Assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships.
There is a relation of vegetation physiognomies with soil and geological conditions that can be represented spatially with the support of remote sensing data. The goal of this research was to map vegetation physiognomies in a mountainous area by using Sentinel-2 Multispectral Instrument (MSI) data and morphometrical covariates through data mining techniques. The research was based on red-edge (RE) bands, and indices, to classify phytophysiognomies at two taxonomic levels. The input data was pixel sampled based on field sample sites. Data mining procedures comprised covariate selection and supervised classification through the Random Forest model. Results showed the potential of bands 3, 5, and 6 to map phytophysiognomies for both seasons, as well as Green Chlorophyll (CLg) and SAVI indices. NDVI indices were important, particularly those calculated with bands 6, 7, 8, and 8A, which were placed at the RE position. The model performance showed reasonable success to Kappa index 0.72 and 0.56 for the first and fifth taxonomic level, respectively. The model presented confusion between Broadleaved dwarf-forest, Parkland Savanna, and Bushy grassland. Savanna formations occurred variably in the area while Bushy grasslands strictly occur in certain landscape positions. Broadleaved forests presented the best performance (first taxonomic level), and among its variation (fifth level) the model could precisely capture the pattern for those on deep soils from gneiss parent material. The approach was thus useful to capture intrinsic soil-plant relationships and its relation with remote sensing data, showing potential to map phytophysiognomies in two distinct taxonomic levels in poorly accessible areas.
Main Authors: | , , , , , , , , |
---|---|
Other Authors: | |
Format: | Artigo de periódico biblioteca |
Language: | English eng |
Published: |
2019-11-05
|
Subjects: | Sensoriamento Remoto, Conservação, Recurso Natural, Remote sensing, Conservation areas, |
Online Access: | http://www.alice.cnptia.embrapa.br/alice/handle/doc/1113915 https://doi.org/10.3390/rs11202448 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-alice-doc-1113915 |
---|---|
record_format |
koha |
spelling |
dig-alice-doc-11139152019-11-06T00:38:30Z Assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships. PINHEIRO, H. S. K. BARBOSA, T. P. R. ANTUNES, M. A. H. CARVALHO, D. C. de NUMMER, A. R. CARVALHO JUNIOR, W. de CHAGAS, C. da S. FERNANDES-FILHO, E. I. PEREIRA, M. G. HELENA S. K. PINHEIRO, UFRRJ; THERESA P. R. BARBOSA, UFRRJ; MAURO A. H. ANTUNES, UFRRJ; DANIEL COSTA DE CARVALHO, UnB; ALEXIS R. NUMMER, UFRRJ; WALDIR DE CARVALHO JUNIOR, CNPS; CESAR DA SILVA CHAGAS, CNPS; ELPÍDIO I. FERNANDES-FILHO, UFV; MARCOS GERVASIO PEREIRA, UFRRJ. Sensoriamento Remoto Conservação Recurso Natural Remote sensing Conservation areas There is a relation of vegetation physiognomies with soil and geological conditions that can be represented spatially with the support of remote sensing data. The goal of this research was to map vegetation physiognomies in a mountainous area by using Sentinel-2 Multispectral Instrument (MSI) data and morphometrical covariates through data mining techniques. The research was based on red-edge (RE) bands, and indices, to classify phytophysiognomies at two taxonomic levels. The input data was pixel sampled based on field sample sites. Data mining procedures comprised covariate selection and supervised classification through the Random Forest model. Results showed the potential of bands 3, 5, and 6 to map phytophysiognomies for both seasons, as well as Green Chlorophyll (CLg) and SAVI indices. NDVI indices were important, particularly those calculated with bands 6, 7, 8, and 8A, which were placed at the RE position. The model performance showed reasonable success to Kappa index 0.72 and 0.56 for the first and fifth taxonomic level, respectively. The model presented confusion between Broadleaved dwarf-forest, Parkland Savanna, and Bushy grassland. Savanna formations occurred variably in the area while Bushy grasslands strictly occur in certain landscape positions. Broadleaved forests presented the best performance (first taxonomic level), and among its variation (fifth level) the model could precisely capture the pattern for those on deep soils from gneiss parent material. The approach was thus useful to capture intrinsic soil-plant relationships and its relation with remote sensing data, showing potential to map phytophysiognomies in two distinct taxonomic levels in poorly accessible areas. 2019-11-06T00:38:22Z 2019-11-06T00:38:22Z 2019-11-05 2019 2019-11-08T11:11:11Z Artigo de periódico Remote Sensing, v. 11, n. 20, 2448, 2019. http://www.alice.cnptia.embrapa.br/alice/handle/doc/1113915 https://doi.org/10.3390/rs11202448 en eng openAccess |
institution |
EMBRAPA |
collection |
DSpace |
country |
Brasil |
countrycode |
BR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-alice |
tag |
biblioteca |
region |
America del Sur |
libraryname |
Sistema de bibliotecas de EMBRAPA |
language |
English eng |
topic |
Sensoriamento Remoto Conservação Recurso Natural Remote sensing Conservation areas Sensoriamento Remoto Conservação Recurso Natural Remote sensing Conservation areas |
spellingShingle |
Sensoriamento Remoto Conservação Recurso Natural Remote sensing Conservation areas Sensoriamento Remoto Conservação Recurso Natural Remote sensing Conservation areas PINHEIRO, H. S. K. BARBOSA, T. P. R. ANTUNES, M. A. H. CARVALHO, D. C. de NUMMER, A. R. CARVALHO JUNIOR, W. de CHAGAS, C. da S. FERNANDES-FILHO, E. I. PEREIRA, M. G. Assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships. |
description |
There is a relation of vegetation physiognomies with soil and geological conditions that can be represented spatially with the support of remote sensing data. The goal of this research was to map vegetation physiognomies in a mountainous area by using Sentinel-2 Multispectral Instrument (MSI) data and morphometrical covariates through data mining techniques. The research was based on red-edge (RE) bands, and indices, to classify phytophysiognomies at two taxonomic levels. The input data was pixel sampled based on field sample sites. Data mining procedures comprised covariate selection and supervised classification through the Random Forest model. Results showed the potential of bands 3, 5, and 6 to map phytophysiognomies for both seasons, as well as Green Chlorophyll (CLg) and SAVI indices. NDVI indices were important, particularly those calculated with bands 6, 7, 8, and 8A, which were placed at the RE position. The model performance showed reasonable success to Kappa index 0.72 and 0.56 for the first and fifth taxonomic level, respectively. The model presented confusion between Broadleaved dwarf-forest, Parkland Savanna, and Bushy grassland. Savanna formations occurred variably in the area while Bushy grasslands strictly occur in certain landscape positions. Broadleaved forests presented the best performance (first taxonomic level), and among its variation (fifth level) the model could precisely capture the pattern for those on deep soils from gneiss parent material. The approach was thus useful to capture intrinsic soil-plant relationships and its relation with remote sensing data, showing potential to map phytophysiognomies in two distinct taxonomic levels in poorly accessible areas. |
author2 |
HELENA S. K. PINHEIRO, UFRRJ; THERESA P. R. BARBOSA, UFRRJ; MAURO A. H. ANTUNES, UFRRJ; DANIEL COSTA DE CARVALHO, UnB; ALEXIS R. NUMMER, UFRRJ; WALDIR DE CARVALHO JUNIOR, CNPS; CESAR DA SILVA CHAGAS, CNPS; ELPÍDIO I. FERNANDES-FILHO, UFV; MARCOS GERVASIO PEREIRA, UFRRJ. |
author_facet |
HELENA S. K. PINHEIRO, UFRRJ; THERESA P. R. BARBOSA, UFRRJ; MAURO A. H. ANTUNES, UFRRJ; DANIEL COSTA DE CARVALHO, UnB; ALEXIS R. NUMMER, UFRRJ; WALDIR DE CARVALHO JUNIOR, CNPS; CESAR DA SILVA CHAGAS, CNPS; ELPÍDIO I. FERNANDES-FILHO, UFV; MARCOS GERVASIO PEREIRA, UFRRJ. PINHEIRO, H. S. K. BARBOSA, T. P. R. ANTUNES, M. A. H. CARVALHO, D. C. de NUMMER, A. R. CARVALHO JUNIOR, W. de CHAGAS, C. da S. FERNANDES-FILHO, E. I. PEREIRA, M. G. |
format |
Artigo de periódico |
topic_facet |
Sensoriamento Remoto Conservação Recurso Natural Remote sensing Conservation areas |
author |
PINHEIRO, H. S. K. BARBOSA, T. P. R. ANTUNES, M. A. H. CARVALHO, D. C. de NUMMER, A. R. CARVALHO JUNIOR, W. de CHAGAS, C. da S. FERNANDES-FILHO, E. I. PEREIRA, M. G. |
author_sort |
PINHEIRO, H. S. K. |
title |
Assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships. |
title_short |
Assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships. |
title_full |
Assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships. |
title_fullStr |
Assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships. |
title_full_unstemmed |
Assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships. |
title_sort |
assessment of phytoecological variability by red-edge spectral indices and soil-landscape relationships. |
publishDate |
2019-11-05 |
url |
http://www.alice.cnptia.embrapa.br/alice/handle/doc/1113915 https://doi.org/10.3390/rs11202448 |
work_keys_str_mv |
AT pinheirohsk assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships AT barbosatpr assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships AT antunesmah assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships AT carvalhodcde assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships AT nummerar assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships AT carvalhojuniorwde assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships AT chagascdas assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships AT fernandesfilhoei assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships AT pereiramg assessmentofphytoecologicalvariabilitybyrededgespectralindicesandsoillandscaperelationships |
_version_ |
1756026373172887552 |