Hg) emissions from anthropogenic sources pose a global problem. In Central Asia, Kazakhstan's central and northern regions are among the most severely Hg-contaminated territories. This is due to two former acetaldehyde (in Temirtau) and chlor-alkali (in Pavlodar) plants, discharges from which during the second half of the 20th century were estimated over 2000 tons of elemental Hg. However, the exact quantities of Hg released through atmospheric emissions to the environment, controlled discharges to the nearby aquatic systems, leakages in the cell plant, and contaminated sludge are still unknown. The present review is the initiation of a comprehensive field investigation study on the current state of these contaminated sites. It aims to provide a critical review of published literature on Hg in soils, sediments, water, and biota of the impacted ecosystems (Nura and Irtysh rivers, and Lake Balkyldak and their surrounding areas). It furthermore compares these contamination episodes with selected similar international cases as well as reviews and recommends demercuration efforts. The findings indicate that the contamination around the acetaldehyde plant site was significant and mainly localized with the majority of Hg deposited in topsoils and riverbanks within 25 km from the discharge point. In the chlor-alkali plant site, Lake Balkyldak in North Kazakhstan is the most seriously contaminated receptor. The local population of both regions might still be exposed to Hg due to fish consumption illegally caught from local rivers and reservoirs. Since the present field data is limited mainly to investigations conducted before 2010 and given the persisting contamination and nature of Hg, a recent up-to-date environmental assessment for both sites is highly needed, particularly around formerly detected hotspots. Due to incomplete site remediation efforts, recommendations given by several researchers for the territories of the former chlor-alkali and acetaldehyde plant site include ex-situ soil washing, soil pulping with gravitational separation, ultrasound and transgenic algae for sediments, and electrokinetic recovery for the former and removal and/or confinement of contaminated silt deposits and soils for the latter. However, their efficiency first needs to be validated. Findings and lessons from these sites will be useful not only on the local scale but also are valuable resources for the assessment and management of similar contaminated sites around the globe.

Indicator rating methodology for Rapid Sustainability Assessment Method (RSAM) for existing residential buildings using opinions of residents.

The presented method provides the details for how each indicator in "RSAM: A Rapid Sustainability Assessment Method" is scored using a residents' opinions-based sustainability assessment procedure that is specifically designed for the assessment of existing residential buildings. Existing methods in the literature mostly suggest indicator scores in construction sustainability assessments using highly technical data and require a high level of engineering and management expertise. This makes them elaborate but labor-, time-, and cost-intensive; and thus, their use is more frequently favored in new projects.•The presented method redefines a set of conventional environmental, social-functional, and economic indicators in a context which combines data from residents' opinions (e.g. perceived quality of indoor temperature comfort level) and easy-to-obtain information (e.g. annual utility bills).•All indicator ratings are represented within a 10-point scale, and their weights on the overall model are identified by stakeholders.•RSAM provides a rapid and low-cost assessment for existing buildings which normally may not go through a conventional sustainability assessment due to resource limitations.

Trends and health impacts of major urban air pollutants in Kazakhstan.

The air quality in cities in Kazakhstan has been poorly investigated despite the worsening conditions. This study evaluates national air pollution monitoring network data (Total Suspended Particle-TSP, NO2, SO2, and O3) from Kazakhstan cities and provides estimates of excess mortality rates associated with PM2.5 exposure using the Global Exposure Mortality Model (GEMM) concentration-response function. Morbidity rates associated with PM10 exposure were also estimated. Annual average (2015-2017) population-weighted concentrations were Kazakhstan cities was 157, 51, 29, and 41 µg m-3 for TSP, NO2, SO2, and O3 respectively. We estimated a total of 8134 adult deaths per year attributable to PM2.5 (average over 2015-2017) in the selected 21 cities of Kazakhstan. The leading causes of death were ischemic heart disease (4080), stroke (1613), lower respiratory infections (662), chronic obstructive pulmonary disease (434), lung cancer (332). The per capita mortality rate attributable to ambient air pollution (per 105 adults per year) was less than 150 in nine cities, between 150 and 204 in nine cities, and between 276 and 373 in three industrial cities (Zhezkazgan, Temirtau, and Balkhash). Implications: Quantitative information on the health impacts of air pollution can be useful for decision-makers in Kazakhstan to justify environmental policies and identify policy and funding priorities for addressing air pollution issues. This information can also be useful for policymakers by improving the quality of government-funded environmental reports and strategic documents, as they have many shortcomings in terms of the selection of air quality indicators, identification of priority pollutants, and identification of sources of pollution. This study has high significance due to the lack of data and knowledge in Central Asia, especially Kazakhstan.

Assessing air quality changes in large cities during COVID-19 lockdowns: The impacts of traffic-free urban conditions in Almaty, Kazakhstan.

Number of cities worlwide experienced air quality improvements during COVID-19 lockdowns; however, such changes may have been different in places with major contributions from nontraffic related sources. In Almaty, a city-scale quarantine came into force on March 19, 2020, which was a week after the first COVID-19 case was registered in Kazakhstan. This study aims to analyze the effect of the lockdown from March 19 to April 14, 2020 (27 days), on the concentrations of air pollutants in Almaty. Daily concentrations of PM2.5, NO2, SO2, CO, O3, and BTEX were compared between the periods before and during the lockdown. During the lockdown, the PM2.5 concentration was reduced by 21% with spatial variations of 6-34% compared to the average on the same days in 2018-2019, and still, it exceeded WHO daily limit values for 18 days. There were also substantial reductions in CO and NO2 concentrations by 49% and 35%, respectively, but an increase in O3 levels by 15% compared to the prior 17 days before the lockdown. The concentrations of benzene and toluene were 2-3 times higher than those during in the same seasons of 2015-2019. The temporal reductions may not be directly attributed to the lockdown due to favorable meteorological variations during the period, but the spatial effects of the quarantine on the pollution levels are evidenced. The results demonstrate the impact of traffic on the complex nature of air pollution in Almaty, which is substantially contributed by various nontraffic related sources, mainly coal-fired combined heat and power plants and household heating systems, as well as possible small irregular sources such as garbage burning and bathhouses.

Trends and health impacts of major urban air pollutants in Kazakhstan.

Air quality in Kazakhstan cities has been poorly investigated despite their deteriorating situations. This study evaluates the national air pollution monitoring network data (PM10, NO2, SO2, and O3) in Kazakhstan cities, and provides the estimates of excess mortality rates associated with PM2.5 exposure using the Global Exposure Mortality Model (GEMM) concentration-response function. Morbidity rates associated with PM10 exposure were also estimated. Firstly, an air quality-based priority ranking of the cities was suggested based on the annual concentrations of the pollutants during the period of 3 years between 2015 and 2017. Nur-Sultan, Almaty, Ust-Kamenogorsk, and Aktobe were identified as the most polluted cities by PM10, NO2, SO2, and O3 respectively. Then, the exposure-response assessment was conducted for 21 cities. In major cities of Kazakhstan attributable to ambient air pollution per capita, mortality rate is 1 193 per 100 000 population per year, which is 8.97 times higher than in Europe. It is estimated that fine particulate matter exposure in the major cities of Kazakhstan causes 101 139 premature deaths annually. This study provides quantitative information on potential public health risks and impacts of air pollution, which is valuable for decision-makers to justify national environmental policies. Implications: Quantitative information on health impacts from air pollution can be useful for decision makers in Kazakhstan to justify environmental policies and identify policy and funding priorities for tackling air pollution issues. It can be also useful for policy makers in improving the quality of government funded environmental reports and strategic documents as they have many shortcomings in terms of selection of air quality indicators, identification of priority pollutants, identification of sources of pollution. This study has high significance due to the lack of data and knowledge in the region of Central Asia, in particular, of Kazakhstan.

Physicochemical and morphological characterization of atmospheric coarse particles by SEM/EDS in new urban central districts of a megacity.

Physicochemical and morphological characteristics of atmospheric particles in new urban centers of fast-developing megacities are not well understood. In this study, atmospheric coarse particles (PM2.5-10) were simultaneously collected in multiple stations (10) in new urban centers, namely Beylikduzu, Buyukcekmece, and Esenyurt, of Istanbul using a modified passive particulate sampling method. Scanning electron microscope and energy dispersive X-photon spectroscopy (SEM-EDS) was used to investigate the size distribution characteristics, chemical composition and their weight percent abundances, and morphological properties of the collected particles. The particle clusters were mainly dominated by Ca-rich Al silicates, Ca dominant, Ca- and S-rich, and NaCl particles, respectively. Their potential sources were assigned to the natural sources (e.g., wind erosion, soil resuspension, and sea sprays) and anthropogenic activities (construction, transportation, mining and crushing, and cement production). In addition to the major contributions (up to 47% of particle number abundance), the minor contribution clusters (less than 1%) with transitional metals rich particles (Fe, Zn, and Cu rich) mainly from anthropogenic sources (combustion, traffic, and vehicular emissions) were identified. The typical size range (> 0.65 to < 11.00 µm) distribution of the major particle clusters fits a left-skewed modal distribution with a peak at 1.10-2.30-µm size range. However, the number of particles decreases significantly with increasing distance to the source, and this justification is stronger for larger size fractions (> 2.3 µm). Particle numbers and varieties indicated significant spatial variations depending upon the identified sources, meteorological factors, and temporal conditions. In general, the results of this study suggest that the passive sampling of PM2.5-10 coupled with SEM/EDS based single-particle analysis is an effective tool to understand the physicochemical characterization and spatial and temporal variations of atmospheric particles in urban environments.

A toxicological and genotoxicological indexing study of ambient aerosols (PM2.5-10) using in vitro bioassays.

This study evaluates the toxicity and genotoxicity levels of atmospheric particulate matter (PM) samples collected at several locations of a megacity (Istanbul, Turkey) with different urban and industrial characteristics. The ambient air samples, in the form of a coarse fraction of inhalable particulates, PM2.5-10, were collected on Teflon filters using a passive sampling method on a monthly basis during a one-year period. Later, they were extracted into both the lipophilic and hydrophilic phases using dimethyl sulfoxide (DMSO) and ultra-pure water, respectively. The obtained aqueous extracts were tested for acute toxicity and genotoxicity using the photo-luminescent bacterium Vibrio fischeri Microtox® and SOS Chromotest® assays, respectively. Statistically significant differences greater than background levels were obtained in both measurements, indicating the presence of toxic substances absorbed on particulate matter. The PM2.5-10 extracts identified significant seasonal and locational differences in the toxicity and genotoxicity levels. Local anthropogenic activities and factors were associated with the quantified higher levels. Finally, a qualitative inner comparison study of regional toxicity and genotoxicity indexes was suggested to provide a clearer picture of the pollution and risk levels (or occurrences) in the Istanbul urban area. In this indexing study, the threshold levels for the urban background and episodic occurrences of the toxicity and genotoxicity levels in PM2.5-10 samples were identified to be 1.11 TU (Toxicity Unit) and 8.73 TU and 0.72 IF (Induction Factor) and 1.38 IF, respectively.

Ragweed pollen observed in Turkey: detection of sources using back trajectory models.

This paper discusses the pollen season and the source apportionment of ragweed (Ambrosia) grains detected in the atmosphere of Istanbul, Turkey. The dynamic migration of this invasive taxon is a serious environmental issue. Ragweed pollen is highly allergenic and causes sensitization in patients at low concentrations. At present, there is no floristic evidence of this taxon in the region. Aerobiological records presented here, though, indicate a local source. Moreover, we argue that ragweed pollen comes from distant sources through air mass movements. The analysis concerns the ragweed season 2007. Pollens were sampled with a Burkard trap and identified at a magnification of 400 ×. Grains were counted on 12 transverse traverses to estimate bi-hourly changes in concentrations. The peak day was on August 28 with 20 grainsm(-3). Ragweed was observed on 22 days during August and September 2007. On all days, except one, the daily average concentration was below 10 grainsm(-3). Diurnal bi-hourly ragweed concentrations reached a maximum at 11:00 EET. Relatively high concentrations were observed between 21:00 and 01:00 EET. This allowed for the assumption of a local and a remote ragweed pollen source. We used HYSPLIT backward trajectory ensembles to identify possible sources on peak day. A frequency analysis of back trajectories covering the entire ragweed season followed. Firstly, possible local sources were the Istanbul Province and Turkish Thrace; secondly, a likely over-regional source was Bulgaria; and lastly, remote sources of ragweed pollen were the Ukraine, the Russian coastal region of the Black Sea and Moldova. This study provides evidence that pollens detected on our receptor site stem from combined local and remote origins.

Determination of air quality zones in Turkey.

In this study, the particulate matter (with an aerodynamic diameter <10 microm; PM10) profile of Turkey with data from the air quality monitoring stations located throughout the country was used. The number of stations (119) was reduced to 55 after a missing data treatment for statistical analyses. First, a classification method was developed based on ongoing national and international (European Commission directives) legislations to categorize air zones into six groups, from a "Very Clear Air Zone" to a "Polluted Air Zone". Then, a Geographic Information System (GIS)-based interpolation technique and statistical analyses (correlation analysis and factor analysis) were used to generate PM10 pollution profiles of the annual heating time and nonheating time periods. Finally, the coherent air pollution management zones of Turkey, based on air quality criteria and measured data using a GIS-based model supported by statistical analyses, were suggested. Based on the analysis, four hot spots were identified: (i) the eastern part of the Black Sea region; (ii) the northeastern part of inland Anatolia; (iii) the western part of Northeastern Anatolia; and (vi) the eastern part of Turkey. The possible reasons for the elevated PM10 levels are discussed using topographic, climatologic, land use, and energy utilization parameters. Finally, the suggested air zones were compared with the administrative air zones, which were newly developed by the Turkish Ministry of Environment and Forestry, to evaluate the level of agreement between the two.

Effect of meteorological parameters on fine and coarse particulate matter mass concentration in a coal-mining area in Zonguldak, Turkey.

In this work, the effect of meteorological parameters and local topography on mass concentrations of fine (PM2.5) and coarse (PM2.5-10) particles and their seasonal behavior was investigated. A total of 236 pairs of samplers were collected using an Anderson Dichotomous sampler between December 2004 and October 2005. The average mass concentrations of PM2.5, PM2.5-10, and particulate matter less than 10 microm in aerodynamic diameter (PM10) were found to be 29.38, 23.85, and 53.23 microg/m3, respectively. The concentrations of PM2.5 and PM10 were found to be higher in heating seasons (December to May) than in summer. The increase of relative humidity, cloudiness, and lower temperature was found to be highly related to the increase of particulate matter (PM) episodic events. During non-rainy days, the episodic events for PM2.5 and PM10 were increased by 30 and 10.7%, respectively. This is a result of the extensive use of fuel during winter for heating purposes and also because of stagnant air masses formed because of low temperature and low wind speed over the study area.

Particulate matter (PM(2.5), PM(10-2.5), and PM(10)) and children's hospital admissions for asthma and respiratory diseases: a bidirectional case-crossover study.

Epidemiological studies reported adverse effects of air pollution on the prevalence of respiratory diseases in children. The purpose of this study was to examine the association between air pollution and admissions for asthma and other respiratory diseases among children who were younger than 15 yr of age. The study used data on respiratory hospital admissions and air pollutant concentrations, including thoracic particulate matter (PM(10)), fine (PM(2.5)), and coarse (PM(10-2.5)) particulate matter in Zonguldak, Turkey. A bidirectional case-crossover design was used to calculate odds ratios for the admissions adjusted for daily meteorological parameters. Significant increases were observed for hospital admissions in children for asthma, allergic rhinitis (AR), and upper (UPRD) and lower (LWRD) respiratory diseases. All fraction of PM in children showed significant positive associations with asthma admissions. The highest association noted was 18% rise in asthma admissions correlated with a 10-microg/m(3) increase in PM(10-2.5) on the same day of admissions. The adjusted odds ratios for exposure to PM(2.5) with an increment of 10 microg/m(3) were 1.15 and 1.21 for asthma and allergic rhinitis with asthma, respectively. PM(10) exerted significant effects on hospital admissions for all outcomes, including asthma, AR, UPRD, and LWRD. Our study suggested a greater effect of fine and coarse PM on asthma hospital admissions compared with PM(10) in children.

An online air pollution forecasting system using neural networks.

In this work, an online air pollution forecasting system for Greater Istanbul Area is developed. The system predicts three air pollution indicator (SO(2), PM(10) and CO) levels for the next three days (+1, +2, and +3 days) using neural networks. AirPolTool, a user-friendly website (http://airpol.fatih.edu.tr), publishes +1, +2, and +3 days predictions of air pollutants updated twice a day. Experiments presented in this paper show that quite accurate predictions of air pollutant indicator levels are possible with a simple neural network. It is shown that further optimizations of the model can be achieved using different input parameters and different experimental setups. Firstly, +1, +2, and +3 days' pollution levels are predicted independently using same training data, then +2 and +3 days are predicted cumulatively using previously days predicted values. Better prediction results are obtained in the cumulative method. Secondly, the size of training data base used in the model is optimized. The best modeling performance with minimum error rate is achieved using 3-15 past days in the training data set. Finally, the effect of the day of week as an input parameter is investigated. Better forecasts with higher accuracy are observed using the day of week as an input parameter.