Publicação

Soil Landscape Modelling – placing place in its place

Ver documento

Detalhes bibliográficos
Resumo:Landscape variables, which are also factors of soil formation, can be combined with existing soil map data to train Artificial Neural Networks (ANNs) in order to predict soil types in unmapped areas. In this study, the impact of location data and proximity of the training data on the performance of ANN models, for two catchments in northern Portugal, is evaluated. Results are largely concurrent between catchments, indicating that using latitude and longitude data produces more accurate models, whilst taking into account the spatial autocorrelative properties of input data makes ANN models converge for a better “local” rather than “global” solution. The conclusion is that hillslopes show some degree of connectivity which is passed onto soils, and conforms to the principles of the catena concept.
Autores principais:Fonseca, Inês
Outros Autores:Freire, Sérgio; Brasil, Ricardo; Rocha, Jorge; Tenedório, José A.
Assunto:Landscape Artificial Neural Networks Soil maps Geographical Information Systems
Ano:2013
País:Portugal
Tipo de documento:capítulo de livro
Tipo de acesso:acesso aberto
Instituição associada:Universidade de Lisboa
Idioma:inglês
Origem:Repositório da Universidade de Lisboa
_version_ 1865920806197919744
author Fonseca, Inês
author2 Freire, Sérgio
Brasil, Ricardo
Rocha, Jorge
Tenedório, José A.
author2_role author
author
author
author
author_facet Fonseca, Inês
Fonseca, Inês
Freire, Sérgio
Brasil, Ricardo
Rocha, Jorge
Tenedório, José A.
Freire, Sérgio
Brasil, Ricardo
Rocha, Jorge
Tenedório, José A.
author_role author
contributor_name_str_mv Repositório Científico de Acesso Aberto da ULisboa
country_str PT
creators_json_str [{\"Person.name\":\"Fonseca, Inês\"},{\"Person.name\":\"Freire, Sérgio\"},{\"Person.name\":\"Brasil, Ricardo\"},{\"Person.name\":\"Rocha, Jorge\",\"Person.identifier.orcid\":\"0000-0002-7228-6330\"},{\"Person.name\":\"Tenedório, José A.\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Repositório Científico de Acesso Aberto da ULisboa
datacite.creators.creator.creatorName.fl_str_mv Fonseca, Inês
Freire, Sérgio
Brasil, Ricardo
Rocha, Jorge
Tenedório, José A.
datacite.date.Accepted.fl_str_mv 2013-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2023-06-08T18:32:41Z
datacite.date.embargoed.fl_str_mv 2023-06-08T18:32:41Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Landscape
Artificial Neural Networks
Soil maps
Geographical Information Systems
datacite.titles.title.fl_str_mv Soil Landscape Modelling – placing place in its place
dc.contributor.none.fl_str_mv Repositório Científico de Acesso Aberto da ULisboa
dc.creator.none.fl_str_mv Fonseca, Inês
Freire, Sérgio
Brasil, Ricardo
Rocha, Jorge
Tenedório, José A.
dc.date.Accepted.fl_str_mv 2013-01-01T00:00:00Z
dc.date.available.fl_str_mv 2023-06-08T18:32:41Z
dc.date.embargoed.fl_str_mv 2023-06-08T18:32:41Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10451/58133
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv APGEOM
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Landscape
Artificial Neural Networks
Soil maps
Geographical Information Systems
dc.title.fl_str_mv Soil Landscape Modelling – placing place in its place
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_3248
description Landscape variables, which are also factors of soil formation, can be combined with existing soil map data to train Artificial Neural Networks (ANNs) in order to predict soil types in unmapped areas. In this study, the impact of location data and proximity of the training data on the performance of ANN models, for two catchments in northern Portugal, is evaluated. Results are largely concurrent between catchments, indicating that using latitude and longitude data produces more accurate models, whilst taking into account the spatial autocorrelative properties of input data makes ANN models converge for a better “local” rather than “global” solution. The conclusion is that hillslopes show some degree of connectivity which is passed onto soils, and conforms to the principles of the catena concept.
dirty 0
eu_rights_str_mv openAccess
format bookPart
fulltext.url.fl_str_mv https://repositorio.ulisboa.pt/bitstreams/93bb48c3-5ff6-48dd-92e8-433e30d4ca5b/download
id ul_745fdec334d5757e75c1951bfc3e2268
identifier.url.fl_str_mv http://hdl.handle.net/10451/58133
instacron_str ul
institution Universidade de Lisboa
instname_str Universidade de Lisboa
language eng
network_acronym_str ul
network_name_str Repositório da Universidade de Lisboa
oai_identifier_str oai:repositorio.ulisboa.pt:10451/58133
organization_str_mv urn:organizationAcronym:ul
person_str_mv Fonseca, Inês
Freire, Sérgio
Brasil, Ricardo
Rocha, Jorge
Rocha, Jorge
https://www.ciencia-id.pt/EC15-76DC-9B96
EC15-76DC-9B96
http://orcid.org/0000-0002-7228-6330
0000-0002-7228-6330
Tenedório, José A.
publishDate 2013
publisher.none.fl_str_mv APGEOM
reponame_str Repositório da Universidade de Lisboa
repository_id_str urn:repositoryAcronym:ul
service_str_mv urn:repositoryAcronym:ul
spelling engAPGEOMpt_PTLandscape variables, which are also factors of soil formation, can be combined with existing soil map data to train Artificial Neural Networks (ANNs) in order to predict soil types in unmapped areas. In this study, the impact of location data and proximity of the training data on the performance of ANN models, for two catchments in northern Portugal, is evaluated. Results are largely concurrent between catchments, indicating that using latitude and longitude data produces more accurate models, whilst taking into account the spatial autocorrelative properties of input data makes ANN models converge for a better “local” rather than “global” solution. The conclusion is that hillslopes show some degree of connectivity which is passed onto soils, and conforms to the principles of the catena concept.application/pdfpt_PTSoil Landscape Modelling – placing place in its placeFonseca, InêsFreire, SérgioBrasil, RicardoPersonalRocha, JorgeDSpacehttp://dspace.org/items/9c7dabc1-d6c6-4636-9293-6babe2ba64c9DSpacehttp://dspace.org/items/9c7dabc1-d6c6-4636-9293-6babe2ba64c9RochaJorgeCiência IDhttps://www.ciencia-id.ptEC15-76DC-9B96ORCIDhttp://orcid.org0000-0002-7228-6330Researcher IDhttps://www.researcherid.comF-3185-2017Researcher IDhttps://www.researcherid.comF-3185-2017Scopus Author IDhttps://www.scopus.com56428061000Tenedório, José A.HostingInstitutionOrganizationalRepositório Científico de Acesso Aberto da ULisboae-mailmailto:repositorio@reitoria.ulisboa.ptrepositorio@reitoria.ulisboa.ptISBNIsPartOf978-989-96462-4-72023-06-08T18:32:41Z20132013-01-01T00:00:00ZHandlehttp://hdl.handle.net/10451/58133http://purl.org/coar/access_right/c_abf2open accessLandscapeArtificial Neural NetworksSoil mapsGeographical Information Systems387912 bytesliteraturehttp://purl.org/coar/resource_type/c_3248book parthttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorio.ulisboa.pt/bitstreams/93bb48c3-5ff6-48dd-92e8-433e30d4ca5b/downloadVI Congresso Nacional de Geomorfologia: Geomorfologia – Novos e Velhos Desafios151155Coimbra, Portugal
spellingShingle Soil Landscape Modelling – placing place in its place
Soil Landscape Modelling – placing place in its place
Fonseca, Inês
Landscape
Artificial Neural Networks
Soil maps
Geographical Information Systems
Fonseca, Inês
Landscape
Artificial Neural Networks
Soil maps
Geographical Information Systems
status SINGLETON
subject.fl_str_mv Landscape
Artificial Neural Networks
Soil maps
Geographical Information Systems
title Soil Landscape Modelling – placing place in its place
title_full Soil Landscape Modelling – placing place in its place
title_fullStr Soil Landscape Modelling – placing place in its place
Soil Landscape Modelling – placing place in its place
title_full_unstemmed Soil Landscape Modelling – placing place in its place
Soil Landscape Modelling – placing place in its place
title_short Soil Landscape Modelling – placing place in its place
title_sort Soil Landscape Modelling – placing place in its place
topic Landscape
Artificial Neural Networks
Soil maps
Geographical Information Systems
topic_facet Landscape
Artificial Neural Networks
Soil maps
Geographical Information Systems
url http://hdl.handle.net/10451/58133
visible 1