Análisis temporal y pronóstico de la temperatura del aire superficial utilizando modelos SARIMA y SVAR: estudio de caso en Bogotá, Colombia

Vista sencilla de ítem
dc.contributor.authorTorres, Diego
dc.contributor.authorRomero, Manuel
dc.contributor.authorRomero Leiton, Johana
dc.coverage.spatialPaises Bajosspa
dc.date.accessioned2021-05-20T19:58:33Z
dc.date.available2021-05-20T19:58:33Z
dc.date.issued2020
dc.description.abstractIn this work, we study the short term dynamics of the Surface Air Temperature (SAT) using data obtained from a meteorological station in Bogotá from 2009 to 2019 and using time series. The data that we used correspond to the monthly mean of the historical registers of SAT and three pollutants. A descriptive analysis of the data follows. Then, some predictions are obtained from two different approaches: (i) a univariate analysis of SAT through a SARIMA model, which shows a good fit; and (ii) a multivariate analysis of SAT and pollutants using a SVAR model. Suitable transformations were first applied on the original dataset to work with stationary time series. Subsequently, A SARIMA model and a VAR(2) with its associated SVAR model are estimated. Furthermore, we obtain one year forecasts for the logarithm of SAT in both models. Our forecasts simulate the natural fluctuation of SAT, presenting peaks and valleys in months when SAT is high and low, respectively. The SVAR model allows us to identify certain shocks that affect the instant relationships among variables. These relations were studied by the impulse response function and the VAR model variance decomposition. The results are consistent with environmental theories.spa
dc.description.abstractenglishIn this work, we study the short term dynamics of the Surface Air Temperature (SAT) using data obtained from a meteorological station in Bogotá from 2009 to 2019 and using time series. The data that we used correspond to the monthly mean of the historical registers of SAT and three pollutants. A descriptive analysis of the data follows. Then, some predictions are obtained from two different approaches: (i) a univariate analysis of SAT through a SARIMA model, which shows a good fit; and (ii) a multivariate analysis of SAT and pollutants using a SVAR model. Suitable transformations were first applied on the original dataset to work with stationary time series. Subsequently, A SARIMA model and a VAR(2) with its associated SVAR model are estimated. Furthermore, we obtain one year forecasts for the logarithm of SAT in both models. Our forecasts simulate the natural fluctuation of SAT, presenting peaks and valleys in months when SAT is high and low, respectively. The SVAR model allows us to identify certain shocks that affect the instant relationships among variables. These relations were studied by the impulse response function and the VAR model variance decomposition. The results are consistent with environmental theories.spa
dc.description.publindexQ3spa
dc.description.researchgroupGrupo de Investigación en Diseño, Análisis y Desarrollo de Sistemas de Ingeniería -GIDADspa
dc.identifier.issn8684952
dc.identifier.urihttp://hdl.handle.net/11371/3999
dc.publisher.facultyFacultad de Ingenieria y Ciencias Basicasspa
dc.relation.citationvolume31spa
dc.relation.ispartofjournalInformatica Journalspa
dc.relation.urihttp://informaticajournal.com/index.htmlspa
dc.source.urihttp://informaticajournal.com/index.htmlspa
dc.titleAnálisis temporal y pronóstico de la temperatura del aire superficial utilizando modelos SARIMA y SVAR: estudio de caso en Bogotá, Colombiaspa
dc.title.translatedTemporal analysis and forecast of surface air temperature using SARIMA and SVAR models: case study in Bogotá, Colombiaspa
Archivos
Colecciones
GRUPO DE INVESTIGACIÓN EN INGENIERÍA APLICADA (GUIAS)