Show simple item record

dc.contributor.authorHagen, Jenny Sjåstad
dc.contributor.authorLeblois, Etienne
dc.contributor.authorLawrence, Deborah
dc.contributor.authorSolomatine, Dimitri
dc.contributor.authorSorteberg, Asgeir
dc.date.accessioned2022-03-22T07:00:19Z
dc.date.available2022-03-22T07:00:19Z
dc.date.created2021-09-07T16:31:54Z
dc.date.issued2021
dc.identifier.issn0022-1694
dc.identifier.urihttps://hdl.handle.net/11250/2986669
dc.description.abstractPrevious studies linking large-scale atmospheric circulation and river flow with traditional machine learning techniques have predominantly explored monthly, seasonal or annual streamflow modelling for applications in direct downscaling or hydrological climate-impact studies. This paper identifies major drivers of daily streamflow from large-scale atmospheric circulation using two reanalysis datasets for six catchments in Norway representing various Köppen-Geiger climate types and flood-generating processes. A nested loop of roughly pruned random forests is used for feature extraction, demonstrating the potential for automated retrieval of physically consistent and interpretable input variables. Random forest (RF), support vector machine (SVM) for regression and multilayer perceptron (MLP) neural networks are compared to multiple-linear regression to assess the role of model complexity in utilizing the identified major drivers to reconstruct streamflow. The machine learning models were trained on 31 years of aggregated atmospheric data with distinct moving windows for each catchment, reflecting catchment-specific forcing-response relationships between the atmosphere and the rivers. The results show that accuracy improves to some extent with model complexity. In all but the smallest, rainfall-driven catchment, the most complex model, MLP, gives a Nash-Sutcliffe Efficiency (NSE) ranging from 0.71 to 0.81 on testing data spanning five years. The poorer performance by all models in the smallest catchment is discussed in relation to catchment characteristics, sub-grid topography and local variability. The intra-model differences are also viewed in relation to the consistency between the automatically retrieved feature selections from the two reanalysis datasets. This study provides a benchmark for future development of deep learning models for direct downscaling from large-scale atmospheric variables to daily streamflow in Norway.en_US
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.urihttps://www.sciencedirect.com/science/article/pii/S0022169421001335
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.titleIdentifying major drivers of daily streamflow from large-scale atmospheric circulation with machine learningen_US
dc.typeJournal articleen_US
dc.typePeer revieweden_US
dc.description.versionpublishedVersionen_US
dc.rights.holderCopyright 2021 The Author(s)en_US
dc.source.articlenumber126086en_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode2
dc.identifier.doi10.1016/j.jhydrol.2021.126086
dc.identifier.cristin1932156
dc.source.journalJournal of Hydrologyen_US
dc.relation.projectNorges forskningsråd: 295046en_US
dc.subject.nsiVDP::Matematikk og naturvitenskap: 400en_US
dc.subject.nsiVDP::Mathematics and natural scienses: 400en_US
dc.identifier.citationJournal of Hydrology. 2021, 596, 126086.en_US
dc.source.volume596en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Navngivelse 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Navngivelse 4.0 Internasjonal