How critical is geometrical confinement? Analysis of spatially and temporally resolved particulate matter removal with an electrostatic precipitator

Application of the Gaussian Model for Monitoring Scenarios and Estimation of SO2 Atmospheric Emissions in the Salamanca Area, Bajío, Mexico

Population and industrial growth in Mexico’s Bajío region demand greater electricity consumption. The production of electricity from fuel oil has severe implications on climate change and people’s health due to SO2 emissions. This study describes the simulation of eight different scenarios for SO2 pollutant dispersion. It takes into account distance, geoenvironmental parameters, wind, terrain roughness, and Pasquill–Gifford–Turner atmospheric stability and categories of dispersion based on technical information about SO2 concentration from stacks and from one of the atmospheric monitoring stations in Salamanca city. Its transverse character, its usefulness for modeling, and epidemiological, meteorological, and fluid dynamics studies, as suggested by the models approved by the Environmental Protection Agency (EPA), show a maximum average concentration of 399 µg/m3, at an average distance of 1800 m. The best result comparison in the scenarios was scenery 8. Maximum nocturnal dispersion was shown at a wind speed of 8.4 m/s, and an SO2 concentration of 280 µg/m3 for stack 4, an atypical situation due to the geography of the city. From the validation process, a relative error of 14.7 % was obtained, which indicates the reliability of the applied Gaussian model. Regarding the mathematical solution of the model, this represents a reliable and low-cost tool that can help improve air quality management, the location or relocation of atmospheric monitoring stations, and migration from the use of fossil fuels to environmentally friendly fuels.

Interpreting convolutional neural network for real-time volatile organic compounds detection and classification using optical emission spectroscopy of plasma

This study presents the investigation of optical emission spectroscopy of plasma using interpretable convolutional neural network (CNN) for real-time volatile organic compounds (VOCs) classification. A microplasma-generation platform was developed to efficiently collect 64 k spectra from various types of VOCs at different concentrations, as training and testing sets for machine learning. A CNN model was trained to classify VOCs with accuracy of 99.9%. To interpret the CNN model and its predictions, the spectral processing mechanism of the CNN was visualized by feature maps and the critical spectral features were identified by gradient-weighted class activation mapping. Such approaches brought insights on how CNN analyzes the spectra and enables the CNN operation to be explainable. Finally, the CNN model was incorporated with the microplasma platform to demonstrate the application of real-time VOC monitoring. The type of VOCs can be identified and reported via messages within 10 s once the microplasma is ignited. We believe that using CNN brings a novel route for plasma spectroscopy analysis for VOC classification and impacts the fields of plasma, spectroscopy, and environmental monitoring.