Robust streamflow forecasting: a Student's t-mixture vector autoregressive model

Simple item page
dc.catalogadorjca
dc.contributor.authorFavereau, Marcel
dc.contributor.authorLorca, Alvaro
dc.contributor.authorNegrete-Pincetic, Matias
dc.contributor.authorVicuña, Sebastian
dc.date.accessioned2023-12-19T18:29:21Z
dc.date.available2023-12-19T18:29:21Z
dc.date.issued2022
dc.description.abstractAccurate streamflow forecasting is one of the main challenges in the management of reservoirs, where autoregressive models have been commonly used. Typically, the noise of these models is considered Gaussian. However, this assumption can overestimate the presence of outliers, generally presented in water inflow real-world data. Motivated by this, we propose a novel streamflow forecasting method by modeling the noise of a vector autoregressive model as a multivariate Student's t-mixture based on the use of the variational expectation-maximization algorithm. The proposed model is able to capture the trend, seasonality, and spatio-temporal correlations of hydro inflows, along with both asymmetry and multimodal features of the vector autoregressive process' residuals. Based on 12 of the main inflows of the Chilean hydroelectric network, our experiments show the proposed model's efficiency and improvements for forecasting medium to long-term inflows over a classical vector autoregressive model. Results show that the expected forecasts are improved with the proposed model and the predictive distributions present tighter intervals based on standard and state-of-the-art metrics.
dc.fechaingreso.objetodigital2023-12-15
dc.fuente.origenWOS
dc.identifier.doi10.1007/s00477-022-02241-y
dc.identifier.eissn1436-3259
dc.identifier.issn1436-3240
dc.identifier.urihttps://doi.org/10.1007/s00477-022-02241-y
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/75543
dc.identifier.wosidWOS:000800800500001
dc.information.autorucEscuela de Ingeniería;Favereau, Marcel;0000-0001-8573-2742;1086200
dc.information.autorucEscuela de Ingeniería;Lorca, Alvaro;0000-0002-9864-0932;148348
dc.information.autorucEscuela de Ingeniería;Negrete Pincetic, Matías;S/I;13212
dc.language.isoen
dc.nota.accesoContenido completo
dc.pagina.final3995
dc.pagina.inicio3979
dc.publisherSPRINGER
dc.revistaStochasticEnvironmentalResearchandRiskAssessment
dc.rightsacceso abierto
dc.subjectStreamflow forecasting
dc.subjectWater resources management
dc.subjectVector autoregressive model
dc.subjectMixture model
dc.subject.ddc550
dc.subject.deweyCiencias de la tierraes_ES
dc.titleRobust streamflow forecasting: a Student's t-mixture vector autoregressive model
dc.typeartículo
dc.volumen36
sipa.codpersvinculados1086200
sipa.codpersvinculados148348
sipa.codpersvinculados13212
sipa.trazabilidadWOS;2022-07-08
sipa.trazabilidadORCID;2023-12-11
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
robust.pdf
Size:
2.59 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas