Time-series forecasting of pollutant concentration levels using particle swarm optimization and artificial neural networks

This study evaluates the application of an intelligent hybrid system for time-series forecasting of atmospheric pollutant concentration levels. The proposed method consists of an artificial neural network combined with a particle swarm optimization algorithm. The method not only searches relevant time lags for the correct characterization of the time series, but also determines the best neural network architecture. An experimental analysis is performed using four real time series and the results are shown in terms of six performance measures. The experimental results demonstrate that the proposed methodology achieves a fair prediction of the presented pollutant time series by using compact networks.

Method for determining the photocatalytic potential of portland cement mortar containing TiO2 for decomposing the pollutant nitrogen monoxide

Photocatalytic materials can minimize atmospheric pollution by decomposing certain organic and inorganic pollutants using sunlight as an energy source. In this paper, the development of a methodology to measure the photocatalytic potential of mortar containing TiO2 nanoparticles is reported. The results indicate that up to 40% of NOx can be degraded by Portland cement mortar containing 30-50% of TiO2, which validates the method developed for evaluating the photocatalytic potential of materials.

VIS-NIR SPECTROMETRY, SOIL PHOSPHATE EXTRACTION METHODS AND INTERACTIONS OF SOIL ATTRIBUTES

The objective of this study was to evaluate the relationships between the spectra in the Vis-NIR range and the soil P concentrations obtained from the PM and Prem extraction methods as well as the effects of these relationships on the construction of models predicting P concentration in Oxisols. Soil samples' spectra and their PM and Prem extraction solutions were determined for the Vis-NIR region between 400 and 2500 nm. Mineralogy and/or organic matter content act as primary attributes allowing correlation of these soil phosphorus fractions with the spectra, mainly at wavelengths between 450-550, 900-1100 nm, near 1400 nm and between 2200-2300 nm. However, the regression models generated were not suitable for quantitative phosphate analysis. Solubilization of organic matter and reactions during the PM extraction process hindered correlations between the spectra and these P soil fractions. For Prem,, the presence of Ca in the extractant and preferential adsorption by gibbsite and iron oxides, particularly goethite, obscured correlations with the spectra.

EVALUATION OF A BUFFERED SOLID PHASE DISPERSION PROCEDURE ADAPTED FOR PESTICIDE ANALYSES IN THE SOIL MATRIX

An evaluation of the pesticides extracted from the soil matrix was conducted using a citrate-buffered solid phase dispersion sample preparation method (QuEChERS). The identification and quantitation of pesticide compounds was performed using gas chromatography-mass spectrometry. Because of the occurrence of the matrix effect in 87% of the analyzed pesticides, the quantification was performed using matrix-matched calibration. The method's quantification limits were between 0.01 and 0.5 mg kg-1. Repeatability and intermediate precision, expressed as a relative standard deviation percentage, were less than 20%. The recoveries in general ranged between 62% and 99%, with a relative standard deviation < 20%. All the responses were linear, with a correlation coefficient (r) ≥0.99.