Leveraging machine learning to analyze and forecast air quality trends in Kota City, India

Lahore, the home of 11 million people, is one of the most polluted cities in the world. Pollution causes deaths, birth defects, and years of life lost. This study’s real-time data analysis of the air quality index (AQI) showed that air pollution remained “unhealthy for everyone” for 54% of the time, and “unhealthy for sensitive groups” for 88% of the time, during the last three years (June 2019–September 2021). The air quality index (AQI) value in Lahore reached 175 µg/m3 in 2021. This alarmingly hazardous air situation was analyzed by selecting fourteen sites based on the provenance of industrialization and tailpipe emissions. An analysis of remote sensing data for these sites was performed, in addition to field surveys, to identify the relationship between pollutant concentration and on-ground current practices. The key primary and secondary air pollutants selected for analysis were carbon monoxide (CO), nitrogen dioxide (NO2), sulphur dioxide (SO2), aerosol optical depth (AOD), methane (CH4), and formaldehyde (HCHO). The assessment was carried out for the study period of July 2018 to April 2021. The real-time AQI was plotted against each pollutant’s monthly concentration, which showed a significant positive correlation of AQI with SO2, NO2, and CO. A plotting of the percentage contribution of each pollutant with its emission sources highlighted the main pollutant to take action to reduce, as a priority on those particular sites. The pollutant hotspot within each economic activity was also determined. Assessments showed that the AQI value was higher on weekends than on weekdays. These findings can help to develop smart adaptation action plans for immediate implementation, to dilute the current environmental risks in the city.

To describe the spatiotemporal variations characteristics and future trends of urban air quality in China, this study evaluates the spatiotemporal evolution features and linkages between the air quality index (AQI) and six primary pollution indicators, using air quality monitoring data from 2014 to 2022. Seasonal autoregressive integrated moving average (SARIMA) and random forest (RF) models are created to forecast air quality. (1) The study’s findings indicate that pollution levels and air quality index values in Chinese cities decline annually, following a “U”-shaped pattern with a monthly variation. The pollutant levels are high in winter and low in spring, and low in summer and rising in the fall (O3 shows the opposite). (2) The spatial distribution of air quality in Chinese cities is low in the southeast and high in the northwest, and low in the coastal areas and higher in the inland areas. The correlation coefficients between AQI and the pollutant concentrations are as follows: fine particulate matter (PM2.5), inhalable particulate matter (PM10), carbon monoxide (CO), nitrogen dioxide (NO2), sulfur dioxide (SO2), and ozone (O3) values are correlated at 0.89, 0.84, 0.54, 0.54, 0.32, and 0.056, respectively. (3) In terms of short-term AQI predictions, the RF model performs better than the SARIMA model. The long-term forecast indicates that the average AQI value in Chinese cities is expected to decrease by 0.32 points in 2032 compared to the 2022 level of 52.95. This study has some guiding significance for the analysis and prediction of urban air quality.

An index for reporting air quality is called the air quality index (AQI). It measures the impact of air pollution on a person’s health over a short period of time. The purpose of the AQI is to educate the public on the negative health effects of local air pollution. The amount of air pollution in Indian cities has significantly increased. There are several ways to create a mathematical formula to determine the air quality index. Numerous studies have found a link between air pollution exposure and adverse health impacts in the population. Data mining techniques are one of the most interesting approaches to forecast AQI and analyze it. The aim of this paper is to find the most effective way for AQI prediction to assist in climate control. The most effective method can be improved upon to find the most optimal solution. Hence, the work in this paper involves intensive research and the addition of novel techniques such as SMOTE to make sure that the best possible solution to the air quality problem is obtained. Another important goal is to demonstrate and display the exact metrics involved in our work in such a way that it is educational and insightful and hence provides proper comparisons and assists future researchers. In the proposed work, three distinct methods—support vector regression (SVR), random forest regression (RFR), and CatBoost regression (CR)—have been utilized to determine the AQI of New Delhi, Bangalore, Kolkata, and Hyderabad. After comparing the results of imbalanced datasets, it was found that random forest regression provides the lowest root mean square error (RMSE) values in Bangalore (0.5674), Kolkata (0.1403), and Hyderabad (0.3826), as well as higher accuracy compared to SVR and CatBoost regression for Kolkata (90.9700%) and Hyderabad (78.3672%), while CatBoost regression provides the lowest RMSE value in New Delhi (0.2792) and the highest accuracy is obtained for New Delhi (79.8622%) and Bangalore (68.6860%). Regarding the dataset that was subjected to the synthetic minority oversampling technique (SMOTE) algorithm, it is noted that random forest regression provides the lowest RMSE values in Kolkata (0.0988) and Hyderabad (0.0628) and higher accuracies are obtained for Kolkata (93.7438%) and Hyderabad (97.6080%) in comparison to SVR and CatBoost regression, whereas CatBoost regression provides the highest accuracies for New Delhi (85.0847%) and Bangalore (90.3071%). This demonstrated definitely that datasets that had the SMOTE algorithm applied to them produced a higher accuracy. The novelty of this paper lies in the fact that the best regression models have been picked through thorough research by analyzing their accuracies. Moreover, unlike most related papers, dataset balancing is carried out through SMOTE. Moreover, all of the implementations have been documented via graphs and metrics, which clearly show the contrast in results and help show what actually caused the improvement in accuracy.

This paper is aimed at developing an air quality monitoring system using machine learning (ML), Internet of Things (IoT), and other elements to predict the level of particulate matter and gases in the air based on the air quality index (AQI). It is an air quality assessor and therefore a means of achieving the Sustainable Development Goals (SDGs), in particular, SDG 3.9 (substantial reduction of the health impacts of hazardous substances) and SDG 11.6 (reduction of negative impacts on cities and populations). AQI quantifies and informs the public about air pollutants and their adverse effects on public health. The proposed air quality monitoring device is low-cost and operates in real-time. It consists of a hardware unit that detects various pollutants to assess air quality as well as other airborne particles such as carbon dioxide (CO2), methane (CH4), volatile organic compounds (VOCs), nitrogen dioxide (NO2), carbon monoxide (CO), and particulate matter with an aerodynamic diameter of 2.5 microns or less (PM2.5). To predict air quality, the device was deployed from November 1, 2022, to February 4, 2023, in certain bauxite-rich areas of Adamawa and certain volcanic sites in western Cameroon. Therefore, machine learning algorithm models, namely, multiple linear regression (MLR), support vector regression (SVR), random forest regression (RFR), XGBoost (XGB), and K-nearest neighbors (KNN) were applied to analyze the collected concentrations and predict the future state of air quality. The performance of these models was evaluated using mean absolute error (MAE), coefficient of determination (R-square), and root mean square error (RMSE). The obtained data in this study show that these pollutants are present in selected localities albeit to different extents. Moreover, the AQI values obtained range from 10 to 530, with a mean of 132.380 ± 63.705, corresponding to moderate air quality state but may induce an adverse effect on sensitive members of the population. This study revealed that XGB regression performed better in air quality forecasting with the highest R-squared (test score of 0.9991 and train score of 0.9999) and lowest RMSE (test score of 1.5748 and train score of 0. 0073) and MAE (test score of 0.0872 and train score of 0.0020), while the KNN model had the worst prediction (lowest R-squared and highest RMSE and MAE). This embryonic work is a prototype for projects in Cameroon as measurements are underway for a national spread over a longer period of time.

Air pollution and pregnancy outcomes in Dhaka, Bangladesh

Ground-received solar radiation is affected by several meteorological and air pollution factors. Previous studies have mainly focused on the effects of meteorological factors on solar radiation, but research on the influence of air pollutants is limited. Therefore, this study aimed to analyse the effects of air pollution characteristics on solar radiation. Meteorological data, air quality index (AQI) data, and data on the concentrations of six air pollutants (O3, CO, SO2, PM10, PM2.5, and NO2) in nine cities in China were considered for analysis. A city model (model-C) based on the data of each city and a unified model (model-U) based on national data were established, and the key pollutants under these conditions were identified. Correlation analysis was performed between each pollutant and the daily global solar radiation. The correlation between O3 and daily global solar radiation was the highest (r = 0.575), while that between SO2 and daily global solar radiation was the lowest. Further, AQI and solar radiation were negatively correlated, while some pollution components (e.g., O3) were positively correlated with the daily global solar radiation. Different key pollutants affected the solar radiation in each city. In Shenyang and Guangzhou, the driving effect of particles on the daily global solar radiation was stronger than that of pollutants. However, there were no key pollutants that affect solar radiation in Shanghai. Furthermore, the prediction performance of model-U was not as good as that of model-C. The model-U showed a good performance for Urumqi (R2 = 0.803), while the difference between the two models was not particularly significant in other areas. This study provides significant insights to improve the accuracy of regional solar radiation prediction and fill the gap regarding the absence of long-term solar radiation monitoring data in some areas.

Copious evidence suggests that rapid urbanization and widespread anthropogenic activities are the main factors resulting in high levels of ambient air pollutant over the Indo-Gangetic Plain (IGP) in India. Continuous monitoring of levels of air pollutants affecting air quality, human health and the ecosystem is essentially required on a day-to-day basis. The influence of pollutants on the air quality, human health and susceptibility of plants is studied widely with the help of various indices, e.g. air-quality index (AQI), air-quality health index (AQHI), air-pollution index (API), air-pollution tolerance index (APTI) and anticipated performance index. In this chapter, we discuss the important indices: AQI, AQHI, API and APTI. As a case study, we have discussed in detail the AQI. We report on the status of ambient air quality (for the year 2016) over the IGP, utilizing the CPCB (Central Pollution Control Board, India) database. Air quality index (AQI) values have been presented systematically in this chapter to better evaluate the air quality associated with various major and potential atmospheric pollutants (available in CPCB database). Ambient data of air pollutants (PM2.5 or PM10, SO2, NO, NO2 and CO) have been retrieved from three sites continuously monitored by CPCB: upwind (Panchkula; states of Haryana), central (Lucknow; states of Uttar Pradesh) and downwind locations (Kolkata; West Bengal) in the IGP. Monthly and seasonally averaged data sets have been discussed and compared for the aforementioned three sites. Results suggest that Lucknow (in central IGP) was more polluted than the Kolkata and Panchkula sites (upwind of major polluting sources in the IGP). Relative to Lucknow, low concentrations of air pollutants at Kolkata suggests the influence of sea- and land-breeze wind systems on ventilation coefficient and efficient dispersion of the pollutants. AQI values at Kolkata ranging between 27 and 137 indicate a good to moderately polluted atmospheric scenario. However, AQI at Lucknow ranging between 301 and 400 indicates very poor air quality, particularly during post-monsoon and wintertime, whereas at Panchkula during most of the time, air quality was found to be satisfactory (AQI: 51-100). The present synthesis documents the air quality scenario over the IGP in a versatile and simplified manner that can be also be utilized for public awareness.

Forest fires that occur in Riau Province due to the rampant clearing of forests used as plantation land, such as oil palm plantations have a negative influence on the air quality of the surrounding area, one of them is Lima Puluh Kota. The purpose of this study was to determine the Air Quality Index (AQI ) hierarchically from Sumatra Island, West Sumatra Province, and larger scale in Lima Puluh Kota Regency and analyze changes in the value of AQI in Lima Puluh Kota in the last few years (2014-2017). This research includes quantitative descriptive research with literary study approach and literature then coordinating national AQI values on Sumatra Island and making more detailed observations in West Sumatra Province, and District of Lima Puluh Kota. The spatial analysis uses the interpolation process (IDW Method). The value in the analysis refers to the prevailing AQI value. The results of the study were fluctuating changes in Sumatra Island AQI values, in 2014 had an average score of AQI 86,796, down in 2017 with an average value of 84,295, after cases and environmental phenomena on the island of Sumatra in the period of 2014-2015, the average AQI value in 2016 dropped to 81.24, in 2017 there have been environmental improvements, this is illustrated by the increase in AQI to 90.471 on the average provincial AQI on Sumatra Island. Positive correlation occurs between the increase and decrease in the value of AQI on the scale of Sumatra Island with concentrations of PM10, SO2, CO and NO2 in the District of Lima Puluh Kota.

During every winter, causalities with disorders via air contamination are rapidly increasing. WHO's 2018 report states that around 7 million individuals die every 12-month period as a result of diseases attributable to air pollution. Due to this one grows extraordinarily crucial towards precisely monitoring and anticipating the grades appropriate contaminants manifested surrounded by this air. The proposed work is to predict AQI accurately with utilizing the data set on different ML model with proper pre-processing technique for finding nature concerning the air rests for the most part signified by its AQI (air quality index) value. In this chapter, it is tried to gauge the air condition in the bounds of a definite zone by utilizing machine learning strategies like support vector regression (SVR), decision tree regression (DTR), multiple linear regression (MLR) and random forest regression (RFR). It has been concluded that which machine learning method are predicting the concerned air nature accurately and all the machine learning models are studied and compared with the use of assorted error metrics, for instance, coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE) and root mean square logarithmic error (RMSLE). The basic outcomes from the models are well analysed and shown that results given by SVR were poor. MLR and DTR were both done acceptably well. RFR played out the finest among all regression examples.

Temporal and spatial trends in air quality in Beijing

Abstract. Trends in air quality across the Northern Hemisphere over a 21-year period (1990–2010) were simulated using the Community Multiscale Air Quality (CMAQ) multiscale chemical transport model driven by meteorology from Weather Research and Forecasting (WRF) simulations and internally consistent historical emission inventories obtained from EDGAR. Thorough comparison with several ground observation networks mostly over Europe and North America was conducted to evaluate the model performance as well as the ability of CMAQ to reproduce the observed trends in air quality over the past 2 decades in three regions: eastern China, the continental United States and Europe. The model successfully reproduced the observed decreasing trends in SO2, NO2, 8 h O3 maxima, SO42− and elemental carbon (EC) in the US and Europe. However, the model fails to reproduce the decreasing trends in NO3− in the US, potentially pointing to uncertainties of NH3 emissions. The model failed to capture the 6-year trends of SO2 and NO2 in CN-API (China – Air Pollution Index) from 2005 to 2010, but reproduced the observed pattern of O3 trends shown in three World Data Centre for Greenhouse Gases (WDCGG) sites over eastern Asia. Due to the coarse spatial resolution employed in these calculations, predicted SO2 and NO2 concentrations are underestimated relative to all urban networks, i.e., US-AQS (US – Air Quality System; normalized mean bias (NMB) = −38% and −48%), EU-AIRBASE (European Air quality data Base; NMB = −18 and −54%) and CN-API (NMB = −36 and −68%). Conversely, at the rural network EU-EMEP (European Monitoring and Evaluation Programme), SO2 is overestimated (NMB from 4 to 150%) while NO2 is simulated well (NMB within ±15%) in all seasons. Correlations between simulated and observed O3 wintertime daily 8 h maxima (DM8) are poor compared to other seasons for all networks. Better correlation between simulated and observed SO42− was found compared to that for SO2. Underestimation of summer SO42− in the US may be associated with the uncertainty in precipitation and associated wet scavenging representation in the model. The model exhibits worse performance for NO3− predictions, particularly in summer, due to high uncertainties in the gas/particle partitioning of NO3− as well as seasonal variations of NH3 emissions. There are high correlations (R > 0.5) between observed and simulated EC, although the model underestimates the EC concentration by 65% due to the coarse grid resolution as well as uncertainties in the PM speciation profile associated with EC emissions. The almost linear response seen in the trajectory of modeled O3 changes in eastern China over the past 2 decades suggests that control strategies that focus on combined control of NOx and volatile organic compound (VOC) emissions with a ratio of 0.46 may provide the most effective means for O3 reductions for the region devoid of nonlinear response potentially associated with NOx or VOC limitation resulting from alternate strategies. The response of O3 is more sensitive to changes in NOx emissions in the eastern US because the relative abundance of biogenic VOC emissions tends to reduce the effectiveness of VOC controls. Increasing NH3 levels offset the relative effectiveness of NOx controls in reducing the relative fraction of aerosol NO3− formed from declining NOx emissions in the eastern US, while the control effectiveness was assured by the simultaneous control of NH3 emission in Europe.

BackgroundThe Air Quality Index (AQI) in the United States is widely used to communicate daily air quality information to the public. While use of the AQI has led to reported changes in individual behaviors, such behavior modifications will only mitigate adverse health effects if AQI values are indicative of public health risks. Few studies have assessed the capability of the AQI to accurately predict respiratory morbidity risks.Methods and findingsIn three major regions of California, Poisson generalized linear models were used to assess seasonal associations between 1,373,165 respiratory emergency department visits and short-term exposure to multiple metrics between 2012–2014, including: daily concentrations of NO2, O3, and PM2.5; the daily reported AQI; and a newly constructed health-based air quality index. AQI values were positively associated (average risk ratio = 1.03, 95% CI 1.02–1.04) during the cooler months of the year (November-February) in all three regions when the AQI was very highly correlated with PM2.5 (R2 ≥ 0.89). During the warm season (March-October) in the San Joaquin Valley region, neither AQI values nor the individual underlying air pollutants were associated with respiratory morbidity. Additionally, AQI values were not positively associated with respiratory morbidity in the Southern California region during the warm season, despite strong associations of the individual underlying air pollutants with respiratory morbidity; in contrast, health-based index values were observed to be significantly associated with respiratory morbidity as part of an applied policy analysis in this region, with a combined risk ratio of 1.02 (95% CI: 1.01–1.03).ConclusionsIn regions where individual air pollutants are associated with respiratory morbidity, and during seasons with relatively simple air mixtures, the AQI can effectively serve as a risk communication tool for respiratory health risks. However, the predictive ability of the AQI and any other index is contingent upon the monitored values being representative of actual population exposures. Other approaches, such as health-based indices, may be needed in order to effectively communicate health risks of air pollution in regions and seasons with more complex air mixtures.

Air pollution has become a serious concern across the world in the last few decades. In specific cities, the air quality index value had changed from very unhealthy to a hazardous level of health concern. Air pollution has a serious impact on daily lives in those cities. Monitoring of air pollution is becoming necessary these days. Air quality monitoring stations are installed to get the air pollution data, which indicates in the air quality index (AQI) value. In order to contain a proper air quality index (AQI) value, it is essential to locate the air quality monitoring stations in the appropriate place of the study area. Several techniques were being used for site selection of air quality monitoring stations for the last few decades. In this short review, all such techniques have been studied systematically, and comprehensive analysis has been reported for further use by the scientific community and policymakers. In this study, the methods used in the site selection of air quality monitoring stations were categorized into four groups. (1) Multi-Criteria Decision Making (MCDM) techniques; (2) Geographical Information System (GIS); (3) hybrid techniques; and (4) miscellaneous. In the site selection of air quality monitoring stations, the decision-makers should consider various parameters based on the study area. While considering various parameters, the problem solving becomes complex. At this point, MCDM techniques, GIS, and Hybrid techniques are found to be helpful tools for the decision-makers.

The current study aims to characterize and estimate the particulate matter (PM) exposure level of the population near an opencast coal mine. PM concentrations of different sizes were monitored at 32 locations distributed uniformly in the study area for spatial profiling and at 1 location for analysing the temporal variations and characterization of dust. Health impacts of PM to nearby residents were estimated using the air quality index (AQI) values and were cross-validated using the health survey data. The monitoring results indicated that the 15 min average concentrations of PM10 and PM2.5 were 2.3–2.4 times of the corresponding 24 h National Ambient Air Quality Standards (NAAQS) in all the monitoring stations. Low wind speed during monitoring campaign that resulted in little PM dispersion is suggested to be the reason for this. AQI levels at five villages surrounding the mine were “moderate to severe” during morning-hours that improved to “satisfactory to moderate” during day-time. Eye irritation and respiratory problems were the two most adverse effects experienced by the residents living nearby to the mine. The health survey data and the corresponding AQI values indicate that respiratory problem is well correlated with the AQI values. The dust contains mainly six major elements in the order of O > C > F > Si > Al > Fe > Ca, accounting for 95% of the weight percentages of the 20 elements for which the characterization was carried out.

The clean air plan in India involves a set of rules, policies, and initiatives targeted at improving the air quality and public health by way of decreasing emissions from various sources. The study aims to evaluate the impact of National Clean Air Program (NCAP) on lowering air pollution levels and improving public health outcomes in Kota city, Rajasthan, highlighting progress, challenges, and the need for sustained emission control efforts. Kota's selection for this study highlights its significance as an educational hub, attracting students from all over India. The rapid population growth and increased vehicle emissions in the city cause adverse impacts on air quality. Improving air quality will not only enhance the health of residents and students but also contribute to a more conducive learning environment. The action plan of NCAP involves enforcing the construction and demolition waste management rules 2016, implementing emission control measures like water sprinkling and covered transport for construction activities, and extensive campaigns against open burning of biomass and waste. It also includes regular checks on industrial emissions, proper waste collection and disposal, and mandatory green belt development in residential areas. It employs a mixed-method approach, combining air quality monitoring data collected from the Central and State Pollution Control Boards from 2014 to 2023. It also examines trends in key pollutants, including NO2, SO2, and PM10, and analyzes the effect of regulatory measures such as emission controls and waste management rules. The study reveals a decreasing trend in NO2 (nitrogen dioxide) levels in Kota city, Rajasthan from 35.35 µg/m³ to 29.90 µg/m³ during 2014 to 2023, showing a significant drop during the COVID-19 lockdown. Similarly, PM10 (particulate matter) levels peaked at 153.28 µg/m³ in 2018 but saw a significant reduction to104.80 µg/m³ by 2020, indicating an improvement in air quality. However, SO2 (sulfur dioxide) concentrations slightly increased in 2019-2023 compared to 2014-2018. The air quality index (AQI) improved modestly but frequently surpassed 100, indicating hazardous air quality for vulnerable populations. The study concludes that while the NCAP in India has significantly improved air quality, challenges remain, with NO2 levels rebounding post-COVID-19 lockdown and persistent high particulate matter levels. It is recommended to ensure stricter enforcement of emission control measures, enhanced monitoring systems, and public awareness campaigns. Future work should focus on the long-term health impacts of particulate matter and strategies to achieve sustained air quality improvements in high-risk regions.