Please use this identifier to cite or link to this item:
Title: Predicción de la calidad del aire de la ciudad de Madrid mediante técnicas de machine-learning
Author: Sanjuán de Caso, Marta
Tutor: Parada Medina, Raúl  
Others: Casas-Roma, Jordi  
Abstract: Climate change is ever more topical issue and the pollution is closely linked, impacting in a direct way into the air quality. It may cause serious consequences on human health and natural environment. To help to reduce the effects of pollution, there are been established appropriate policy to solve it that forcing pollutants to minimize their impacts in different levels of forcefulness. Considering that, it has been established measuring monitoring stations that may obtain in a constant way a variety of indexes that can be established the air quality. This measurements together with weather history and non-working days history, that can be obtain in open data sources, let us to develop prediction models able to predict the evolution of air quality a few days in advance, and it may allow to institutional agents act accordingly. The aim of this master's degrees final project is obtain a predictive model good enough to be used to predict the air quality forecast a few days in advance in a reliable and accurate way, and in this way public institutions will able to act with enough time in advance. For this purpose, it will apply different techniques and data mining algorithms (RNN, LSTM, and GRU) to the open data offered by the public institutions. A secondary objective will be to obtain specific predictions by area of the city, making use of measurement point location information and be able to make predictions more accurate by area indeed.
Keywords: prediction
air quality index
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 24-Jun-2020
Publication license:  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 


484,17 MBMP4View/Open
martasanjuanTFM0620memoria.pdfMemoria del TFM3,71 MBAdobe PDFThumbnail