RESUMEN
Predicting soil heavy metal (SHM) content is crucial for understanding SHM pollution levels in urban residential areas and guide efforts to reduce pollution. However, current research indicates low SHM prediction accuracy in urban areas. Therefore, we employed a deep learning method (fully connected deep neural network) alongside four other methods (muti-layer perceptron, radial basis function neural network, multiple stepwise linear regression, and Kriging interpolation) to predict SHM content in the urban residential areas of Beijing and demonstrated the strength of deep learning in improving prediction accuracy. We found the contents of the evaluated heavy metals (Cd, Cu, Pb, and Zn) exhibited significant correlations with numerous other soil physicochemical properties and environmental factors. The prediction accuracy for Cu, Pb, and Zn contents was relatively high across different methods. Notably, deep learning showed considerable strength in predicting the contents of the four heavy metals, with the R2 for the test set of the model ranging from 0.75 to 0.91. Compared to other methods, deep learning achieved markedly higher prediction accuracy according to different accuracy evaluation indicators (e.g., deep learning showed increases in the cumulative R2 of the four heavy metals ranging from 53.16 % to 187.36 % compared to other methods). Our study indicates that deep learning can significantly improve SHM content prediction accuracy in urban areas and is highly applicable in urban residential areas with complex environmental influences.
RESUMEN
Exposure to metal(loid)s can cause adverse health effects. This study evaluated the concentrations of aluminum, arsenic, cadmium, chromium, mercury, nickel, and lead in particulate matter <10 µm (PM10) and in the urine of 100 participants from urban residential areas in Iran. A total of 100 residential buildings (one adult from each household) in six cities across Iran were recruited for this study. The levels of metal(loid)s in PM10 and the urine of participants were measured using acid digestion followed by inductively coupled plasma mass spectrometry (ICP-MS). The average (±SE) PM10 concentration in the buildings was 51.7 ± 3.46 µg/m3. Aluminum and cadmium had the highest and lowest concentrations among the metal(loid)s, averaging 3.74 ± 1.26 µg/m3 and 0.01 ± 0.001 µg/m3, respectively. In 85 % of the samples, the concentration of metal(loid)s in indoor air exceeded WHO air quality standards. Cadmium and lead had the highest and lowest numbers of indoor air samples exceeding the recommended standards, respectively. A significant correlation was found between the concentration of metal(loid)s in urine samples and indoor PM10 levels, as well as the wealth index of participants. There was also a significant direct relationship between the concentrations of nickel, arsenic, lead, and mercury in urine and the age of participants. Factors such as building location, type of cooling systems, use of printers at home, and natural ventilation influenced the concentration and types of metal(loid)s in the indoor air.
Asunto(s)
Contaminantes Atmosféricos , Contaminación del Aire Interior , Monitoreo Biológico , Exposición a Riesgos Ambientales , Contaminación del Aire Interior/análisis , Contaminación del Aire Interior/estadística & datos numéricos , Irán , Humanos , Contaminantes Atmosféricos/análisis , Exposición a Riesgos Ambientales/análisis , Exposición a Riesgos Ambientales/estadística & datos numéricos , Adulto , Material Particulado/análisis , Ciudades , Metales/análisis , Metales/orina , Masculino , Monitoreo del Ambiente/métodos , Femenino , Arsénico/análisis , Persona de Mediana EdadRESUMEN
The concentration of polycyclic aromatic hydrocarbons (PAHs) in the air inside residential houses in Iran along with measuring the amount of 1-OHpyrene metabolite in the urine of the participants in the study was investigated by gas chromatography-mass spectrometry (GC-MS). Demographic characteristics (including age, gender, and body composition), equipment affecting air quality, and wealth index were also investigated. The mean ± standard error (SE) concentration of particulate matter 10 (PM10) and ∑PAHs in the indoor environment was 43.2 ± 1.98 and 1.26 ± 0.15 µg/m3, respectively. The highest concentration of PAHs in the indoor environment in the gaseous and particulate phase related to Naphthalene was 1.1 ± 0.16 µg/m3 and the lowest was 0.01 ± 0. 0.001 µg/m3 Pyrene, while the most frequent compounds in the gas and particle phase were related to low molecular weight hydrocarbons. 30% of the samples in the indoor environment have BaP levels higher than the standards provided by WHO guidelines. 68% of low molecular weight hydrocarbons were in the gas phase and 73 and 75% of medium and high molecular weight hydrocarbons were in the particle phase. There was a significant relationship between the concentration of some PAH compounds with windows, evaporative coolers, printers, and copiers (p < 0.05). The concentration of PAHs in houses with low economic status was higher than in houses with higher economic status. The average concentration of 1-hydroxypyrene metabolite in the urine of people was 7.10 ± 0.76 µg/L, the concentration of this metabolite was higher in men than in women, and there was a direct relationship between the amount of this metabolite in urine and the amount of some hydrocarbon compounds in the air, PM10, visceral fat and body fat. This relationship was significant for age (p = 0.01). The concentration of hydrocarbons in the indoor environment has been above the standard in a significant number of non-smoking indoor environments, and the risk assessment of these compounds can be significant. Also, various factors have influenced the amount of these compounds in the indoor air, and paying attention to them can be effective in reducing these hydrocarbons in the air.