1. Identificação | |
Tipo de Referência | Artigo em Revista Científica (Journal Article) |
Site | plutao.sid.inpe.br |
Código do Detentor | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
Identificador | 8JMKD3MGP3W/43NH6TT |
Repositório | sid.inpe.br/plutao/2020/12.07.14.52.46 (acesso restrito) |
Última Atualização | 2020:12.08.21.32.09 (UTC) lattes |
Repositório de Metadados | sid.inpe.br/plutao/2020/12.07.14.52.47 |
Última Atualização dos Metadados | 2022:01.04.01.31.24 (UTC) administrator |
DOI | 10.1016/j.jag.2020.102215 |
ISSN | 0303-2434 |
Rótulo | lattes: 9511166263268121 5 MartinsKalGelNagMac:2020:DeNeNe |
Chave de Citação | MartinsKalGelNagMac:2020:DeNeNe |
Título | Deep neural network for complex open-water wetland mapping using high-resolution WorldView-3 and airborne LiDAR data |
Ano | 2020 |
Mês | Dec. |
Data de Acesso | 16 maio 2024 |
Tipo de Trabalho | journal article |
Tipo Secundário | PRE PI |
Número de Arquivos | 1 |
Tamanho | 11634 KiB |
|
2. Contextualização | |
Autor | 1 Martins, Vitor S. 2 Kaleita, Amy L. 3 Gelder, Brian K. 4 Nagel, Gustavo Willy 5 Maciel, Daniel Andrade |
Grupo | 1 2 3 4 DIDPI-CGOBT-INPE-MCTIC-GOV-BR 5 SER-SRE-SESPG-INPE-MCTIC-GOV-BR |
Afiliação | 1 Iowa State University (ISU) 2 Iowa State University (ISU) 3 Iowa State University (ISU) 4 Instituto Nacional de Pesquisas Espaciais (INPE) 5 Instituto Nacional de Pesquisas Espaciais (INPE) |
Endereço de e-Mail do Autor | 1 vitors@iastate.edu 2 kaleita@iastate.edu 3 4 gustavo.nagel@inpe.br 5 daniel.maciel@inpe.br |
Revista | International Journal of Applied Earth Observation and Geoinformation |
Volume | 93 |
Páginas | e102215 |
Nota Secundária | B1_GEOCIÊNCIAS |
Histórico (UTC) | 2020-12-07 14:52:47 :: lattes -> administrator :: 2020-12-08 21:28:59 :: administrator -> lattes :: 2020 2020-12-08 21:32:10 :: lattes -> administrator :: 2020 2022-01-04 01:31:24 :: administrator -> simone :: 2020 |
|
3. Conteúdo e estrutura | |
É a matriz ou uma cópia? | é a matriz |
Estágio do Conteúdo | concluido |
Transferível | 1 |
Tipo do Conteúdo | External Contribution |
Tipo de Versão | publisher |
Palavras-Chave | Deep learning Small wetlands Machine learning Optical and LiDAR data PCA |
Resumo | Wetland inventory maps are essential information for the conservation and management of natural wetland areas. The classification framework is crucial for successful mapping of complex wetlands, including the model selection, input variables and training procedures. In this context, deep neural network (DNN) is a powerful technique for remote sensing image classification, but this model application for wetland mapping has not been discussed in the previous literature, especially using commercial WorldView-3 data. This study developed a new framework for wetland mapping using DNN algorithm and WorldView-3 image in the Millrace Flats Wildlife Management Area, Iowa, USA. The study area has several wetlands with a variety of shapes and sizes, and the minimum mapping unit was defined as 20 m2 (0.002 ha). A set of potential variables was derived from WorldView-3 and auxiliary LiDAR data, and a feature selection procedure using principal components analysis (PCA) was used to identify the most important variables for wetland classification. Furthermore, traditional machine learning methods (support vector machine, random forest and k-nearest neighbor) were also implemented for the comparison of results. In general, the results show that DNN achieved satisfactory results in the study area (overall accuracy = 93.33 %), and we observed a high spatial overlap between reference and classified wetland polygons (Jaccard index ∼0.8). Our results confirm that PCA-based feature selection was effective in the optimization of DNN performance, and vegetation and textural indices were the most informative variables. In addition, the comparison of results indicated that DNN classification achieved relatively similar accuracies to other methods. The total classification errors vary from 0.104 to 0.111 among the methods, and the overlapped areas between reference and classified polygons range between 87.93 and 93.33 %. Finally, the findings of this study have three main implications. First, the integration of DNN model and WorldView-3 image is useful for wetland mapping at 1.2-m, but DNN results did not outperform other methods in this study area. Second, the feature selection was important for model performance, and the combination of most relevant input parameters contributes to the success of all tested models. Third, the spatial resolution of WorldView-3 is appropriate to preserve the shape and extent of small wetlands, while the application of medium resolution image (30-m) has a negative impact on the accurate delineation of these areas. Since commercial satellite data are becoming more affordable for remote sensing users, this study provides a framework that can be utilized to integrate very high-resolution imagery and deep learning in the classification of complex wetland areas. |
Área | SRE |
Arranjo 1 | urlib.net > BDMCI > Fonds > Produção anterior à 2021 > DIDPI > Deep neural network... |
Arranjo 2 | urlib.net > Fonds > Produção pgr ATUAIS > SER > Deep neural network... |
Arranjo 3 | urlib.net > BDMCI > Fonds > LabISA > Deep neural network... |
Conteúdo da Pasta doc | acessar |
Conteúdo da Pasta source | não têm arquivos |
Conteúdo da Pasta agreement | não têm arquivos |
|
4. Condições de acesso e uso | |
Idioma | en |
Arquivo Alvo | martins_deep.pdf |
Grupo de Usuários | lattes |
Grupo de Leitores | administrator lattes |
Visibilidade | shown |
Política de Arquivamento | denypublisher denyfinaldraft24 |
Permissão de Leitura | deny from all and allow from 150.163 |
Permissão de Atualização | não transferida |
|
5. Fontes relacionadas | |
Unidades Imediatamente Superiores | 8JMKD3MGPCW/3EQCCU5 8JMKD3MGPCW/3F3NU5S 8JMKD3MGPCW/439EAFB |
Lista de Itens Citando | sid.inpe.br/bibdigital/2013/10.18.22.34 2 sid.inpe.br/bibdigital/2020/09.18.00.06 2 |
Divulgação | WEBSCI; PORTALCAPES; SCOPUS. |
Acervo Hospedeiro | dpi.inpe.br/plutao@80/2008/08.19.15.01 |
|
6. Notas | |
Campos Vazios | alternatejournal archivist callnumber copyholder copyright creatorhistory descriptionlevel e-mailaddress format isbn lineage mark mirrorrepository nextedition notes number orcid parameterlist parentrepositories previousedition previouslowerunit progress project resumeid rightsholder schedulinginformation secondarydate secondarykey session shorttitle sponsor subject tertiarymark tertiarytype url |
|
7. Controle da descrição | |
e-Mail (login) | simone |
atualizar | |
|