Browsing by Author "Bonilla Bedoya, Santiago Patricio"

Now showing 1 - 3 of 3

Gradient boosting machine to assess the public protest impact on urban air quality
(2021) Alexandrino, Katiuska; Díaz Suárez, María Valeria; Bastidas, Marco G.; Mejía Coronel, Julio Danilo; Bonilla Bedoya, Santiago Patricio; Rybarczyk, Yves; Zalakeviciute, Rasa
Political and economic protests build-up due to the financial uncertainty and inequality spreading throughout the world. In 2019, Latin America took the main stage in a wave of protests. While the social side of protests is widely explored, the focus of this study is the evolution of gaseous urban air pollutants during and after one of these events. Changes in concentrations of NO2, CO, O3 and SO2 during and after the strike, were studied in Quito, Ecuador using two approaches: (i) inter-period observational analysis; and (ii) machine learning (ML) gradient boosting machine (GBM) developed business-as-usual (BAU) comparison to the observations. During the strike, both methods showed a large reduction in the concentrations of NO2 (31.5–32.36%) and CO (15.55–19.85%) and a slight reduction for O3 and SO2. The GBM approach showed an exclusive potential, especially for a lengthier period of predictions, to estimate strike impact on air quality even after the strike was over. This advocates for the use of machine learning techniques to estimate an extended effect of changes in human activities on urban gaseous pollution.
Spatiotemporal variation of forest cover and its relation to air quality in urban andean socio-ecological systems
(2021) Bonilla Bedoya, Santiago Patricio
Confronting the dynamics of global urbanization is one of the challenges of sustainability in the 21st century. Latin America is expected to be one of the regions with the highest urban growth; however, research related to variations in urban land coverage and air quality is relatively new, despite its importance for urban planning and citizens well-being. This study determines the relationship between the spatial variability of some atmospheric pollutants and changes in land cover in a Andean mountain cities of Latin American. We quantified the changes and transitions of land cover using SPOT optical images and generating an object-based classification. In addition, we identified variations in the mean concentrations of some atmospheric pollutants; and, finally, using various linear regression models, we explained the relationship between the spatiotemporal variation of atmospheric pollutants with the spatiotemporal variations of the land cover and some meteorological and topographical factors. Changes in land cover indicated an increase of impervious cover and a loss of urban non-forest vegetation. However, there was also an increase in forest fragments and urban woodland to the detriment of green areas and shrubbery. On the other hand, the concentrations of the air pollutants CO, O3, and PM2.5 showed significant variations between periods, reducing their concentrations in the air. Finally, land cover such as forests and urban trees, as well as meteorological and topographical factors were associated with and explained (r2 > 0.6) the spatiotemporal variation of air pollutants. Urban green infrastructure management in developing regions should consider a multidisciplinary approach to achieve an equitable and minimum distribution of local green infrastructure; by promoting conditions that allow the conversion of land use and coverage, in order to maximize the benefits and the ecosystemic forest services that a city demands
Urban soil management in the strategies for adaptation to climate change of cities in the tropical andes
(2022) Salazar, Laura; Vaca Yánez, Angélica Elizabeth; Herrera Machuca, Miguel Ángel; Bonilla Bedoya, Santiago Patricio; López Ulloa, Ruth Magdalena; Mejía Coronel, Julio Danilo; Zalakeviciute, Rasa
The unique characteristics of a city amplify the impacts of climate change; therefore, urban planning in the 21st century is challenged to apply mitigation and adaptation strategies that ensure the collective well-being. Despite advances in monitoring urban environmental change, research on the application of adaptation-oriented criteria remains a challenge in urban planning in the Global South. This study proposes to include urban land management as a criterion and timely strategy for climate change adaptation in the cities of the Tropical Andes. Here, we estimate the distribution of the soil organic carbon stock (OCS) of the city of Quito (2,815 m.a.s.l.; population 2,011,388; 197.09 km2) in the following three methodological moments: i) field/laboratory: city-wide sampling design established to collect 300 soil samples (0–15 cm) and obtain data on organic carbon (OC) concentrations in addition to 30 samples for bulk density (BD); ii) predictors: geographic, spectral and anthropogenic dimensions established from 17 co-variables; and iii) spatial modeling: simple multiple regression (SMRM) and random forest (RFM) models of organic carbon concentrations and density as well as OCS stock estimation. We found that the spatial modeling techniques were complementary; however, SMRM showed a relatively higher fit both (OC: r2 = 20%, BD: r2 = 16%) when compared to RFM (OC: r2 = 8% and BD: r2 = 5%). Thus, soil carbon stock (0–0.15 m) was estimated with a spatial variation that fluctuated between 9.89 and 21.48 kg/m2; whereas, RFM showed fluctuations between 10.38 and 17.67 kg/m2. We found that spatial predictors (topography, relative humidity, precipitation, temperature) and anthropogenic predictors (population density, roads, vehicle traffic, land cover) positively influence the model, while spatial predictors have little influence and show multicollinearity with relative humidity. Our research suggests that urban land management in the 21st century provides key information for adaptation and mitigation strategies aimed at coping with global and local climate variations in the cities of the Tropical Andes.