2023 CiteScore: 1.9
eISSN: 2476-3071
Editor-in-Chief:
Ramin Nabizadeh Nodehi, Ph.D.
Vol 10 No 1 (2025): Winter 2025
Original Research
-
Introduction: Air pollution can trigger the attack in asthmatic patients if uncontrolled. Previous works focused on controlling pollution by proposing algorithms to predict air pollution. While these prediction algorithms save
patients from attack triggers, they have limitations such as prediction accuracy, mathematical complexity, and lack of adequate patient notification systems.
Materials and methods: This study proposed a novel Intelligent Air Pollution Prediction (IAPP) algorithm based on optimizing Random Forest Regression (RFR) to predict air pollution and send an alert message to the patient and hospital in real time. Meanwhile, IAPP utilized reliable data from Internet of Things (IoT)-based air pollution detection nodes. The performance of IAPP was evaluated in a real-world environment during the peak pollutant season to test the prediction accuracy of air pollution.
Results: Results showed that the proposed IAPP achieved a high prediction accuracy of 99.98% with an R squared value of 0.99. This demonstrated that the IAPP algorithm based on the RFR model can effectively protect asthmatic patients from attack triggers.
Conclusion: As a result, the IAPP algorithm reduces hospital visits during high pollution and enables patients to complete their daily activities without obstacles or absence. -
Introduction: In Ghana, the road subsector serves as the primary mode of transport, accounting for 96% of passenger and cargo traffic. Air quality issues have been exacerbated by the prevalence of aged and poorly performing vehicular engines, posing significant health risks. This study, therefore, investigated ambient air quality during the dry season along key roadways in Winneba, located in the Central Region of Ghana.
Materials and methods: Stationary monitoring devices, including EPAM-7500 particulate monitors and Aeroqual Series 500 gas monitors were used to measure concentrations of Particulate Matters (PM₂.₅, PM₁₀), Carbon monoxide (CO), Nitrogen Oxides (NOₓ), Sulphur dioxide (SO2), and Volatile Organic Compound (VOCs) including temperature and relative humidity. Data collection was conducted using a purposive rotation among the selected roads, with each monitoring session replicated three times.
Results: Winneba junction-WindyBay Avenue (WJ’WBA) exhibited the highest concentrations of CO (2125±182.40 µg/m³) whilst the highest level of NOₓ (198±27.01 µg/m³) was at Winneba central-Donkorkyiem (WC’D). PM2.5 concentrations at WJ’WBA was the lowest (871 ± 79.54 µg/m³), while the Control Road (CR) had highest mean concentration of 902 ± 107.16 µg/m³. The PM10 highest mean level was at WJ’WBA (931±51.29 µg/m³) and lowest at the CR (874±90.42 µg/m³). Levels of SO₂ and VOCs were below the detection limits of the gas monitors. In all, levels of the measured pollutants did not differ significantly (p<0.05) between the sampling locations, but exceeded the pollution thresholds established by the World Health Organization (WHO) and
the United States Environmental Protection Agency (USEPA). All monitored roads were classified as "extremely polluted" based on the Air Quality Index (AQI). The Exceedance Factors (EF) confirmed the severity of pollution levels. Statistical analyses, correlation and regression methods, indicated no significant relationship between weather conditions and air pollution levels.
Conclusion: These findings underscore the severity of air quality issues in Winneba and the urgent need for enhanced monitoring systems including the implementation of regular vehicular emission testing and the use of bioindicators for monitoring vehicular pollutants to mitigate both human and environmental health risks. -
Introduction: Air pollution is a significant global health challenge, contributing to the deaths of millions of people annually. Among these pollutants, Particulate Matter (PM2.5) is the most harmful to the respiratory system causing serious health problems. This study focused on predicting PM2.5 in the air of Islamabad, capital of Pakistan by using machine learning and deep learning models.
Materials and methods: Two machine learning models (Decision Tree and Random Forest) and four deep learning models including Multi-Layer Neural Network (MLNN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU) are used in the study. Each model's performance was assessed by using statistical indicators including coefficient of determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Relative Root Mean Square Error (RRMSE). These models are also ranked based on their performance by compromise programming technique.
Results: Machine learning models performed better in the training phase by achieving higher R2 values of 0.98 and 0.97 but couldn’t maintain the same performance in the testing phase. Whereas the deep learning models
performed best in both the training and testing phases. MLNN model attained higher R2 value of 0.98 in training and 0.88 in testing and is evaluated as top-ranked prediction model in predicting particulate matter PM2.5. Whereas, LSTM, GRU, RNN, Decision Tree, and Random Forest are placed at the 2nd, 3rd, 4th, 5th, and 6th positions having R2 values of 0.86, 0.87, 0.82, 0.99, and 0.97 during training and 0.71, 0.69, 0.69, 0.75, and 0.85 respectively during testing.
Conclusion: Deep learning models, especially MLNN, showed strong performance in predicting PM2.5 as compared to the machine learning models. -
Introduction: Air quality forecasting, particularly predicting Particulate Matter (PM2.5 ) concentrations, has gained significant attention due to its critical implications for public health and environmental management.
Accurately predicting PM2.5 , a harmful air pollutant associated with respiratory and cardiovascular diseases, is vital for effective air quality management in densely populated urban areas.
Materials and methods: This study uses various meteorological and environmental data combinations in Tehran, Iran, this study investigates the efficacy of three predictive modeling techniques Auto Regressive Integrated Moving Average (ARIMA), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory (LSTM) in forecasting daily and monthly PM2.5 levels. The models were evaluated based on performance metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R² scores.
Results: Results indicate that XGBoost excelled in daily predictions when using solely meteorological data, achieving an R² score of 0.998674, while ARIMA demonstrated strong predictive capacity but struggled with added complexity. LSTM maintained reasonable performance amidst increased data input but faced challenges in both daily and monthly forecasts. Monthly predictions from all models proved less reliable, particularly with ARIMA yielding negative R² values, indicating suboptimal performance compared to simplistic models.
Conclusion: The findings highlight the importance of model selection and feature engineering in accurately predicting PM2.5 levels. The study suggests a shift towards hybrid modeling approaches and incorporating diverse environmental data to enhance forecasting accuracy in air quality management, particularly for long-term predictions. -
Introduction: There are many artisans brick kilns near the communities in Nejapa city. The reported prevalence of respiratory diseases or symptoms in this city is 7.2%. This study aims to determine the relationship between exposure to smoke generated by artisan brick kilns and the presence of respiratory symptoms in residents ≥18 years of age in a gated community in the Nejapa city.
Materials and methods: This is an analytical cross-sectional study that included 46 individuals. Data were collected through an interview form and an observation form. Frequency analysis, association measures, and prevalence ratios were calculated. This study received ethical approval.
Results: Twenty-nine individuals reported respiratory symptoms such as sneezing, itching, and nasal congestion. Twenty-eight people reported experiencing respiratory symptoms. The most frequently reported symptoms were sneezing, nasal itching, nasal congestion, and cough. Daily exposure to smoke from the brick kilns doubled the risk of nasal congestion. Living at 61 m or more from the brick kilns increased the risk of nasal congestion by 3.22 times. Living at a distance between 46 and 60 m from the kilns doubled the risk of coughing.
Conclusion: There is a relationship between the development of respiratory symptoms and daily exposure to smoke generated by artisan brick kilns. The risk of developing symptoms varies depending on the distance between the individual’s residence and the brick kilns. -
Introduction: Air pollution is one of the world’s major global issues. In this research we aimed to calculate the impact of weather factors on air pollution and show the results by using the econometric method of data analysis. After that, we also studied the effect of car exhaust on air pollution in relation to urban congestion and car age.
Materials and methods: Data cleaning methods used in this research include as correcting structural errors, dealing with missing data and sorting data. For calculation, correlation analysis was used to find the relationship of the time series dataset, and then used panel model for the test results, which are estimated by least squares method. In correlation analysis, used air quality and weather’s data of Ulaanbaatar city’s last 3 years.Results: As a result of the research, we found that the amount of air pollutant depends on weather factors, that is, location and wind speed have the greatest influence on air pollution. Also the decrease in the amount of sulfur dioxide is due to the ban on burning raw coal in the capital. Our findings indicate that the nitrogen dioxide level in the residential area is high even in the warm season, which is due to congestion and age of vehicles.
Conclusion: The most important weather factors affecting air pollution are location and wind direction. In the future, with comprehensive data collection, future research could better identify sources of air pollution and develop effective mitigation strategies. -
Introduction: In the current study of specific air pollutants, including levels of NO2 , SO2, and Particulate Matter (PM10), as well as the Air Quality Index(AQI), has been done on the current state of air quality in Lucknow.
Materials and methods: To assess the ambient air quality in Lucknow, this secondary data was recorded from three key sources: Uttar Pradesh Pollution Control Board (UPPCB), Central Pollution Control Board (CPCB), and
Centre for Science and Environment (CSE), from five monitoring stations across various areas of the city, including residential areas like Aliganj and Mahanagar, commercial sectors like Hazratganj and Ansal TC, and the industrial sector of Talkatora.
Results: The results showed that, within a range of 111.24 to 240.89 μg/m3, the average 24-h PM10 concentration was evaluated as 178.09 μg/m3. The average concentrations of SO2 and NO2 over 24 h ranged between 6.96 and 11.50 and 25.28 and 44.41 μg/m3 respectively. Seasonal fluctuations in PM10, SO2
, and NO2 were observed, with maximum values recorded in winter at 218.20, 10.32, and 41.43 μg/m3 , and minimum values recorded in monsoon season at 123.47, 7.19, and 28.31 μg/m3 , respectively. Maximum values
were recorded in winter at 177 μg/m3 , while lowest values were recorded in monsoon at 111 μg/m3.
Conclusion: The study focused on monthly and seasonal variations in PM10, SO2, and NO2 levels at five representative locations in Lucknow. Key findings revealed that while the annual PM10 concentration exceeded National Ambient Air Quality (NAAQ) standards. The SO2 and NO2 concentrations remained below recommended levels throughout the year, with lower concentrations observed during the monsoon season compared to summer and winter. -
Introduction: Introduction: Air pollution is a significant environmental challenge globally, exacerbated by industrialization and increasing vehicular emissions. This study focuses on Jaipur, India, where rapid urbanization and industrial growth have intensified pollution levels, impacting public health and environmental quality.
Materials and methods: This study utilized secondary data from the Rajasthan State Pollution Control Board and satellite imagery obtained from the NRSC BHUVAN. Geographic Information System (GIS) tools were employed to analyze pollution data from six sample sites in Jaipur. Interpolation techniques, including Kriging and Inverse Distance Weighting (IDW), were used to map the spatial distribution of pollutants.
Results: From 2011 to 2019, Jaipur experienced varying levels of air pollution, with high concentrations of Particulate Matter (PM10), Sulfur dioxide (SO₂), and Nitrogen dioxide (NO₂) observed in industrial and commercial zones, such as the Vishwakarma Industrial Area and Ajmeri Gate. Areas with natural features, like Jhalana Dungri and the Malaviya Industrial Area, consistently showed lower pollution levels.
Conclusion: The study highlights significant spatial and temporal variations in air quality across Jaipur, influenced by industrial activities and vehicular emissions. Effective pollution control measures and urban planning strategies are essential to mitigate the adverse impacts of air pollution on public health and environmental sustainability in Jaipur and similar urban centers.
