Logo do repositório
 
Publicação

Geospatial data disaggregation through self-trained encoder–decoder convolutional models

2021-09-16Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorMonteiro, João
dc.contributor.authorMartins, Bruno
dc.contributor.authorCosta, Miguel
dc.contributor.authorPires, João M.
dc.contributor.institutionNOVALincs
dc.contributor.pblMDPI - Multidisciplinary Digital Publishing Institute
dc.date.accessioned2022-07-28T22:25:23Z
dc.date.available2022-07-28T22:25:23Z
dc.date.issued2021-09-16
dc.description
dc.description.abstractDatasets collecting demographic and socio-economic statistics are widely available. Still, the data are often only released for highly aggregated geospatial areas, which can mask important local hotspots. When conducting spatial analysis, one often needs to disaggregate the source data, transforming the statistics reported for a set of source zones into values for a set of target zones, with a different geometry and a higher spatial resolution. This article reports on a novel dasymetric disaggregation method that uses encoder–decoder convolutional neural networks, similar to those adopted in image segmentation tasks, to combine different types of ancillary data. Model training constitutes a particular challenge. This is due to the fact that disaggregation tasks are ill-posed and do not entail the direct use of supervision signals in the form of training instances mapping lowresolution to high-resolution counts. We propose to address this problem through self-training. Our method iteratively refines initial estimates produced by disaggregation heuristics and training models with the estimates from previous iterations together with relevant regularization strategies. We conducted experiments related to the disaggregation of different variables collected for Continental Portugal into a raster grid with a resolution of 200 m. Results show that the proposed approach outperforms common alternative methods, including approaches that use other types of regression models to infer the dasymetric weights.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent15054784
dc.identifier.doi10.3390/ijgi10090619
dc.identifier.issn2220-9964
dc.identifier.otherPURE: 45672157
dc.identifier.otherPURE UUID: 4ab714fb-a6b2-4bb1-9561-84f8d5e21299
dc.identifier.otherScopus: 85116928682
dc.identifier.otherWOS: 000699817700001
dc.identifier.otherORCID: /0000-0001-9933-936X/work/116509052
dc.identifier.urihttp://hdl.handle.net/10362/142607
dc.identifier.urlhttps://www.scopus.com/pages/publications/85116928682
dc.language.isoeng
dc.peerreviewedyes
dc.relationinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FCCI-CIF%2F32607%2F2017/PT
dc.relationMIning MUlti-source and MUlti-modal geo-referenced information
dc.relationInstituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa
dc.subjectConvolutional neural networks
dc.subjectDasymetric disaggregation
dc.subjectDeep learning
dc.subjectEncoder–decoder neural networks
dc.subjectGeospatial data disaggregation
dc.subjectSelf-supervised learning
dc.subjectGeography, Planning and Development
dc.subjectComputers in Earth Sciences
dc.subjectEarth and Planetary Sciences (miscellaneous)
dc.titleGeospatial data disaggregation through self-trained encoder–decoder convolutional modelsen
dc.typejournal article
degois.publication.issue9
degois.publication.titleISPRS International Journal of Geo-Information
degois.publication.volume10
dspace.entity.typePublication
oaire.awardNumberPTDC/CCI-CIF/32607/2017
oaire.awardNumberUIDB/50021/2020
oaire.awardTitleMIning MUlti-source and MUlti-modal geo-referenced information
oaire.awardTitleInstituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FCCI-CIF%2F32607%2F2017/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F50021%2F2020/PT
oaire.fundingStream3599-PPCDT
oaire.fundingStream6817 - DCRRNI ID
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccess
relation.isProjectOfPublicationdba0d91c-9bac-4f62-a9ea-535d4f56499b
relation.isProjectOfPublication1cf59518-2425-4137-a914-53580cbf4712
relation.isProjectOfPublication.latestForDiscoverydba0d91c-9bac-4f62-a9ea-535d4f56499b

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
ijgi_10_00619_v2.pdf
Tamanho:
14.36 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)