Mapping Macrophyte Species in the Amazon Floodplain Wetlands Using Fully Polarimetric ALOS/PALSAR Data

Sartori, Lauriana Rúbio; Imai, Nilton Nobuhiro; Mura, José Cláudio; Novo, Evlyn Márcia Leão de Moraes; Silva, Thiago Sanna Freire

doi:10.1109/tgrs.2011.2157972

Cited by 33 publications

(23 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most of the previous studies have described high H areas as forests and high α areas as cities (e.g., [23,64,65]). However, high biomass vegetation assessed in this study featured very high H. According to the a priori labeling criteria, the location of the PFT A pixels in the H/α plane was similar to the location of pixels with floodable trees and shrubs in the Amazonas floodplain [32]. High α values in pixels dominated by the equisetoid herbs of PFT A (e.g., Schoenoplectus californicus in bulrush marshes) presented high α values such as predicted due to its high double-bounce scattering in presence of a water film [60].…”

Section: H/α Segmentationsmentioning

confidence: 57%

Mapping Plant Functional Types in Floodplain Wetlands: An Analysis of C-Band Polarimetric SAR Data from RADARSAT-2

et al. 2016

View full text Add to dashboard Cite

Abstract:The inclusion of functional approaches on wetland characterizations and on biodiversity assessments improves our understanding of ecosystem functioning. In the Lower Paraná River floodplain, we assessed the ability of C-band polarimetric SAR data of contrasting incidence angles to discriminate wetland areas dominated by different plant functional types (PFTs). Unsupervised H/α and H/A/α Wishart classifications were implemented on two RADARSAT-2 images differing in their incidence angles (FQ24 and FQ08). Obtained classes were assigned to the information classes (open water, bare soil and PFTs) by a priori labeling criteria that involved the expected interaction mechanisms between SAR signal and PFTs as well as the relative values of H and α. The product obtained with the shallow incidence angle scene had a higher accuracy than the one obtained with the steep incidence angle product (61.5% vs. 46.2%). We show how a systematic analysis of the H/A/α space can be used to improve the knowledge about the radar polarimetric response of herbaceous vegetation. The map obtained provides novel ecologically relevant information about plant strategies dominating the floodplain. Since the obtained classes can be interpreted in terms of their functional features, the approach is a valuable tool for predicting vegetation response to floods, anthropic impacts and climate change.

show abstract

Section: H/α Segmentationsmentioning

confidence: 57%

Mapping Plant Functional Types in Floodplain Wetlands: An Analysis of C-Band Polarimetric SAR Data from RADARSAT-2

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Entropy is the randomness of scattering mechanisms, alpha angle represents the dominant scattering mechanism, and anisotropy characterizes directional dependence and importance of the secondary scattering mechanism. Among these three polarimetric decompositions, many authors have found the Freeman-Durden decomposition in particular to be useful for wetland mapping [77][78][79]. These polarimetric decompositions represent the advanced analysis possible with radar polarimetry and thus were included in the random forest models which evaluated the effectiveness of RADARSAT-2 imagery for mapping wetlands.…”

Section: Optical Input Datamentioning

confidence: 99%

“…Such variables are particularly important when discriminating between forest structural condition (i.e., open or closed canopy), monitoring stand age and regrowth, and estimating species composition and richness [85][86][87]. Studies have also established that the multiple scattering and subsequent depolarization of the radar signal explains the importance of HV polarization for classifying land cover and estimating biomass, particularly in forested regions [72,78,87]. It is important to note that even though our best results included ancillary soils and topographic input data, without the inclusion of ancillary data, the selected remotely sensed layers in the RDL model retain their level of importance.…”

Section: Upland Water and Wetland Land Cover Classification (Level 1)mentioning

confidence: 99%

Influence of Multi-Source and Multi-Temporal Remotely Sensed and Ancillary Data on the Accuracy of Random Forest Classification of Wetlands in Northern Minnesota

2013

View full text Add to dashboard Cite

Abstract:Wetland mapping at the landscape scale using remotely sensed data requires both affordable data and an efficient accurate classification method. Random forest classification offers several advantages over traditional land cover classification techniques, including a bootstrapping technique to generate robust estimations of outliers in the training data, as well as the capability of measuring classification confidence. Though the random forest classifier can generate complex decision trees with a multitude of input data and still not run a high risk of over fitting, there is a great need to reduce computational and operational costs by including only key input data sets without sacrificing a significant level of accuracy. Our main questions for this study site in Northern Minnesota were: (1) how does classification accuracy and confidence of mapping wetlands compare using different remote sensing platforms and sets of input data; (2) what are the key input variables for accurate differentiation of upland, water, and wetlands, including wetland type; and (3) which datasets and seasonal imagery yield the best accuracy for wetland classification. Our results show the key input variables include terrain (elevation and curvature) and soils descriptors (hydric), along with an assortment of remotely sensed data collected in the spring (satellite visible, near infrared, and thermal bands; satellite normalized vegetation index and Tasseled Cap greenness and wetness; and horizontal-horizontal (HH) and horizontal-vertical (HV) polarization using L-band satellite radar). We undertook this exploratory analysis to inform decisions by natural resource OPEN ACCESS Remote Sens. 2013, 5 3213 managers charged with monitoring wetland ecosystems and to aid in designing a system for consistent operational mapping of wetlands across landscapes similar to those found in Northern Minnesota.

show abstract

“…No total, 34 atributos foram extraídos. Maiores detalhes sobre o processamento da imagem PALSAR e a geração de atributos podem ser vistos em Sartori et al (2011).…”

Section: Processamento Da Imagem Palsar E Dos Elementos Amostraisunclassified

Atributos polarimétricos de imagem radar na inferência de parâmetros morfológicos de macrófitas

et al. 2012

View full text Add to dashboard Cite

O propósito deste trabalho é ajustar um modelo de regressão múltipla em função de atributos de imagens de radar polarimétrico, para estimativa da variável morfológica "volume da haste" de macrófitas encontradas na planície de inundação da Amazônia, no Lago Grande de Monte Alegre (Pará - Brasil). Com esta estimativa, pretende-se avaliar o potencial dos dados polarimétricos do sensor ALOS/PALSAR, destacando a importância da informação de fase das imagens de radar. Para este estudo, foram coletados dados de campo em época próxima à aquisição do dado de radar. Variáveis morfológicas, como altura e diâmetro da haste emergente, de três espécies de macrófitas foram medidas em campo e usadas para derivar o "volume da haste", o qual foi modelado usando atributos da imagem de radar. Dois atributos da decomposição de Freeman-Durden, dois de Touzi e um de Pope apresentaram melhor desempenho na modelagem. Apesar do modelo não ter obtido um elevado coeficiente de determinação (44%), ele apresentou boa capacidade preditiva, já que todos os elementos de validação caíram dentro do intervalo de predição de 95% de confiança. Dentre as cinco variáveis independentes do modelo, quatro foram geradas a partir da informação de fase das imagens, o que reforça a importância dessa informação.

show abstract

Mapping Macrophyte Species in the Amazon Floodplain Wetlands Using Fully Polarimetric ALOS/PALSAR Data

Cited by 33 publications

References 21 publications

Mapping Plant Functional Types in Floodplain Wetlands: An Analysis of C-Band Polarimetric SAR Data from RADARSAT-2

Mapping Plant Functional Types in Floodplain Wetlands: An Analysis of C-Band Polarimetric SAR Data from RADARSAT-2

Influence of Multi-Source and Multi-Temporal Remotely Sensed and Ancillary Data on the Accuracy of Random Forest Classification of Wetlands in Northern Minnesota

Atributos polarimétricos de imagem radar na inferência de parâmetros morfológicos de macrófitas

Contact Info

Product

Resources

About