Air Quality Index Research Articles

Meteorological Visibility Estimation Using Landmark Object Extraction and the ANN Method

Visibility can be interpreted as the largest distance of an object that can be recognized or detected under a bright environment that can be used as an environmental indicator for weather conditions and air pollution. The accuracy of the classical approach of visibility calculation, in which meteorological laws and image feature extraction from digital images are used, depends on the quality and noise disturbances of the image. Therefore, artificial intelligence (AI) and digital image approaches have been proposed for visibility estimation in the past. Image features for the whole digital image are generated by pre-trained convolutional neural networks, and the Artificial Neural Network (ANN) is designed for correlation between image features and visibilities. Instead of using the information of the whole digital images, past research has been proposed to identify effective subregions from which image features are generated. A generalized regression neural network (GRNN) was designed to correlate the image features with the visibilities. Past research results showed that this method is more accurate than the classical approach of using handcrafted features. However, the selection of effective subregions of digital images is not fully automated and is based on manual selection by expert judgments. In this paper, we proposed an automatic effective subregion selection method using landmark object extraction techniques. Image features are generated from these LMO subregions, and the ANN is designed to approximate the mapping between LMO regions’ feature values and visibility values. The experimental results show that this approach can minimize the reductant information for ANN training and improve the accuracy of visibility estimation as compared to the single image approach.

Enhancing urban air quality prediction using time-based-spatial forecasting framework.

Air quality forecasting plays a pivotal role in environmental management, public health and urban planning. This research presents a comprehensive approach for forecasting the Air Quality Index (AQI). The proposed Time-Based-Spatial (TBS) forecasting framework is integrated with spatial and temporal information using machine learning techniques on data collected from a wide range of cities. The TBS employs Convolutional Neural Networks (CNNs) to capture spatial dependencies based on normalized latitude and longitude coordinates of the cities. Simultaneously, time series model, specifically the ARIMA (AutoRegressive Integrated Moving Average)was employed to capture temporal dependencies using pollutant concentration readings over time. The dataset included information such as date, time, pollutant concentrations and AQI was further preprocessed and divided into training and testing sets. The CNN was configured to utilize the normalized latitude and longitude grid, while the ARIMA model concurrently processed the pollutant concentrations. The model was trained on the training dataset, and a 6hour forecast is generated for each test instance. The outcomes demonstrate the TBS model's ability to accurately predict AQI values. The integration of CNNs and time series model allowed for an clearer and deeper understanding of geographical and pollutant concentration factors that contribute to air quality variations.

Development of a respiratory virus risk model with environmental data based on interpretable machine learning methods

In recent years, numerous studies have explored the relationship between atmospheric conditions and respiratory viral infections. However, these investigations have faced certain limitations, such as the use of modestly sized datasets, a restricted geographical focus, and an emphasis on a limited number of respiratory pathogens. This study aimed to develop a nationwide respiratory virus infection risk prediction model through machine learning approach. We utilized the CRFC algorithm, a random forest-based method for multi-label classification, to predict the presence of various respiratory viruses. The model integrated binary classification outcomes for each virus category and incorporated air quality and meteorological data to enhance its accuracy. The data was collected from 31 regions in China between 2016 and 2021, encompassing pathogen detection, air quality indices, and meteorological measurements. The model’s performance was evaluated using ROC curves, AUC scores, and precision-recall curves. Our model demonstrated robust performance across various metrics, with an average overall accuracy of 0.76, macro sensitivity of 0.75, macro precision of 0.77, and an average AUC score of 0.9. The SHAP framework was employed to interpret the model’s predictions, revealing significant contributions from parameters such as age, NO2 levels, and meteorological conditions. Our model provides a reliable tool for predicting respiratory virus risks, with a comprehensive integration of environmental and clinical data. The model’s performance metrics indicate its potential utility in clinical decision-making and public health planning. Future work will focus on refining the model and expanding its applicability to diverse populations and settings.

Analysis of IoT Applications in Highly Precise Agriculture Farming

Background: The IoT (Internet of Things) assigns to the capacity of Device-to-Machine (D2M) connections, which is a vital component in the development of the digital economy. IoT integration with a human being enables real-time decision-making in communication, collaboration, and technology analytics. Furthermore, environmental factors impacting plants, such as air humidity, temperature, air quality index, and soil wetness, are not frequently documented, emphasizing the development of a data monitoring system for future agricultural research and development. Methods: An IoT-based Intelligent Farming System is proposed. An innovative IoT-based intelligent farming system is developed that integrates real-time data monitoring, machine learning algorithms, and IoT technology to address the identified gaps and challenges. Result: In the face of climate change, extreme weather, and environmental constraints, increased food demand must be satisfied. Intelligent agriculture enabled by IoT technology can reduce waste and increase productivity for producers and farmers, from fertilizer use to tractor trips. Conclusion: In conclusion, this paper provides insightful and informative commentary on the progress made in technology within the agriculture industry and the challenges that still need to be overcome to achieve optimal outcomes.

Developing a machine learning model using satellite data to predict the Air Quality Index (AQI) over Korba Coalfield, Chhattisgarh (India)

Developing a machine learning model using satellite data to predict the Air Quality Index (AQI) over Korba Coalfield, Chhattisgarh (India)

Leveraging pretrained transformers for enhanced air quality index prediction model

Leveraging pretrained transformers for enhanced air quality index prediction model

A novel ensemble framework based on intelligent weight optimization and multi-model fusion for air quality index prediction

A novel ensemble framework based on intelligent weight optimization and multi-model fusion for air quality index prediction

SPATIAL ASSESSMENT OF GASEOUS POLLUTANTS (PM2.5, PM10 SO2, NO2, CO2, CO) ON AIR QUALITY USING AIR QUALITY INDEX NORTH-EASTERN NIGERIA

In response to the alarming rate of air pollution, a study was carried out at Savannah Sugar Company, Ashaka Cement Plc, and Alkaleri Kaolin Industry in North Eastern Nigeria with the following objectives: to assess the amount of hazardous substances in the atmosphere, to examine the impact of industrial activities on air quality, and to compare the overall results of the air quality assessment with the air quality index (AQI) rating. The Air Ae Steward Meter (Haz-Dust Tm; PM2.5 and PM10, Model: HD1000) and Gasman Air Monitoring Meter (Models 1200-19831) were used to evaluate the air quality state of the studied sites. In the industrial districts, the findings of the air quality assessment were examined according to the following ranges: SO2 (0.665-0.680), NO2 (0.30-0.315), CO (35.88-36.84), and CO2 (8125.78-8707.94). The ranges for PM2.5 and PM10 were 104.02-126.03µg/m3 and 138.43-161.10µg/m3, respectively. The results showed that Ashaka had the highest concentrations in all the parameters due to some heavy equipment’s with more anthropogenic activities. The air quality Index (AQI) ratings of the obtained results showed that, in the three emerging industrial sites indicated a category for ‘Unhealthy for sensitive group’ (Orange) to ‘Unhealthy’ (Red) for PM2.5 and PM10 while for CO was rated Good (Green), NO2 and SO2 was rated Moderate (Yellow) and CO2 was rated hazardous (Maroon). There is need for a routine monitoring of the air quality in Northern part of Nigeria and in Nigeria as a whole to ensure safety, and a few helpful recommendations were suggested in this study for positive impacts on the environment.

Air Quality Index Prediction Using Machine Learning Techniques

Air pollution poses a serious threat to public health and the environment, making accurate monitoring and prediction crucial. This research focuses on Air Quality Index (AQI) prediction using machine learning (ML) techniques. We analyze pollutant levels, including PM2.5, NO₂, CO, and O₃, along with meteorological factors such as temperature, humidity, and wind speed. The dataset is collected from cloud-based sources, preprocessed, and split into 80% training and 20% testing sets [1]. Various ML models—Linear Regression, K-Nearest Neighbors (KNN), and Lasso Regression—are applied and evaluated using Mean Squared Error (MSE) and Mean Absolute Error (MAE). The results demonstrate that KNN outperforms other models in AQI prediction. This study highlights the potential of ML in environmental management, enabling timely interventions for air pollution contro[2].

Smart electronic device for air quality and exposure risk assessment

ABSTRACT This article reports on the measurement of air pollutants and assessment of health exposure risks in two reference hospitals in the city of Yaoundé, using a locally manufactured smart electronic device for the measurement of highly toxic air pollutants. This low-cost device is based on an Atmega328 microcontroller, toxic gas sensors (O3, PM2.5, CO, CO2 and NO2), temperature (T), relative humidity (RH) sensors, and XBee modules to establish the Internet of Things (IoT). In each of the two hospitals, 2 weeks of measurements conducted from October 15 to 30, 2023 at Biyem-assi Hospital and from September 1 to 15, 2023 at Central Hospital. The average values obtained were 0.96 ± 0.06 ppm and 0.37 ± 0.09 ppm for O3, 39.66 ± 10 µg/m3 and 39.72 ± 10 µg/m3 for PM2.5, 0.41 ± 0.01 ppm and 0.42 ± 0.02 ppm for CO, 316.55 ± 63 ppm and 305.84 ± 89 ppm for CO2, and 0.43 ± 0.01 ppm and 0.45 ± 0,02 ppm for NO2 in Biyem-assi and Central Hospitals, respectively. These values were used to assess the risk of exposure through the Air Quality Index (AQI) and the Air Quality Health Index (AQHI2.5).

Temporal dynamics of indoor air quality: Investigating the impact of cooking activities and ventilation efficiency in shared kitchens

Indoor air quality (IAQ) plays a pivotal role in safeguarding human health and well-being, particularly in shared spaces like hostel kitchens where cooking is frequent. This study investigates the temporal dynamics of IAQ in shared kitchens, focusing on pollutant fluctuations during cooking activities and the role of ventilation efficiency. Using advanced monitoring tools, volatile organic compounds (VOCs), Carbon Dioxide (CO2), and Air Quality Index (AQI) were analyzed over a seven-day period. Results indicate pronounced peaks in pollutant levels during morning and evening cooking hours, attributed to frying, grilling, and other high-emission activities, compounded by insufficient ventilation. Comprehensive visualizations such as scatter plots, heatmaps, and 3D scatter graphs reveal actionable insights into pollutant behavior over time. Based on these findings, interventions including advanced ventilation systems, cleaner cooking technologies, and real-time air quality monitoring are proposed. These measures aim to mitigate IAQ challenges, ensuring healthier living environments for residents.

A comparative study of traditional machine learning and hybrid fuzzy inference system machine learning models for air quality index forecasting

A comparative study of traditional machine learning and hybrid fuzzy inference system machine learning models for air quality index forecasting

Post-War Air Quality Index in Mosul City, Iraq: Does War Still Have an Impact on Air Quality Today?

The air quality in Mosul was adversely affected both directly and indirectly during and after the conflict phase, spanning from the occupation to the liberation of the city from ISIS (2014–2017). Direct impacts included the ignition of oil fields and sulphur deposits, as well as the use of military weapons and their propellants. Indirectly, the air quality was also compromised by various other factors negatively affecting the quality due to excessive emission levels of air pollutants, such as particulate matter (PM), sulphur dioxide (SO2), nitrogen dioxide (NO2) and other toxic gases. Six important locations in the city of Mosul were selected, and the concentrations of the parameters PM2.5, PM10, formaldehyde (HCHO), total volatile organic compounds (TVOC), NO2 and SO2 were determined at monthly intervals during the year 2022. The sites were selected both according to their proximity and their specific distance from the direct conflict zone. The aim was to assess the present pollutant levels based on WHO guidelines and to compare the results with previous pre-war studies to understand the long-term war impact on air quality. The results showed that the annual average values of PM2.5, PM10 and NO2 were above the WHO limits at all locations throughout the year. In contrast, the annual average values of TVOC, HCHO and SO2 were within the limits in the hot months but exceeded them in the cold months (December to March), which can be attributed to the use of heating material in winter. Two sites revealed higher pollution levels than the others, which can be attributed to their proximity to the devastated areas (conflict zones), high traffic density and a high density of power generators. These factors were further exacerbated by post-war migration from the destroyed and unsafe areas. Thus, in addition to the short-term effects of burning oil fields and sulphur deposits, as well as airborne weapon emissions, the increase in traffic, the use of decentralized power generators, and the higher demand for heating oil, progressive desertification due to deforestation and the destruction of extensive green areas, as well as increasing and unaddressed environmental violations in general, can be held responsible for declining air quality in the urban area. This work should be considered as preliminary work to emphasise the urgent need for conventional air quality monitoring to consolidate air quality data and monitor the effectiveness of different approaches to mitigate war-related air quality deterioration. Possible approaches include the implementation of air purification technologies, the preservation of existing ecosystems, the replacement of fossil energy sources with renewable energy options, proactive and sustainable urban planning and enforcing strict air quality regulations and policies to control and reduce pollution levels.

Impact of Ambient Air Pollution on Reduced Visual Acuity Among Children and Adolescents

ABSTRACT Purpose Previous studies have assessed the impact of air pollution on myopia from the individual level, while none of them have explored the role of air pollution in visual health disparities between different regions from the area level. This ecological study aimed to investigate the impact of ambient air pollution on reduced visual acuity (VA). Methods The data were derived from the Chinese National Survey on Students’ Constitution and Health (CNSSCH) conducted in 2014 and 2019, which involved 261,833 and 267,106 students respectively. The participants were 7–22 years old randomly selected from 30 mainland provinces in China. Locally weighted scatterplot smoothing (LOESS) regression models and fixed-effects panel regression models were used to explore the associations of provincial-level prevalence of reduced VA with air quality index (AQI), fine particulate matter ;(PM2.5), PM10, sulfur dioxide (SO2), carbon monoxide (CO), nitrogen dioxide (NO2) and ozone (O3) concentrations. Results There were nearly linear positive dose-response relationships between AQI, air pollutant concentrations and the prevalence of reduced VA. After adjusting for covariates, an interquartile range increase in PM2.5 exposure was significantly associated with a 5.0% (95% confidence interval, 0.7%-9.3%) increase in the prevalence of reduced VA, whereas no significant associations were observed between AQI, the other five pollutants and the prevalence of reduced VA. Conclusion Regions with more polluted air tend to have a higher prevalence of reduced VA. Exposure to PM2.5 might be an important risk factor for myopia among children and adolescents.

Applying Deep Learning for Wildfire Identification: Economical and Accessible Solutions Leveraging Small Datasets

Wildfires significantly impact human health, air quality, visibility, weather, and climate change and cause substantial economic losses. While state and county-operated air quality monitors provide critical insights during wildfires, they are not available in all regions. This highlights the need for affordable, accessible tools that allow the general public to assess air quality impacts. In this study, we apply machine learning with deep neural networks to diagnose air quality rapidly from sky images taken at the Pacific Northwest National Laboratory in Richland, WA, USA. Using a convolutional neural network (CNN) framework, we trained a deep learning model to classify air quality indices based on sky images. By leveraging transfer learning, our approach fine-tunes a pre-trained model on a small dataset of sky images, significantly reducing training time while maintaining high accuracy. Our results demonstrate the potential of deep learning to provide rapid air quality diagnostics during wildfire episodes, offering early warnings to the public and enabling timely mitigation strategies, particularly for vulnerable populations. Additionally, we show that lower respiratory infections pose the highest health risk during acute smoke exposures. Reactive oxygen species (ROS) from wildfire particles further exacerbate health risks by triggering inflammation and other adverse effects.

RSTMAQI: framework for prescriptive analysis and precision factor in forecasting on air quality index

RSTMAQI: framework for prescriptive analysis and precision factor in forecasting on air quality index

P1273 High Crohn's Disease incidence associated with multiple heavy metal contamination in agricultural soils: findings from the CROPS project in Northern France

Abstract Background Crohn's Disease (CD) is a chronic intestinal disease with an unclear etiology and suspected environmental risk factors. The CROPS (CROhn’s disease and Pollution of Soils) project was initiated in Northern France to investigate links between the high incidence of CD and environmental pollutants. In this context, we combined data of a population-based registry of Inflammatory Bowel Disease (IBD) with environmental sampling data to identify the environmental profile of multi-contamination associated with high incidence. Methods This ecological study was conducted at the municipal level within the coverage area of the registry in Northern France. All patients diagnosed between 2000 and 2017 were included (n=9,019). Spatial clusters of significantly high (n=4) and low (n=4) CD incidence, adjusted for age and sex, were identified based on patients' residence addresses at diagnosis. Within these clusters, environmental sampling was performed across 240 sites using a hexagonal grid to ensure 30 samples per cluster. A total of 490 parameters were analyzed: 306 in soil (including emerging pollutants such as hormones and antibiotics, polycyclic aromatic hydrocarbons [PAHs], heavy metals, and pesticides), 152 in tap water (examining heavy metals and PAHs), and 30 in lichens (assessing heavy metals as indicators of air quality). Multi-contamination indices, such as the Mean Impregnation Ratio (MIR) and Pollution Index, were applied. Data analysis included Principal Component Analysis (PCA), Hierarchical Cluster Analysis (HCA), and Analysis of Variance (ANOVA) tests. Results High-incidence clusters, predominantly agricultural, had elevated heavy metal concentrations in soil (notably chromium, arsenic, zinc, and nickel), sulfadiazine in soils, high nitrate levels in water, and heavy metals in lichens. Low-incidence clusters, with greater urbanization, showed elevated PAHs in soil, heavy metals in water, and BPA in soils. Pollution profiles aligned with different land covers, with significant findings for agricultural lands (p<0.0001). A positive correlation between the relative risk and soil’s MIR for heavy metals in agricultural zones was noted (r=0.557, p=0.005). Conclusion These findings suggest a possible link between high CD incidence and heavy metal exposure in agricultural lands. Profiles of pollution were created for each cluster. Future studies should expand on pesticide and agricultural pollutant analysis to strengthen this hypothesis, and consider individual-level epidemiological approaches to further elucidate these potential environmental risk factors.

Association of Cardiovascular Disease Mortality and Ambient Temperature Variation in Shanghai, China: Beyond Air Quality Index PM2.5

Evidence from megacity registry data regarding the independent association between ambient temperature and cardiovascular disease (CVD) mortality, after accounting for Particulate Matter 2.5 (PM2.5), remains scarce. In this study, we collected 308,116 CVD mortality cases in Shanghai from 2015 to 2020. The distributed lag non-linear model (DLNM) was utilized. The daily PM2.5 concentration was transformed using a natural spline (ns) function and integrated into the model for adjustment. The DLNM analysis revealed that the exposure–response curve between daily temperature and CVD mortality approximated an inverted “J” shape, consistent for both women and men. The minimum mortality temperature (MMT) for total CVD mortality was 25 °C, with an MMT of 26 °C for females and 24 °C for males. The highest relative risk (RR) of CVD mortality was 2.424 [95% confidence interval (95% CI): 2.035, 2.887] at the lowest temperature of −6.1 °C, with 2.244 (95% CI: 1.787, 2.818) for female and 2.642 (95% CI: 2.100, 3.326) for male. High temperatures exert acute and short-term effects, with the peak risk occurring on the day of exposure. In contrast, the risk from low temperature peaks on day 3 of the lag time and subsequently declines until days 16–21. This study offers evidence-based support for the prevention of temperature-induced CVD mortality.

Associations between water exposure and the development of amyotrophic lateral sclerosis: a matched case-control study

Objective Previous studies have hinted at an association between water exposure and the development of ALS. However, proximity measures to these water sources have been limited to questionnaires or large buffers due to a lack of fine geospatial measures. They also do not distinguish the various classes of hydrographic features. Thus, we created a robust database to investigate the association between proximity to water bodies at place of residence and the development of ALS. Methods A matched (sex and year of birth) case-control study was conducted in New Brunswick, Canada from January 2003 to February 2021. Study population included 304 ALS patients and 1207 controls with their historical postal codes linked to spatial proximity datasets and air pollution index indicators (proxy measures for contamination by run-off). Results Odds of ALS were not significantly associated with proximity to water bodies, even within a 250 m buffer from place of residence (Oceans: 1.10, 0.60–2.00 [95% CI], Reservoirs/Ponds/Lakes: 1.24, 0.47–3.30 [95% CI]). As for interaction models investigating proximity to potentially contaminated water bodies, none of the final fitted models observed an association between proximity to water bodies with indicators of potential run-off sources and the development of ALS. Conclusions No significant association between proximity to water bodies at place of residence and the development of ALS were observed in the current study. Future studies should consider taking direct measurements of water quality or utilize geomaps of spraying activities and cyanobacteria blooms alongside proximity measures. Household water quality is another avenue to explore, particularly well water use.

A machine learning interpretation of the correlation between poverty and air pollution in the contiguous United States

The correlation between poverty and air pollution in the contiguous United States is a widely debated issue, often suggesting that impoverished areas suffer higher pollution levels due to socioeconomic disparities. However, existing studies frequently lack the integration of advanced analytical techniques and fail to account for a comprehensive range of variables. This research paper addresses these gaps by employing sophisticated machine learning models to analyze an extensive dataset encompassing various socioeconomic and environmental metrics. Utilizing linear regression, decision trees, and neural networks, we rigorously examined the data. While the variables were able to predict county-wide poverty rates to reasonably low RMSE and MAE values, our results indicate no significant correlation between poverty levels alone with air pollution indices. The latter finding challenges conventional understanding and highlights the complexity of the relationship between socioeconomic status and environmental quality. By offering a data-driven perspective, our study encourages policymakers to reconsider the factors influencing environmental justice and to look beyond economic status alone. Our work underscores the necessity for further investigation into other potential determinants of pollution, contributing to the discourse on environmental equity. This research provides a fresh, nuanced view that questions established beliefs and underscores the multifaceted nature of socioeconomic-environmental interactions.