A machine learning approach to analyse ozone concentration in metropolitan area of Lima, Peru.

The main objective of this study is to model the concentration of ozone in the winter season on air quality through machine learning algorithms, detecting its impact on population health. The study area involves four monitoring stations: Ate, San Borja, Santa Anita and Campo de Marte, all located in Metropolitan Lima during the years 2017, 2018 and 2019. Exploratory, correlational and predictive approaches are presented. The exploratory results showed that ATE is the station with the highest prevalence of ozone pollution. Likewise, in an hourly scale analysis, the pollution peaks were reported at 00:00 and 14:00. Finally, the machine learning models that showed the best predictive capacity for adjusting the ozone concentration were the linear regression and support vector machine.

Statistical modeling approach for PM10 prediction before and during confinement by COVID-19 in South Lima, Perú.

A total of 188,859 meteorological-PM[Formula: see text] data validated before (2019) and during the COVID-19 pandemic (2020) were used. In order to predict PM[Formula: see text] in two districts of South Lima in Peru, hourly, daily, monthly and seasonal variations of the data were analyzed. Principal Component Analysis (PCA) and linear/nonlinear modeling were applied. The results showed the highest annual average PM[Formula: see text] for San Juan de Miraflores (SJM) (PM[Formula: see text]-SJM: 78.7 [Formula: see text]g/m[Formula: see text]) and the lowest in Santiago de Surco (SS) (PM[Formula: see text]-SS: 40.2 [Formula: see text]g/m[Formula: see text]). The PCA showed the influence of relative humidity (RH)-atmospheric pressure (AP)-temperature (T)/dew point (DP)-wind speed (WS)-wind direction (WD) combinations. Cool months with higher humidity and atmospheric instability decreased PM[Formula: see text] values in SJM and warm months increased it, favored by thermal inversion (TI). Dust resuspension, vehicular transport and stationary sources contributed more PM[Formula: see text] at peak times in the morning and evening. The Multiple linear regression (MLR) showed the best correlation (r = 0.6166), followed by the three-dimensional model LogAP-LogWD-LogPM[Formula: see text] (r = 0.5753); the RMSE-MLR (12.92) exceeded that found in the 3D models (RMSE [Formula: see text]) and the NSE-MLR criterion (0.3804) was acceptable. PM[Formula: see text] prediction was modeled using the algorithmic approach in any scenario to optimize urban management decisions in times of pandemic.

Biomonitoring of Potentially Toxic Elements in Two Polluted Areas from Lurigancho-Chosica Using the genus Tillandsia latifolia and T. purpurea as Biomonitor.

In the present study, an urban and industrial area were evaluated through a biomonitoring study employing the Tillandsia purpurea and T. latifolia species as a biomonitor. Plants were collected from a non-contaminated area and transplanted and exposed for three months into study areas to determine metal accumulation. Sixteen elements (Al, As, Ba, Ca, Cd, Co, Cr, Cu, Fe, K, Mg, Mn, Ni, Pb, Rb, Sb, V, and Zn) were measured using ICP-MS analysis. Datasets were assessed by one-way ANOVA, exposed-to-baseline (EB) ratio, and principal component analysis. Results showed significant differences among study areas for most elements, but no differences were found between species. According to EB ratios, As, Cd, Cr, Cu, Fe, Ni, Pb, Sb, V, and Zn showed EB ratios > 1.75 for both Tillandsia species around the industrial area, indicating influence from the Smelter plant. Ba, Sb, and Zn showed EB ratios > .1.75 in the urban area for both plants, indicating the releasing of pollutants from vehicular sources. PCA showed that most elements are derived from vehicular sources, industrial activities, and dust resuspension.

Trace element biomonitoring in the Peruvian andes metropolitan region using Flavoparmelia caperata lichen.

In the present study, in situ lichens (Flavoparmelia caperata) were used to assess the deposition of atmospheric trace elements in the metropolitan area of Huancayo (Junín, Peru). In total, ten sampling sites were chosen and categorized as urban, peri-urban (rural-urban) and rural areas according to land use. In addition, samples were also collected from a non-contaminated area categorized as a control site. The concentrations of 16 trace elements were measured using an inductively coupled plasma mass spectrometer (ICP-MS) and examined by enrichment factor (EF), hierarchical cluster analysis (HCA), and principal component analysis (PCA). Twelve of the 16 trace elements in urban and peri-urban sites present concentration higher than those at the rural and control sites (p < 0.05). The EF results revealed significant enrichment (at least twice that of the control site) of Ba, Cr, Cd, Pb, Sb, V, and Zn at most sites. PCA and HCA showed that more elements were derived from vehicular sources and fewer from agricultural and natural sources.