Examinando por Materia "Calidad del aire"
Mostrando 1 - 4 de 4
Resultados por página
Opciones de ordenación
Publicación Análisis comparativo de modelos predictivos para la estimación de PM2.5 : un enfoque basado en aprendizaje automático y predicción conformal(Universidad EAFIT, 2024) Camelo Valera, Matías; Martínez Vargas, Juan David; Sepúlveda Cano, Lina MariaFine particulate matter (𝑃𝑀2.5pollution poses a significant environmental and public health challenge, requiring accurate predictive models for its monitoring and control. This study compares different machine learning approaches, including Linear Regression, Random Forest, and XGBoost, with and without the inclusion of mobility variables, to estimate 𝑃𝑀2.5 levels. Additionally, inductive conformal prediction is implemented to quantify uncertainty in the estimates and provide confidence intervals with 𝛼=0.05. The results show that while XGBoost experiences performance deterioration during training when mobility variables are included, it achieves the best validation performance with the lowest mean absolute error and the highest coefficient of determination. Conformal prediction enabled the establishment of confidence intervals with 89.26% coverage, close to the expected 95%, ensuring model reliability across different spatial and temporal scenarios. In conclusion, the use of machine learning models combined with advanced validation and calibration techniques, such as conformal prediction, enhances the accuracy and reliability of 𝑃𝑀2.5 estimation. However, the quality of input variables, particularly mobility-related data, remains a challenge, highlighting the need to incorporate meteorological information and improve data resolution. These findings contribute to the development of more reliable predictive tools for environmental management and air quality policy decision-making.Ítem Cambios en el uso del suelo y su incidencia en la concentración y deposición de nitrogenados en el modelo de química de transporte LOTOS-EUROS para el Valle de Aburrá(Universidad EAFIT, 2021) Sánchez Aguirre, Andrés Felipe; Zapata Correa, Juliana; Yarce Botero, Andrés; López Restrepo, SantiagoConservation in the new century presents a multitude of challenges that are growing. One of the main challenges is the change in land use because it generates many transformed spaces that are constantly expanding and negatively affect the atmosphere, climate, ecosystems, and human health. Consideration in the land cover or use changes, together with transport chemistry models, enables the analysis of posible causes and consequences of future atmospheric dynamics in various temporal or spatial scenarios. The objective is to evaluate the variables of NOy Dry Deposition and NOx Surface Concentration, predicted by the LOTOS-EUROS transport chemistry model, when subjected to different land-use scenarios of the Aburrá Valley, generating an approximation to evaluate and predict the consequences of cover changes on the atmospheric dynamics of nitrogen and its possible effect on the surrounding ecosystems. This study analyzes different perspectives from the implementation for a case study in the Aburrá Valley of a chemistry-transport models as an important urban planning tool.Ítem Participación ciudadana como instrumento para la investigación y la construcción de políticas de desarrollo sostenible(Universidad EAFIT, 2021) Giraldo Rodríguez, Diego Alejandro; Orjuela Mendoza, Juan PabloÍtem Responsabilidad del Estado colombiano sobre los perjuicios ocasionados a la salud de las personas por el deterioro de la calidad del aire de Medellín(Universidad EAFIT, 2020) Jaramillo Sánchez, Camilo; Roldán García, Maria Isabel; Rodas Monsalve, Julio CesarThe purpose of this thesis is to determine the responsibility of the Metropolitan Area of Valle de Aburrá and the Municipality of Medellín for the damages that are generated in the population due to poor air quality in the city of Medellín. For this, the different norms and jurisprudential rulings of the Colombian high courts will be analyzed.