Modelos de machine learning para el estudio de la contaminación y su impacto en la salud
Loading...
Identifiers
Publication date
Reading date
Authors
Collaborators
Advisors
Aguilera-Venegas, Gabriel
Tutors
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Share
Department/Institute
Abstract
En el contexto actual, los debates sobre el cambio climático han reavivado la preocupación acerca de los efectos de la contaminación ambiental en nuestro entorno. En este proyecto se plantea un enfoque innovador mediante el uso de técnicas de aprendizaje automático (Machine Learning) para analizar el impacto de la contaminación ambiental en la salud pública.
El trabajo actual se basa en la comparación de diversos métodos automáticos de análisis, con especial énfasis en los bosques aleatorios (Random Forests), destacando su potencial para modelar relaciones complejas en datos ambientales y de salud. Para llevar a cabo el estudio, se ha realizado un exhaustivo preprocesamiento de datos, así como una evaluación rigurosa de métodos de interpolación espacial, priorizando el método de ponderación inversa por distancia (Inverse Distance Weighting) por su efectividad y adecuación al tipo de datos analizados.
Este proyecto contribuye a ampliar la perspectiva bioestadística tradicional, integrando herramientas avanzadas de Machine Learning para ofrecer una interpretación más precisa y robusta del impacto de la contaminación en la salud, facilitando así la toma de decisiones informadas en políticas públicas ambientales y sanitarias.
In the current context, climate change debates have renewed concern about the effects of environmental pollution on our surroundings. This project proposes an innovative approach using machine learning techniques to analyze the impact of environmental pollution on public health. The present study is based on the comparison of various automated analysis methods, with special emphasis on Random Forests, highlighting their potential to model complex relationships in environmental and health data. To this end, an exhaustive data preprocessing has been carried out, along with a rigorous evaluation of spatial interpolation methods, prioritizing the Inverse Distance Weighting method for its e!ectiveness and suitability to the type of data analyzed. This project contributes to expanding the traditional biostatistical perspective by integrating advanced machine learning tools to provide a more precise and robust interpretation of pollution’s impact on health, thus facilitating informed decisionmaking in environmental and health public policies.
In the current context, climate change debates have renewed concern about the effects of environmental pollution on our surroundings. This project proposes an innovative approach using machine learning techniques to analyze the impact of environmental pollution on public health. The present study is based on the comparison of various automated analysis methods, with special emphasis on Random Forests, highlighting their potential to model complex relationships in environmental and health data. To this end, an exhaustive data preprocessing has been carried out, along with a rigorous evaluation of spatial interpolation methods, prioritizing the Inverse Distance Weighting method for its e!ectiveness and suitability to the type of data analyzed. This project contributes to expanding the traditional biostatistical perspective by integrating advanced machine learning tools to provide a more precise and robust interpretation of pollution’s impact on health, thus facilitating informed decisionmaking in environmental and health public policies.
Description
Bibliographic citation
Collections
Endorsement
Review
Supplemented By
Referenced by
Creative Commons license
Except where otherwised noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International










