| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Solos. |
|
Data corrente: |
16/11/2022 |
|
Data da última atualização: |
22/11/2022 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
FERREIRA, A. C. de S.; CEDDIA, M. B.; COSTA, E. M.; PINHEIRO, E. F. M.; NASCIMENTO, M. M. do; VASQUES, G. M. |
|
Afiliação: |
ANA CAROLINA DE S. FERREIRA, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; MARCOS B. CEDDIA, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; ELIAS M. COSTA, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; ÉRIKA F. M. PINHEIRO, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; MARIANA MELO DO NASCIMENTO, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; GUSTAVO DE MATTOS VASQUES, CNPS. |
|
Título: |
Use of airborne radar images and machine learning algorithms to map soil clay, silt, and sand contents in remote areas under the Amazon rainforest. |
|
Ano de publicação: |
2022 |
|
Fonte/Imprenta: |
Remote Sensing, v. 14, n. 22, 5711, 2022. |
|
DOI: |
https://doi.org/10.3390/rs14225711 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Soil texture has a great influence on the physical-hydric and chemical behavior of soils. In the Amazon regions, due to the presence of dense forest cover and limited access to roads, carrying out surveys and mapping of soils is challenging. When data exist, they are relatively sparse and the distribution is quite uneven. In this context, machine learning algorithms (ML) associated with remote sensor covariates offer a framework to derive digital maps of soil attributes. The objective of this study was to produce maps of surface and subsurface soil clay, silt, and sand contents in a 13.440 km2 area in the Amazon. The specific objectives were to a) evaluate the gain in prediction accuracy when using the P-band of airborne radar as a covariate; b) evaluate two sampling approaches (Reference Area-RA and Total Area-TA); and c) evaluate the transferability and performance of three ML algorithms: regression tree (RT), random forest (RF), and support vector machine (SVM). The study site was divided into three blocks, called Urucu, Araracanga, and Juruá, respectively. The soil dataset consisted of 151 surface and subsurface sand, silt, and clay observations and 21 covariates (20 relief variables and the backscattering coefficient from the P-band). Both the RA and TA sampling approach used 114 observations for training the prediction models (75%) and 37 for validation (25%). The RA approach was better for the development of sand and silt models. Overall, RF derived the most accurate predictions for all variables. The effect of introducing the P-band backscattering coefficient improved the sand prediction accuracy at the surface and subsurface in Araracanga, which had the highest sand content, with relative improvements (RI) of the R2, root mean square error (RMSE), and mean absolute error (MAE) of 46%, 3%, and 4% at the surface, respectively, and 66.7%, 4.4%, and 5.2% at the subsurface, respectively. For silt, the P-band improved the predictions at the surface in Araracanga, which had the lowest silt contents among the blocks. For clay, adding the P-band improved the RF predictions at the subsurface, with RI of the R2, RMSE, and MAE of 29%, 5%, and 5%, respectively. Despite the low observation density, inherently hindered by the low accessibility of the area and high costs of sampling thereof, the results showed the potential of ML algorithms boosted by airborne radar P-band to map soil clay, silt, and sand contents in the Amazon. MenosSoil texture has a great influence on the physical-hydric and chemical behavior of soils. In the Amazon regions, due to the presence of dense forest cover and limited access to roads, carrying out surveys and mapping of soils is challenging. When data exist, they are relatively sparse and the distribution is quite uneven. In this context, machine learning algorithms (ML) associated with remote sensor covariates offer a framework to derive digital maps of soil attributes. The objective of this study was to produce maps of surface and subsurface soil clay, silt, and sand contents in a 13.440 km2 area in the Amazon. The specific objectives were to a) evaluate the gain in prediction accuracy when using the P-band of airborne radar as a covariate; b) evaluate two sampling approaches (Reference Area-RA and Total Area-TA); and c) evaluate the transferability and performance of three ML algorithms: regression tree (RT), random forest (RF), and support vector machine (SVM). The study site was divided into three blocks, called Urucu, Araracanga, and Juruá, respectively. The soil dataset consisted of 151 surface and subsurface sand, silt, and clay observations and 21 covariates (20 relief variables and the backscattering coefficient from the P-band). Both the RA and TA sampling approach used 114 observations for training the prediction models (75%) and 37 for validation (25%). The RA approach was better for the development of sand and silt models. Overall, RF derived the most accurate ... Mostrar Tudo |
|
Palavras-Chave: |
Digital soil mapping; Radar P-band; Reference area. |
|
Thesagro: |
Mapa; Reconhecimento do Solo; Textura do Solo. |
|
Thesaurus Nal: |
Soil surveys; Soil texture. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/doc/1148295/1/Use-of-airborne-radar-images-and-machine-learning-algorithms-2022.pdf
|
|
Marc: |
LEADER 03374naa a2200289 a 4500
001 2148295
005 2022-11-22
008 2022 bl uuuu u00u1 u #d
024 7 $ahttps://doi.org/10.3390/rs14225711$2DOI
100 1 $aFERREIRA, A. C. de S.
245 $aUse of airborne radar images and machine learning algorithms to map soil clay, silt, and sand contents in remote areas under the Amazon rainforest.$h[electronic resource]
260 $c2022
520 $aSoil texture has a great influence on the physical-hydric and chemical behavior of soils. In the Amazon regions, due to the presence of dense forest cover and limited access to roads, carrying out surveys and mapping of soils is challenging. When data exist, they are relatively sparse and the distribution is quite uneven. In this context, machine learning algorithms (ML) associated with remote sensor covariates offer a framework to derive digital maps of soil attributes. The objective of this study was to produce maps of surface and subsurface soil clay, silt, and sand contents in a 13.440 km2 area in the Amazon. The specific objectives were to a) evaluate the gain in prediction accuracy when using the P-band of airborne radar as a covariate; b) evaluate two sampling approaches (Reference Area-RA and Total Area-TA); and c) evaluate the transferability and performance of three ML algorithms: regression tree (RT), random forest (RF), and support vector machine (SVM). The study site was divided into three blocks, called Urucu, Araracanga, and Juruá, respectively. The soil dataset consisted of 151 surface and subsurface sand, silt, and clay observations and 21 covariates (20 relief variables and the backscattering coefficient from the P-band). Both the RA and TA sampling approach used 114 observations for training the prediction models (75%) and 37 for validation (25%). The RA approach was better for the development of sand and silt models. Overall, RF derived the most accurate predictions for all variables. The effect of introducing the P-band backscattering coefficient improved the sand prediction accuracy at the surface and subsurface in Araracanga, which had the highest sand content, with relative improvements (RI) of the R2, root mean square error (RMSE), and mean absolute error (MAE) of 46%, 3%, and 4% at the surface, respectively, and 66.7%, 4.4%, and 5.2% at the subsurface, respectively. For silt, the P-band improved the predictions at the surface in Araracanga, which had the lowest silt contents among the blocks. For clay, adding the P-band improved the RF predictions at the subsurface, with RI of the R2, RMSE, and MAE of 29%, 5%, and 5%, respectively. Despite the low observation density, inherently hindered by the low accessibility of the area and high costs of sampling thereof, the results showed the potential of ML algorithms boosted by airborne radar P-band to map soil clay, silt, and sand contents in the Amazon.
650 $aSoil surveys
650 $aSoil texture
650 $aMapa
650 $aReconhecimento do Solo
650 $aTextura do Solo
653 $aDigital soil mapping
653 $aRadar P-band
653 $aReference area
700 1 $aCEDDIA, M. B.
700 1 $aCOSTA, E. M.
700 1 $aPINHEIRO, E. F. M.
700 1 $aNASCIMENTO, M. M. do
700 1 $aVASQUES, G. M.
773 $tRemote Sensing$gv. 14, n. 22, 5711, 2022.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Solos (CNPS) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 16 | |
| 3. |  | EVANGELISTA, J. S.; NEVES, E. de S.; AZEVEDO, V. R.; WADT, L. H. de O. Germinação de sementes de castanheira para produção de mudas. In: SEMINÁRIO DE INICIAÇÃO CIENTÍFICA PIBIC/PIBITI EMBRAPA ACRE, 1., 2013, Rio Branco, AC. Anais... Rio Branco, AC: Embrapa Acre, 2013. 7 p.| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Acre. |
|    |
| 4. | | AZEVEDO, V. R.; ALVARES, V. de S.; KLIMAS, C. A.; WADT, L. H. de O. Identificação e caracterização de métodos de extração de óleo de andiroba. In: SEMINÁRIO DE INICIAÇÃO CIENTÍFICA PIBIC/CNPq/UFAC, 13., 2004, Rio Branco, AC. Anais... Rio Branco, AC: Ufac, 2004. 1 p.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Acre. |
| |
| 6. | | PACHECO JÚNIOR, F.; AZEVEDO, V. R.; RAMOS, L. de B.; SALES, F. de; DRUMOND, P. M. Trap-nesting bees and wasp in the State of Acre, amazon region, Brazil. In: ENCONTRO SOBRE ABELHAS, 10., 2012, Ribeirão Preto. Anais... Ribeirão Preto: FUNPEC, 2012. 1 CD-ROM.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Acre. |
| |
| 8. | | KLIMAS, C. A.; AZEVEDO, V. R.; SILVA, A. C. C. da; KAINER, K. A.; WADT, L. H. de O. Andiroba: aspectos ecológicos e considerações para o manejo. In: SIVIERO, A.; MING, L. C.; SILVEIRA, M.; DALY, D. C.; WALLACE, R. H. (org.). Etnobotânica e botânica econômica do Acre. Rio Branco, AC: Edufac, 2016. cap. 9, p. 141-154.| Tipo: Capítulo em Livro Técnico-Científico |
| Biblioteca(s): Embrapa Acre. |
|  |
| 9. | | AZEVEDO, V. R.; WADT, L. H. de O.; PEDROZO, C. A.; FONSECA, F. L. da; RESENDE, M. D. V. de. Coeficiente de repetibilidade para produção de frutos e seleção de matrizes de Bertholletia excelsa (Bonpl.) em castanhais nativos do estado do Acre. Ciência Florestal, Santa Maria, v. 30, n. 1, p. 135-144, jan./mar. 2020.| Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 2 |
| Biblioteca(s): Embrapa Acre; Embrapa Florestas; Embrapa Rondônia; Embrapa Roraima. |
| |
| 10. | | SILVA, S. M. M.; AZEVEDO, V. R.; RIBAS, L. A.; WADT, L. H. de O.; MESQUITA, A. G. G. Estrutura populacional de jatobá em florestas manejadas na Amazônia Sul-Ocidental. In: CONGRESSO DE ECOLOGIA DO BRASIL, 9.; CONGRESSO LATINO AMERICANO DE ECOLOGIA, 3., 2009, São Lourenço. Ecologia e o futuro da biosfera: anais. São Paulo: SEB: Instituto de Biociências, 2009. 2 p.| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Acre. |
| |
| 12. | | BALDONI, A. B.; SEBBENN, A. M.; AZEVEDO, V. R.; BOTIN, A. A.; TONINI, H.; HOOGERHEIDE, E. S. S. Estudo da diversidade genética e estrutura populacional de castanheira-do-brasil (Bertholletia excelsa) em florestas nativas do Mato Grosso. In. CONGRESSO BRASILEIRO DE RECURSOS GENÉTICOS, 3., 2014, Santos. Anais... Brasília, DF: Sociedade Brasileira de Recursos Genéticos, 2014. Resumo. 150. 1 CD-ROM.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Agrossilvipastoril; Embrapa Recursos Genéticos e Biotecnologia. |
| |
| 13. | | KLIMAS, C. A.; KAINER, K. A.; WADT, L. H. de O.; AZEVEDO, V. R.; CORREIA, M. F. Produção de sementes e regeneração de Carapa guianensis em dois ambientes de floresta primária na Amazônia, estado do Acre nos anos de 2004 a 2007. In: SEMINÁRIO ANUAL DE COOPERAÇÃO UFAC/UF, 6., 2008, Rio Branco. Parcerias em pesquisa e pós-graduação: anais. Rio Branco: Ufac; University of Florida, 2008. p. 139. 1 CD-ROM.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Acre. |
| |
| 14. | | AZEVEDO, V. R.; WADT, L. H. de O.; PEDROZO, C.; FONSECA, F. L.; EVANGELISTA, J. S.; REIS, S. F. dos. Seleção de matrizes de bertholletia excelsa bonpl em populações naturais no estado do Acre. In: CONGRESSO DE ECOLOGIA DO BRASIL, 12., 2015, São Lourenço. [Anais...]. [São Lourenço: CEB], 2015.| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Rondônia. |
| |
| 15. | | KLIMAS, C. A; KAINER, K. A.; AZEVEDO, V. R.; CORREIA, M. F.; STAUDHAMMER, C.; LIMA, L. M. da S.; WADT, L. H. de O. Fenologia e produção de sementes de Carapa guianensis (andiroba): um estudo de 5 anos para definir as características das árvores e variáveis climáticas influenciando a produção de sementes. In: SEMINÁRIO ANUAL DE COOPERAÇÃO UFAC/UF, 2009, Rio Branco. Parcerias em pesquisa e ação para a conservação e desenvolvimento sustentável: anais. Rio Branco, AC: Ufac, 2009. p. 253. 1 CD-ROM.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Acre. |
| |
| 16. | | MUNIZ, A. V. C. da S.; VITORIA, M. F.; AZEVEDO, V. R. R.; SA. A. J.; NASCIMENTO, A. L. S.; CARDOSO, M. N.; SOARES, A. N. R.; SILVA JUNIOR, J. F.; LEDO, A. da S. Genetic diversity of the mangaba genebank using microsatellites. Genetics and Molecular Research, v. 18, n. 1, p. 18108, 2019.| Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 2 |
| Biblioteca(s): Embrapa Tabuleiros Costeiros. |
| |
| Registros recuperados : 16 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
