Hybrid unorganized machines to estimate the number of hospital admissions caused by PM[Formula: see text] concentration.

Air pollution levels exceeding the recommended limit can be the main cause of illnesses that affect human health, mainly diseases of the respiratory system. Consequently, this high exposure can impact public health management, given the increase in hospital admissions. One of the most influential air pollution parameters related to respiratory diseases is particulate matter (PM) concentrations. Thus, this paper proposes to estimate hospital admissions due to respiratory diseases caused by PM concentration with an aerodynamic diameter less than 10 [Formula: see text]m (PM[Formula: see text]), using artificial neural networks. Three hybrid neural network models are developed by combining two architectures denoted unorganized machines: extreme learning machines and echo state networks. These models also comprise extension strategies that seek to improve the generalization capability and the variation in the nonlinear outputs. Case studies explore three cities' datasets from São Paulo state, Brazil: Cubatão, Campinas, and São Paulo, to assess the quality of the hospital admissions estimations obtained by applying the proposed models. Results demonstrate that the hybrid models outperform the previously developed standard approaches in several scenarios. An overall analysis shows that the hybrid models can be a suitable strategy considering the instance particularities, especially in large datasets.

The new WHO air quality guidelines for PM2.5: predicament for small/medium cities.

The global burden of disease estimated that approximately 7.1 million deaths worldwide were related to air pollution in 2016. However, only a limited number of small- and middle-sized cities have air quality monitoring networks. To date, air quality in terms of particulate matter is still mainly focused on mass concentration, with limited compositional monitoring even in mega cities, despite evidence indicating differential toxicity of particulate matter. As this evidence is far from conclusive, we conducted PM2.5 bioaccessibility studies of potentially harmful elements in a medium-sized city, Londrina, Brazil. The data was interpreted in terms of source apportionment, the health risk evaluation and the bioaccessibility of inorganic contents in an artificial lysosomal fluid. The daily average concentration of PM2.5 was below the WHO guideline, however, the chemical health assessment indicated a considerable health risk. The in vitro evaluation showed different potential mobility when compared to previous studies in large-sized cities, those with 1 million inhabitants or more (Curitiba and Manaus). The new WHO guideline for PM2.5 mass concentration puts additional pressure on cities where air pollution monitoring is limited and/or neglected, because decision making is mainly revenue-driven and not socioeconomic-driven. Given the further emerging evidence that PM chemical composition is as, or even more, important than mass concentration levels, the research reported in the paper could pave the way for the necessary inter- and intra-city collaborations that are needed to address this global health challenge.

Dynamic model to predict the association between air quality, COVID-19 cases, and level of lockdown.

Studies have reported significant reductions in air pollutant levels due to the COVID-19 outbreak worldwide global lockdowns. Nevertheless, all of the reports are limited compared to data from the same period over the past few years, providing mainly an overview of past events, with no future predictions. Lockdown level can be directly related to the number of new COVID-19 cases, air pollution, and economic restriction. As lockdown status varies considerably across the globe, there is a window for mega-cities to determine the optimum lockdown flexibility. To that end, firstly, we employed four different Artificial Neural Networks (ANN) to examine the compatibility to the original levels of CO, O3, NO2, NO, PM2.5, and PM10, for São Paulo City, the current Pandemic epicenter in South America. After checking compatibility, we simulated four hypothetical scenarios: 10%, 30%, 70%, and 90% lockdown to predict air pollution levels. To our knowledge, ANN have not been applied to air pollution prediction by lockdown level. Using a limited database, the Multilayer Perceptron neural network has proven to be robust (with Mean Absolute Percentage Error âˆ¼ 30%), with acceptable predictive power to estimate air pollution changes. We illustrate that air pollutant levels can effectively be controlled and predicted when flexible lockdown measures are implemented. The models will be a useful tool for governments to manage the delicate balance among lockdown, number of COVID-19 cases, and air pollution.

Air pollution epidemiology: A simplified Generalized Linear Model approach optimized by bio-inspired metaheuristics.

Studies in air pollution epidemiology are of paramount importance in diagnosing and improve life quality. To explore new methods or modify existing ones is critical to obtain better results. Most air pollution epidemiology studies use the Generalized Linear Model, especially the default version of R, Splus, SAS, and Stata softwares, which use maximum likelihood estimators in parameter optimization. Also, a smooth time function (usually spline) is generally used as a pre-processing step to consider seasonal and long-term tendencies. This investigation introduces a new approach to GLM, proposing the estimation of the free coefficients through bio-inspired metaheuristics - Particle Swarm Optimization (PSO), Genetic Algorithms, and Differential Evolution, as well as the replacement of the spline function by a simple normalization procedure. The considered case studies comprise three important cities of São Paulo state, Brazil with distinct characteristics: São Paulo, Campinas, and Cubatão. We considered the impact of particles with an aerodynamic diameter less than 10 µm (PM10), ambient temperature, and relative humidity in the number of hospital admissions for respiratory diseases (ICD-10, J00 to J99). The results showed that the new approach (especially PSO) brings performance gains compared to the default version of statistical software like R.

Polycyclic Aromatic Hydrocarbons (PAHs) and nitrated analogs associated to particulate matter emission from a Euro V-SCR engine fuelled with diesel/biodiesel blends.

Among the new technologies developed for the heavy-duty fleet, the use of Selective Catalytic Reduction (SCR) aftertreatment system in standard Diesel engines associated with biodiesel/diesel mixtures is an alternative in use to control the legislated pollutants emission. Nevertheless, there is an absence of knowledge about the synergic behaviour of these devices and biodiesel blends regarding the emissions of unregulated substances as the Polycyclic Aromatic Hydrocarbons (PAHs) and Nitro-PAHs, both recognized for their carcinogenic and mutagenic effects on humans. Therefore, the goal of this study is the quantification of PAHs and Nitro-PAHs present to total particulate matter (PM) emitted from the Euro V engine fuelled with ultra-low sulphur diesel and soybean biodiesel in different percentages, B5 and B20. PM sampling was performed using a Euro V - SCR engine operating in European Stationary Cycle (ESC). The PAHs and Nitro-PAHs were extracted from PM using an Accelerated Solvent Extractor and quantified by GC-MS. The results indicated that the use of SCR and the largest fraction of biodiesel studied may suppress the emission of total PAHs. The Toxic Equivalent (TEQ) was lower when using 20% biodiesel, in comparison with 5% biodiesel on the SCR system, reaffirming the low toxicity emission using higher percentage biodiesel. The data also reveal that use of SCR, on its own, suppress the Nitro-PAHs compounds. In general, the use of larger fractions of biodiesel (B20) coupled with the SCR aftertreatment showed the lowest PAHs and Nitro-PAHs emissions, meaning lower toxicity and, consequently, a potential lower risk to human health. From the emission point of view, the results of this work also demonstrated the viability of the Biodiesel programs, in combination with the SCR systems, which does not require any engine adaptation and is an economical alternative for the countries (Brazil, China, Russia, India) that have not adopted Euro VI emission standards.

Assessing the impact of PM2.5 on respiratory disease using artificial neural networks.

Understanding the impact on human health during peak episodes in air pollution is invaluable for policymakers. Particles less than PM2.5 can penetrate the respiratory system, causing cardiopulmonary and other systemic diseases. Statistical regression models are usually used to assess air pollution impacts on human health. However, when there are databases missing, linear statistical regression may not process well and alternative data processing should be considered. Nonlinear Artificial Neural Networks (ANN) are not employed to research environmental health pollution even though another advantage in using ANN is that the output data can be expressed as the number of hospital admissions. This research applied ANN to assess the impact of air pollution on human health. Three well-known ANN were tested: Multilayer Perceptron (MLP), Extreme Learning Machines (ELM) and Echo State Networks (ESN), to assess the influence of PM2.5, temperature, and relative humidity on hospital admissions due to respiratory diseases. Daily PM2.5 levels were monitored, and hospital admissions for respiratory illness were obtained, from the Brazilian hospital information system for all ages during two sampling campaigns (2008-2011 and 2014-2015) in Curitiba, Brazil. During these periods, the daily number of hospital admissions ranged from 2 to 55, PM2.5 concentrations varied from 0.98 to 54.2 µg m-3, temperature ranged from 8 to 26 °C, and relative humidity ranged from 45 to 100%. Of the ANN used in this study, MLP gave the best results showing a significant influence of PM2.5, temperature and humidity on hospital attendance after one day of exposure. The Anova Friedman's test showed statistical difference between the appliance of each ANN model (p < .001) for 1 lag day between PM2.5 exposure and hospital admission. ANN could be a more sensitive method than statistical regression models for assessing the effects of air pollution on respiratory health, and especially useful when there is limited data available.

Effectiveness of selective catalytic reduction systems on reducing gaseous emissions from an engine using diesel and biodiesel blends.

The aim of this investigation was to quantify organic and inorganic gas emissions from a four-cylinder diesel engine equipped with a urea selective catalytic reduction (SCR) system. Using a bench dynamometer, the emissions from the following mixtures were evaluated using a Fourier transform infrared (FTIR) spectrometer: low-sulfur diesel (LSD), ultralow-sulfur diesel (ULSD), and a blend of 20% soybean biodiesel and 80% ULSD (B20). For all studied fuels, the use of the SCR system yielded statistically significant (p < 0.05) lower NOx emissions. In the case of the LSD and ULSD fuels, the SCR system also significantly reduced emissions of compounds with high photochemical ozone creation potential, such as formaldehyde. However, for all tested fuels, the SCR system produced significantly (p < 0.05) higher emissions of N2O. In the case of LSD, the NH3 emissions were elevated, and in the case of ULSD and B20 fuels, the non-methane hydrocarbon (NMHC) and total hydrocarbon of diesel (HCD) emissions were significantly higher.

Gaseous emissions from a heavy-duty engine equipped with SCR aftertreatment system and fuelled with diesel and biodiesel: assessment of pollutant dispersion and health risk.

The changes in the composition of fuels in combination with selective catalytic reduction (SCR) emission control systems bring new insights into the emission of gaseous and particulate pollutants. The major goal of our study was to quantify NOx, NO, NO2, NH3 and N2O emissions from a four-cylinder diesel engine operated with diesel and a blend of 20% soybean biodiesel. Exhaust fume samples were collected from bench dynamometer tests using a heavy-duty diesel engine equipped with SCR. The target gases were quantified by means of Fourier transform infrared spectrometry (FTIR). The use of biodiesel blend presented lower concentrations in the exhaust fumes than using ultra-low sulfur diesel. NOx and NO concentrations were 68% to 93% lower in all experiments using SCR, when compared to no exhaust aftertreatment. All fuels increased NH3 and N2O emission due to SCR, a precursor secondary aerosol, and major greenhouse gas, respectively. An AERMOD dispersion model analysis was performed on each compound results for the City of Curitiba, assumed to have a bus fleet equipped with diesel engines and SCR system, in winter and summer seasons. The health risks of the target gases were assessed using the Risk Assessment Information System For 1-h exposure of NH3, considering the use of low sulfur diesel in buses equipped with SCR, the results indicated low risk to develop a chronic non-cancer disease. The NOx and NO emissions were the lowest when SCR was used; however, it yielded the highest NH3 concentration. The current results have paramount importance, mainly for countries that have not yet adopted the Euro V emission standards like China, India, Australia, or Russia, as well as those already adopting it. These findings are equally important for government agencies to alert the need of improvements in aftertreatment technologies to reduce pollutants emissions.