RT info:eu-repo/semantics/bachelorThesis
T1 Feasibility study of artificial intelligence techniques applied to the prediction of dust
A1 Galván Fraile, Victor
A2 Grado En Física
K1 Aerosol mineral, fuentes de polvo, aprendizaje automatico, ´
aprendizaje profundo, prediccion de polvo.
AB This end of degree project constitutes an introduction to the application ofMachine Learning techniques on the prediction of meteorological variables,concretely, aerosols. It presents a bibliographic review of the role onatmospheric phenomena played by dust, including not only its main sources,but the fundamental production mechanisms as well. Furthermore, it presentsa combination of theoretical concepts of Machine Learning algorithms,mainly based on the guidelines of the book “Hands-on Machine Learningwith Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniquesto Build Intelligent Systems” [Ger19 ´ ], and on the courses of “Machine andDeep Learning” of the University of Standford, taught online at Coursera[Ng22]. The aim of this project is, therefore, to realize a first approach tosome of the basic algorithms of Machine Learning and put them into practice.Particularly, after a preprocessing phase of the data, two models with differentartificial intelligence architectures were build up, training and testing themwith different periods. Furthermore, a study of the input variables and thewindow sizes has been carried out in order to optimize the performance ofthe models. Finally, several analysis of the results obtained from them havebeen done, highlighting the strengths and weaknesses of each of them, inaddition to suggesting the basis for future projects in this field. Additionally,and with the aim of increasing the transversality of this study, two dustintrusion classifying models have been made, describing not only their maincharacteristics, but also the results obtained and their possible improvements.
YR 2022
FD 2022
LK http://riull.ull.es/xmlui/handle/915/28439
UL http://riull.ull.es/xmlui/handle/915/28439
LA es
DS Repositorio institucional de la Universidad de La Laguna
RD 04-may-2024