Show simple item record

dc.contributor.authorLarraondo P.R.en_US
dc.contributor.authorRenzullo L.J.en_US
dc.contributor.authorVan Dijk A.I.J.M.en_US
dc.contributor.authorInza I.en_US
dc.contributor.authorLozano J.A.en_US
dc.date.accessioned2020-05-14T15:35:28Z
dc.date.available2020-05-14T15:35:28Z
dc.date.issued2020
dc.identifier.issn19422466
dc.identifier.urihttp://hdl.handle.net/20.500.11824/1106
dc.description.abstractThis work introduces a methodology for optimizing neural network models using a combination of continuous and categorical binary indices in the context of precipitation forecasting. Probability of detection or false alarm rate are popular metrics used in the verification of precipitation models. However, machine learning models trained using gradient descent cannot be optimized based on these metrics, as they are not differentiable. We propose an alternative formulation for these categorical indices that are differentiable and we demonstrate how they can be used to optimize the skill of precipitation neural network models defined as a multi-objective optimization problem. To our knowledge, this is the first proposal of a methodology for optimizing weather neural network models based on categorical indices.en_US
dc.description.sponsorshipTIN2016-78365-Ren_US
dc.formatapplication/pdfen_US
dc.language.isoengen_US
dc.publisherJournal of Advances in Modeling Earth Systemsen_US
dc.relationES/1PE/SEV-2017-0718en_US
dc.relationEUS/BERC/BERC.2018-2021en_US
dc.relationEUS/ELKARTEKen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/es/en_US
dc.subjectmachine learningen_US
dc.subjectoptimizationen_US
dc.subjectdeep learningen_US
dc.subjectprecipitationsen_US
dc.subjectbinary metricsen_US
dc.titleOptimization of deep learning precipitation models using categorical binary metricsen_US
dc.typeinfo:eu-repo/semantics/articleen_US
dc.typeinfo:eu-repo/semantics/acceptedVersionen_US
dc.identifier.doihttps://doi.org/10.1002/qj.828.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

info:eu-repo/semantics/openAccess
Except where otherwise noted, this item's license is described as info:eu-repo/semantics/openAccess