Registro Completo |
Biblioteca(s): |
Embrapa Solos. |
Data corrente: |
09/10/2023 |
Data da última atualização: |
07/12/2023 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
SANTOS, P. A. dos; PINHEIRO, H. S. K.; CARVALHO JUNIOR, W. de; SILVA, I. L. da; PEREIRA, N. R.; BHERING, S. B.; CEDDIA, M. B. |
Afiliação: |
PRISCILLA AZEVEDO DOS SANTOS, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; HELENA SARAIVA KOENOW PINHEIRO, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; WALDIR DE CARVALHO JUNIOR, CNPS; IGOR LEITE DA SILVA, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; NILSON RENDEIRO PEREIRA, CNPS; SILVIO BARGE BHERING, CNPS; MARCOS BACIS CEDDIA, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO. |
Título: |
Hydropedological digital mapping: machine learning applied to spectral VIS-IR and radiometric data dimensionality reduction. |
Ano de publicação: |
2023 |
Fonte/Imprenta: |
Revista Brasileira de Ciência do Solo, v. 47, e0220149, 2023. |
DOI: |
https://doi.org/10.36783/18069657rbcs20220149 |
Idioma: |
Inglês |
Conteúdo: |
Pedosphere-hydrosphere interface accounts for the association between soil hydrology and landscape, represented by topographic and Remote Sensing data support and integration. This study aimed to analyze different statistical radiometric and spectral data selection methods and dimensionality reduce environment-related data to support the classification of soil physical-hydric properties, such as soil basic infiltration rate (bir) and saturated hydraulic conductivity (Ksat); as well as to act in data mining processes applied to hydropedological properties digital mapping. Accordingly, research integrated information from Visible to Infrared (VIS-IR) spectral indices and Sentinel's 2A mission Multispectral Instrument (MSI) sensor bands, terrain numerical modeling and aerogeophysics set to model soil-water content in two soil layers (0.00-0.20 m and 0.20-0.40 m). Pre-processed data were subjected to statistical analysis (multivariate and hypothesis tests); subsequently, the methods were applied (variation inflation factor - VIF, Stepwise Akaike information criterion - Stepwise AIC, and recursive feature elimination - RFE) to mine covariates used for Random Forest modeling. Based on the results, there were distinctions and singularities in spectral and radiometric data selection for each adopted method; the importance degree, and contribution of each one to soil physical-hydric properties have varied. According to the applied statistical metrics and decision-making criteria (highest R2 and lowest RMSE / MAE), the chosen methods were RFE (0.00-0.20 m layers) and Stepwise AIC (0.20-0.40 m layers) - both concerned with the assessed variables (bir and Ksat). This approach captured the importance of environmental variables and highlighted their potential use in hydropedological digital mapping at Guapi-Macacu watershed. MenosPedosphere-hydrosphere interface accounts for the association between soil hydrology and landscape, represented by topographic and Remote Sensing data support and integration. This study aimed to analyze different statistical radiometric and spectral data selection methods and dimensionality reduce environment-related data to support the classification of soil physical-hydric properties, such as soil basic infiltration rate (bir) and saturated hydraulic conductivity (Ksat); as well as to act in data mining processes applied to hydropedological properties digital mapping. Accordingly, research integrated information from Visible to Infrared (VIS-IR) spectral indices and Sentinel's 2A mission Multispectral Instrument (MSI) sensor bands, terrain numerical modeling and aerogeophysics set to model soil-water content in two soil layers (0.00-0.20 m and 0.20-0.40 m). Pre-processed data were subjected to statistical analysis (multivariate and hypothesis tests); subsequently, the methods were applied (variation inflation factor - VIF, Stepwise Akaike information criterion - Stepwise AIC, and recursive feature elimination - RFE) to mine covariates used for Random Forest modeling. Based on the results, there were distinctions and singularities in spectral and radiometric data selection for each adopted method; the importance degree, and contribution of each one to soil physical-hydric properties have varied. According to the applied statistical metrics and decision-making criteria (hig... Mostrar Tudo |
Palavras-Chave: |
Applied statistics; Estatística aplicada; Geoprocessamento; Geoprocessing; Hidropedologia; Hydropedology; Radiometria. |
Thesagro: |
Sensoriamento Remoto. |
Thesaurus Nal: |
Radiometry; Remote sensing. |
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/doc/1157151/1/Hydropedological-digital-mapping-2023.pdf
|
Marc: |
LEADER 02864naa a2200325 a 4500 001 2157151 005 2023-12-07 008 2023 bl uuuu u00u1 u #d 024 7 $ahttps://doi.org/10.36783/18069657rbcs20220149$2DOI 100 1 $aSANTOS, P. A. dos 245 $aHydropedological digital mapping$bmachine learning applied to spectral VIS-IR and radiometric data dimensionality reduction.$h[electronic resource] 260 $c2023 520 $aPedosphere-hydrosphere interface accounts for the association between soil hydrology and landscape, represented by topographic and Remote Sensing data support and integration. This study aimed to analyze different statistical radiometric and spectral data selection methods and dimensionality reduce environment-related data to support the classification of soil physical-hydric properties, such as soil basic infiltration rate (bir) and saturated hydraulic conductivity (Ksat); as well as to act in data mining processes applied to hydropedological properties digital mapping. Accordingly, research integrated information from Visible to Infrared (VIS-IR) spectral indices and Sentinel's 2A mission Multispectral Instrument (MSI) sensor bands, terrain numerical modeling and aerogeophysics set to model soil-water content in two soil layers (0.00-0.20 m and 0.20-0.40 m). Pre-processed data were subjected to statistical analysis (multivariate and hypothesis tests); subsequently, the methods were applied (variation inflation factor - VIF, Stepwise Akaike information criterion - Stepwise AIC, and recursive feature elimination - RFE) to mine covariates used for Random Forest modeling. Based on the results, there were distinctions and singularities in spectral and radiometric data selection for each adopted method; the importance degree, and contribution of each one to soil physical-hydric properties have varied. According to the applied statistical metrics and decision-making criteria (highest R2 and lowest RMSE / MAE), the chosen methods were RFE (0.00-0.20 m layers) and Stepwise AIC (0.20-0.40 m layers) - both concerned with the assessed variables (bir and Ksat). This approach captured the importance of environmental variables and highlighted their potential use in hydropedological digital mapping at Guapi-Macacu watershed. 650 $aRadiometry 650 $aRemote sensing 650 $aSensoriamento Remoto 653 $aApplied statistics 653 $aEstatística aplicada 653 $aGeoprocessamento 653 $aGeoprocessing 653 $aHidropedologia 653 $aHydropedology 653 $aRadiometria 700 1 $aPINHEIRO, H. S. K. 700 1 $aCARVALHO JUNIOR, W. de 700 1 $aSILVA, I. L. da 700 1 $aPEREIRA, N. R. 700 1 $aBHERING, S. B. 700 1 $aCEDDIA, M. B. 773 $tRevista Brasileira de Ciência do Solo$gv. 47, e0220149, 2023.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Solos (CNPS) |
|