Current studies show that traditional deterministic models tend to struggle to capture the non-linear relationship between the concentration of air pollutants and their sources of emission and dispersion. To tackle such a limitation, the most promising approach is to use statistical models based on machine learning techniques. Nevertheless, it is puzzling why a certain algorithm is chosen over another for a given task. This systematic review intends to clarify this question by providing the reader with a comprehensive description of the principles underlying these algorithms and how they are applied to enhance prediction accuracy. A rigorous search that conforms to the PRISMA guideline is performed and results in the selection of the 46 most relevant journal papers in the area. Through a factorial analysis method these studies are synthetized and linked to each other. The main findings of this literature review show that: (i) machine learning is mainly applied in Eurasian and North American continents and (ii) estimation problems tend to implement Ensemble Learning and Regressions, whereas forecasting make use of Neural Networks and Support Vector Machines. The next challenges of this approach are to improve the prediction of pollution peaks and contaminants recently put in the spotlights (e.g., nanoparticles).

Outdoor air pollution costs millions of premature deaths annually, mostly due to anthropogenic fine particulate matter (or PM_2.5). Quito, the capital city of Ecuador, is no exception in exceeding the healthy levels of pollution. In addition to the impact of urbanization, motorization, and rapid population growth, particulate pollution is modulated by meteorological factors and geophysical characteristics, which complicate the implementation of the most advanced models of weather forecast. Thus, this paper proposes a machine learning approach based on six years of meteorological and pollution data analyses to predict the concentrations of PM_2.5 from wind (speed and direction) and precipitation levels. The results of the classification model show a high reliability in the classification of low (25 µg/m³) and low (<10 µg/m³) versus moderate (10–25 µg/m³) concentrations of PM_2.5. A regression analysis suggests a better prediction of PM_2.5 when the climatic conditions are getting more extreme (strong winds or high levels of precipitation). The high correlation between estimated and real data for a time series analysis during the wet season confirms this finding. The study demonstrates that the use of statistical models based on machine learning is relevant to predict PM_2.5 concentrations from meteorological data.

Levels of urban pollution can be influenced largely by meteorological conditions and the topography of the area. The impact of the relative humidity (RH) on the daily average PM_2.5 concentrations was studied at several sites in a mid-size South American city at a high elevation over the period of nine years. In this work, we show that there is a positive correlation between daily average urban PM_2.5 concentrations and the RH in traffic-busy central areas, and a negative correlation in the outskirts of the city in more industrial areas. While in the traffic sites strong events of precipitation (≥9 mm) played a major role in PM_2.5 pollution removal, in the city outskirts, the PM_2.5 concentrations decreased with increasing RH independently of rain accumulation. Increasing PM_2.5 concentrations are to be expected in any highly motorized city where there is high RH and a lack of strong precipitation, especially in rapidly growing and developing countries with high motorization due to poor fuel quality. Finally, two models, based on a logistic regression algorithm, are proposed to describe the effect of rain and RH on PM_2.5, when the source of pollution is traffic-based vs. industry-based.

The perceived direction of a grating moving behind an elongated aperture is biased towards the aperture's long axis. This “barber pole” illusion is a consequence of integrating one-dimensional (1D) or grating and two-dimensional (2D) or terminator motion signals. In humans, we recorded the ocular following responses to this stimulus. Tracking was always initiated at ultra-short latencies (≈ 85 ms) in the direction of grating motion. With elongated apertures, a later component was initiated 15–20 ms later in the direction of the terminator motion signals along the aperture's long axis. Amplitude of the later component was dependent upon the aperture's aspect ratio. Mean tracking direction at the end of the trial (135–175 ms after stimulus onset) was between the directions of the vector sum computed by integrating either terminator motion signals only or both grating and terminator motion signals. Introducing an elongated mask at the center of the “barber pole” did not affect the latency difference between early and later components, indicating that this latency shift was not due to foveal versus peripheral locations of 1D and 2D motion signals. Increasing the size of the foveal mask up to 90% of the stimulus area selectively reduced the strength of the grating motion signals and, consequently, the amplitude of the early component. Conversely, reducing the contrast of, or indenting the aperture's edges, selectively reduced the strength of terminator motion signals and, consequently, the amplitude of the later component. Latencies were never affected by these manipulations. These results tease apart an early component of tracking responses, driven by the grating motion signals and a later component, driven by the line-endings moving at the intersection between grating and aperture's borders. These results support the hypothesis of a parallel processing of 1D and 2D motion signals with different temporal dynamics.

In the light of the 21st century, after two devastating world wars, humanity still has not learned to solve their conflicts through peaceful negotiations and dialogue. Armed conflicts, both international and within a single state, still cause devastation, displacement, and death all over the world. Not to mention the consequences that war has on the environment. Due to a lack of published research about war impact on modern air quality, this work studies air pollution evolution during the first months of the Russian-Ukrainian conflict. Satellite images of NO₂, CO, O₃, SO₂, and PM_2.5 over Ukrainian territory and PM_2.5 land monitoring data for Kyiv were analyzed. The results showed that NO₂ and PM_2.5 correlated the most with war activities. CO and O3 levels increased, while SO₂ concentrations reduced four-fold as war intensified. Drastic increases in pollution (especially PM_2.5) from bombing and structural fires, raise additional health concerns, which might have serious implications for the exposed local and regional populations. This study is an invaluable proof of the impact any armed conflict has on air quality, the population, and environment.

The worldwide research initiatives on Corona Virus disease 2019 lockdown effect on air quality agree on pollution reduction, but the most reliable method to pollution reduction quantification is still in debate. In this paper, machine learning models based on a Gradient Boosting Machine algorithm are built to assess the outbreak impact on air quality in Quito, Ecuador. First, the precision of the prediction was evaluated by cross‐validation on the four years prelockdown, showing a high accuracy to estimate the real pollution levels. Then, the changes in pollution are quantified. During the full lockdown, air pollution decreased by −53 ± 2%, −45 ± 11%, −30 ± 13%, and −15 ± 9% for NO₂, SO₂, CO, and PM_2.5, respectively. The traffic‐busy districts were the most impacted areas of the city. After the transition to the partial relaxation, the concentrations have nearly returned to the levels as before the pandemic. The quantification of pollution drop is supported by an assessment of the prediction confidence.