Potential of Multi-Temporal ALOS-2 PALSAR-2 ScanSAR Data for Vegetation Height Estimation in Tropical Forests of Mexico
Information on the spatial distribution of forest structure parameters (e.g., aboveground biomass, vegetation height) are crucial for assessing terrestrial carbon stocks and emissions. In this study, we sought to assess the potential and merit of multi-temporal dual-polarised L-band observations for...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-08-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | http://www.mdpi.com/2072-4292/10/8/1277 |
id |
doaj-cf348f254fff4282bf6d368cd36916d7 |
---|---|
record_format |
Article |
spelling |
doaj-cf348f254fff4282bf6d368cd36916d72020-11-25T00:44:16ZengMDPI AGRemote Sensing2072-42922018-08-01108127710.3390/rs10081277rs10081277Potential of Multi-Temporal ALOS-2 PALSAR-2 ScanSAR Data for Vegetation Height Estimation in Tropical Forests of MexicoMikhail Urbazaev0Felix Cremer1Mirco Migliavacca2Markus Reichstein3Christiane Schmullius4Christian Thiel5International Max Planck Research School for Global Biogeochemical Cycles, Max Planck Institute for Biogeochemistry, Hans-Knoell-Str. 10, 07745 Jena, GermanyDepartment of Earth Observation, Friedrich-Schiller University Jena, Loebdergraben 32, 07743 Jena, GermanyDepartment of Biogeochemical Integration, Max Planck Institute for Biogeochemistry, Hans-Knoell-Strasse 10, 07745 Jena, GermanyDepartment of Biogeochemical Integration, Max Planck Institute for Biogeochemistry, Hans-Knoell-Strasse 10, 07745 Jena, GermanyDepartment of Earth Observation, Friedrich-Schiller University Jena, Loebdergraben 32, 07743 Jena, GermanyDepartment of Earth Observation, Friedrich-Schiller University Jena, Loebdergraben 32, 07743 Jena, GermanyInformation on the spatial distribution of forest structure parameters (e.g., aboveground biomass, vegetation height) are crucial for assessing terrestrial carbon stocks and emissions. In this study, we sought to assess the potential and merit of multi-temporal dual-polarised L-band observations for vegetation height estimation in tropical deciduous and evergreen forests of Mexico. We estimated vegetation height using dual-polarised L-band observations and a machine learning approach. We used airborne LiDAR-based vegetation height for model training and for result validation. We split LiDAR-based vegetation height into training and test data using two different approaches, i.e., considering and ignoring spatial autocorrelation between training and test data. Our results indicate that ignoring spatial autocorrelation leads to an overoptimistic model’s predictive performance. Accordingly, a spatial splitting of the reference data should be preferred in order to provide realistic retrieval accuracies. Moreover, the model’s predictive performance increases with an increasing number of spatial predictors and training samples, but saturates at a specific level (i.e., at 12 dual-polarised L-band backscatter measurements and at around 20% of all training samples). In consideration of spatial autocorrelation between training and test data, we determined an optimal number of L-band observations and training samples as a trade-off between retrieval accuracy and data collection effort. In summary, our study demonstrates the merit of multi-temporal ScanSAR L-band observations for estimation of vegetation height at a larger scale and provides a workflow for robust predictions of this parameter.http://www.mdpi.com/2072-4292/10/8/1277L-bandSAR backscattervegetation heightforest structure parametersspatial autocorrelationYucatanMexico |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mikhail Urbazaev Felix Cremer Mirco Migliavacca Markus Reichstein Christiane Schmullius Christian Thiel |
spellingShingle |
Mikhail Urbazaev Felix Cremer Mirco Migliavacca Markus Reichstein Christiane Schmullius Christian Thiel Potential of Multi-Temporal ALOS-2 PALSAR-2 ScanSAR Data for Vegetation Height Estimation in Tropical Forests of Mexico Remote Sensing L-band SAR backscatter vegetation height forest structure parameters spatial autocorrelation Yucatan Mexico |
author_facet |
Mikhail Urbazaev Felix Cremer Mirco Migliavacca Markus Reichstein Christiane Schmullius Christian Thiel |
author_sort |
Mikhail Urbazaev |
title |
Potential of Multi-Temporal ALOS-2 PALSAR-2 ScanSAR Data for Vegetation Height Estimation in Tropical Forests of Mexico |
title_short |
Potential of Multi-Temporal ALOS-2 PALSAR-2 ScanSAR Data for Vegetation Height Estimation in Tropical Forests of Mexico |
title_full |
Potential of Multi-Temporal ALOS-2 PALSAR-2 ScanSAR Data for Vegetation Height Estimation in Tropical Forests of Mexico |
title_fullStr |
Potential of Multi-Temporal ALOS-2 PALSAR-2 ScanSAR Data for Vegetation Height Estimation in Tropical Forests of Mexico |
title_full_unstemmed |
Potential of Multi-Temporal ALOS-2 PALSAR-2 ScanSAR Data for Vegetation Height Estimation in Tropical Forests of Mexico |
title_sort |
potential of multi-temporal alos-2 palsar-2 scansar data for vegetation height estimation in tropical forests of mexico |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2018-08-01 |
description |
Information on the spatial distribution of forest structure parameters (e.g., aboveground biomass, vegetation height) are crucial for assessing terrestrial carbon stocks and emissions. In this study, we sought to assess the potential and merit of multi-temporal dual-polarised L-band observations for vegetation height estimation in tropical deciduous and evergreen forests of Mexico. We estimated vegetation height using dual-polarised L-band observations and a machine learning approach. We used airborne LiDAR-based vegetation height for model training and for result validation. We split LiDAR-based vegetation height into training and test data using two different approaches, i.e., considering and ignoring spatial autocorrelation between training and test data. Our results indicate that ignoring spatial autocorrelation leads to an overoptimistic model’s predictive performance. Accordingly, a spatial splitting of the reference data should be preferred in order to provide realistic retrieval accuracies. Moreover, the model’s predictive performance increases with an increasing number of spatial predictors and training samples, but saturates at a specific level (i.e., at 12 dual-polarised L-band backscatter measurements and at around 20% of all training samples). In consideration of spatial autocorrelation between training and test data, we determined an optimal number of L-band observations and training samples as a trade-off between retrieval accuracy and data collection effort. In summary, our study demonstrates the merit of multi-temporal ScanSAR L-band observations for estimation of vegetation height at a larger scale and provides a workflow for robust predictions of this parameter. |
topic |
L-band SAR backscatter vegetation height forest structure parameters spatial autocorrelation Yucatan Mexico |
url |
http://www.mdpi.com/2072-4292/10/8/1277 |
work_keys_str_mv |
AT mikhailurbazaev potentialofmultitemporalalos2palsar2scansardataforvegetationheightestimationintropicalforestsofmexico AT felixcremer potentialofmultitemporalalos2palsar2scansardataforvegetationheightestimationintropicalforestsofmexico AT mircomigliavacca potentialofmultitemporalalos2palsar2scansardataforvegetationheightestimationintropicalforestsofmexico AT markusreichstein potentialofmultitemporalalos2palsar2scansardataforvegetationheightestimationintropicalforestsofmexico AT christianeschmullius potentialofmultitemporalalos2palsar2scansardataforvegetationheightestimationintropicalforestsofmexico AT christianthiel potentialofmultitemporalalos2palsar2scansardataforvegetationheightestimationintropicalforestsofmexico |
_version_ |
1725275378294980608 |