Journal of Air Pollution and Health
Volume:8 Issue: 3, Summer 2023

Air pollution is a major environmental challenge worldwide and predicting air quality is key to regulating air pollution. The extent of air pollution is quantified by the Air Quality Index (AQI). Air quality forecasting has become an important area of research. Deep Neural Networks (DNN) are useful in predicting the AQI instead of traditional methods which involve numerous computations. The aim of this research paper is to investigate the use of the deep neural networks as a framework for predicting the air quality index based on time series data of pollutants.

To resolve this problem, the study proposes a DNN to develop the best model for predicting the AQI. Long Short-Term Memory (LSTM) and Bi-directional LSTM have been introduced in the study to understand and predict the relationship between the pollutants affecting the AQI. The model’s performance is evaluated using the metrics, Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and coefficient of determination (R2). To conduct the study, real-time hourly data for the period November 2017 to January 2020 from an air quality monitoring station was considered for the proposed capital region of the state of Andhra Pradesh in India.

The multivariate modeling considers seven pollutants as independent variables and AQI as the target variable. After experimenting and training the algorithm on the dataset, Bi-directional LSTM was shown to have the lowest MAE and RMSE values and the highest R2, indicating that it has the highest accuracy in AQI prediction.

The development of a capital city involves massive construction activity resulting in air pollution. The results are helpful to the authorities to monitor the quality of air of develop air quality management programs thus avoiding the impact of air pollution on health.

Discernable air pollution occurs in most developing countries due to rapid urbanization which can be parameterized by air, humidity, population density, temperature, contaminants, exorbitant fossil fuel consumption, and inadequate transportation. Nitrogen dioxide (NO2), one of the most widely recognized air pollutants, has a detrimental impact on human health explicitly or implicitly and considerably influences on atmospheric composition.

In this study, NO2 intensity was analyzed from 2018 with aiming to monitor spatiotemporal changes in Dhaka and its surrounding areas with the Tropospheric Monitoring Instrument (TROPOMI) sensor data. Copernicus Sentinel-5 Precursor satellite data was used in the Google Earth Engine platform to get the result.

The results revealed a strong relationship (R2=0.9478) between the NO2 concentration and high population density and the temporal variation is higher during the pre-monsoon than throughout the post-monsoon. The reason behind is the lack of sunlight and the difficulty to break down the NO2, which causes the removal of NO2 from the atmosphere to proceed more slowly. In contrast, Land Use and Land Cover (LULC) are also impacted by the high concentration which is remains in the built-up area.

This research mainly considered that how NO2 concentration measured from satellite images with temporal variation within a year and what factors strongly influence raising NO2 levels. This model can be used for policy-making to take proper initiatives to reduce NO2 concentrations. The result showed significant uses of TROPOMI with relating population density and LULC in Dhaka and its surrounding areas of Bangladesh.

Chiang Mai’s air pollution has risen to number one in the world for the highest level of fine particulate matter which further exacerbates the damage to human health. Fine particulate matter can enter the human body and blood circulation, destroying organ systems, increasing the risk for chronic disease and cancer, despite not having smoking habits or other morbidities. The Thai government must sort out this issue before it is too late as the whole nation’s health is at risk due to excessive dust levels higher than standard guidelines. Collection of pollution data can help us to come up with solutions and prevent it from turning into a hazardous situation. Unfortunately, pollution data are missing and need to be dealt with before analysis to obtain accurate results.

A new method of imputation for estimating population mean based on a transformed variable has been suggested under simple random sampling without replacement and the uniform nonresponse mechanism. The bias and mean square error of the proposed estimator are investigated up to the first order of approximation. The performance of the proposed estimator is studied via applications to air pollution data in Chiang Mai, Thailand.

The proposed estimator shows the best performance, giving the least bias and mean square error for all levels of sampling fractions. For the results from application the estimated value of sulfur dioxide from Particulate Matter 2.5 (PM2.5), the Percentage Relative Efficiency (PRE) is higher than all existing estimators by at least 16%. For the estimated PM2.5 from PM10 the PRE is higher than all existing estimators by at least 1600%, an extremely significant difference exhibiting similarity to real values.

The proposed imputation technique based on the transformed auxiliary variable can be helpful for imputing missing values and improving the efficiency of the estimators.

Human activities disrupted by COVID-19 have reduced global air pollution. Meteorological day-to-day and year-to-year variability affects pollution levels and complicates estimating reductions. This paper uses data clustering to remove the complexity of non-linear relationships by separating meteorology from complex emission patterns before modelling. The case study is based on PM2.5 concentration time series data and meteorological data for 2018 to 2021 in Colombo, Sri Lanka.

The southwest monsoon brings sea breezes from the Indian Ocean to land from May to October. To separate the effect of the monsoon winds on PM2.5 concentrations, analysis of time series data, polar plots, clusters, and Theil-Sen trends were used based on hourly-average air pollution and meteorological data for the whole dataset.

Two clear clusters were identified from scatterplots, representing the monsoon and non-monsoon periods. The study suggests that due to the combined effect of the monsoon winds and a reduction in the levels of traffic as a result of perturbations in human activity, the PM2.5 concentrations decreased at an average rate of 10.61 µg/m3/year (95% CI: 12.86 - 8.11) over the four years. During the non-monsoon season, due to traffic reductions alone, PM2.5 concentrations reduced at an average rate of 7.95 µg/m3/year (95% CI: 10.07 – 5.51).

These results are relevant to policymakers in the post pandemic planning of traffic and industry, with the methodology readily adapted for use in other locations where a separation of effects may be beneficial

While many national-level governments have worked to tighten atmospheric air quality standard, the Authors observe, Indoor Air Quality (IAQ) control as part of building-codes have remained understudied and not yet enforced in many national-level regulations. The COVID-19 pandemic seemed to trigger an immediate response worldwide for IAQ control. Indoor air pollutants need to be tightly regulated. International agencies have produced recommendations to cope with the pandemic, however, national level IAQ standards and building codes have been slow to adapt.

IAQ regulations from various nations worldwide were studied along with the international standards: The American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE), and World Health Organization (WHO). A comprehensive review was conducted comparing the national-level building codes and regulations as legal implementation instruments. Focus group discussions were also conducted to complement preliminary findings and further analysis.

Except for Indonesia, bacteria and fungi have been categorized as infectious aerosols in many national-level regulations that fare up to the international standards as indoor air pollutants with their acceptable levels. However, while they set thresholds for pollutants, their effectiveness regulating IAQ in public buildings remain unknown. It also found that there is a significant lack of national building codes in Indonesia.

The COVID-19 epidemic raises awareness of IAQ. The health aspect is currently being prioritized, particularly in Indonesia, where the majority of related regulations are still fragmented and prioritize energy conservation over health. This study can inform policymakers with evidence of IAQ control and practices worldwide for applicable regulatory building and implementation, as well as for health emergency and disaster risk management.

Coupling the indoor and outdoor airflow of roadside buildings in a street canyon, the impact of flat and triangular roofs on indoor air pollutant concentration and ventilation rates of naturally ventilated buildings is studied using numerical simulation methods.

The flow and pollutant diffusion control equations are solved by using ANSYS Fluent. In simulation, RNG k-ε turbulence model is adopted. The numerical model is validated using the three-dimensional street canyon test data from the wind tunnel experiment at University of Karlsruhe.

The flow and pollutant concentration distributions under different roof shapes are obtained. The ventilation rates with different air flow resistances and pollution level indoors are provided.

Ventilation direction through windows of roadside buildings determines the level of indoor air polluted by vehicle emissions in street canyon. When the building main height equals to the width of the street, flat roofs make the indoor concentration basically consistent with that near the external walls of the canyon. The higher the triangular roofs, the higher the ventilation rate and the lower the indoor concentration. The ventilation rate is influenced not only by roofs, but also by the floor location and indoor ventilation resistance.

Air pollutants emitted from household spray products used in our homes and offices have adverse effects on human health. The quantification and identification of emission sources of air pollutants forms a foundation for an effective indoor exposure control. This study presents the results of a fundamental study conducted to evaluate the kinetics and emission trends Total Volatile Organic Compounds (TVOCs) and Carbon Monoxide (CO) from household spray products.

Fortyfive (45) commonly used household spray products were selected for this study. The experiment was conducted in an isolated empty room of dimension (2.72×2.82×2.00) m3 with no known/significant indoor emission source(s). CO and TVOCs concentrations were measured with Aeroqual® 500 series monitor with CO and TVOCs head at 15 min, 1 h, 3 h, and 24 h, for all 45 samples of household spray products.

Spontaneous second – order conversion of TVOCs to CO was observed for most of the spray products in the indoor environment. For the insecticides samples, TVOCs initial concentrations were 7.2–73±19.76 ppm which after one hour the concentrations became 1.8 – 17±7.20 ppm. CO measured initial concentration were 0 – 4±1.08 ppm which the concentration levels reduced to 0–7±2.16 ppm. TVOCs concentration was above the permissible limit set by USEPA and CO concentration for some of the air fresheners, perfume, shoe impregnation spray and hair sprays fall short the limit of 40,081.89 and 25,562.37 µg/m3 set by United States Environmental Protection Agency (USEPA) and World Health Organization (WHO), respectively.

As the concentration of TVOCs decreased as the concentration the concentration, CO increased following a second order kinetics. The result obtained will help in the development of safer products and a proper guide on how to use them in a way it will not cause harm to both the user of the product and the environment.

This paper focuses on the prediction of weekly peak levels of Particulate Matter with an aerodynamic diameter of less than 2.5 µm (PM2.5), using various Machine Learning (ML) models. The study compares ML models to deep learning models and emphasizes the explain ability of ML models for PM2.5 prediction.

We examine different combinations of features and time window dimensions to evaluate the performance of ML models. It utilizes Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Decision Tree (DT), and five Ensemble Models (EL) including AdaBoost, XGBoost, LightGBM, CatBoost, and Random Forest (RF). The dataset includes three years of daily measurements of weather parameters and PM2.5.

Lagged values of PM2.5 improves prediction performance, particularly when the lagged value window size spans seven days or multiples thereof. This confirms that road traffic, which exhibits a weekly seasonality, is the primary source of PM2.5 in Algiers. Interestingly, including lagged values of weather parameters decreases prediction performance, even when chosen based on their correlation with PM2.5. The AdaBoost model performs the best, achieving a Root Mean Squared Error (RMSE) of 2.899 µg/m³ and an R2 value of 0.96.

EL models, specifically AdaBoost, exhibit strong performance in predicting PM2.5 levels. They not only provide accurate predictions but also allow analysis of feature importance. Lagged values of PM2.5 have a greater impact on predictions compared to weather parameters. Surprisingly, including weather parameters hampers prediction performance. Therefore, the utilization of ensemble learning models offers valuable insights into feature significance.