The global forest/non-forest map from TanDEM-X interferometric SAR data

Martone, Michele; Rizzoli, Paola; Wecklich, Christopher; González, Carolina; Bueso-Bello, José-Luis; Valdo, Paolo; Schulze, Daniel; Zink, Manfred; Krieger, Gerhard; Moreira, Alberto

doi:10.1016/j.rse.2017.12.002

Cited by 132 publications

(129 citation statements)

References 33 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…Further evaluations of this dataset should involve comparisons with other sources of elevation data including local LiDAR surface/terrain models and global DEMs such as the MERIT DEM and the upcoming NASADEM, as well as geomorphometric analyses, landslide characterization and hydrological modeling. A global forest/non-forest map derived from TanDEM-X data has been recently presented by Martone et al (2018); the dataset is expected to be released freely to the scientific community and can be of great value in assessing the influence of land cover type, such as open vegetation (savanna), in the representation of the topographic surface by InSAR DEMs.…”

Section: Resultsmentioning

confidence: 99%

Evaluation of TanDEM-X DEMs on selected Brazilian sites: Comparison with SRTM, ASTER GDEM and ALOS AW3D30

Grohmann¹

2018

Remote Sensing of Environment

155

101

View full text Add to dashboard Cite

A first assessment of the TanDEM-X DEMs over Brazilian territory is presented through a comparison with SRTM, ASTER GDEM and ALOS AW3D30 DEMs in seven study areas with distinct geomorphological contexts, vegetation coverage, and land use. Visual analysis and elevation histograms point to a finer effective spatial (i.e., horizontal) resolution of TanDEM-X compared to SRTM and ASTER GDEM. In areas of open vegetation, TanDEM-X lower elevations indicate a deeper penetration of the radar signal. DEMs of differences (DoDs) allowed the identification of issues inherent to the production methods of the analyzed DEMs, such as mast oscillations in SRTM data and mismatch between adjacent scenes in ASTER GDEM and ALOS AW3D30. A systematic difference in elevations between TanDEM-X 12 m, TanDEM-X 30 m, and SRTM was observed in the steep slopes of the coastal ranges, related to the moving-window process used to resample the 12 m data to a 30 m pixel size. It is strongly recommended to produce a DoD with SRTM before using ASTER GDEM or ALOS AW3D30 in any analysis, to evaluate if the area of interest is affected by these problems. The DoDs also highlighted changes in land use in the time span between the acquisition of SRTM (2000) and TanDEM-X (2013) data, whether by natural causes or by human interference in the environment. The results show a high level of detail and consistency for TanDEM-X data, indicate that the effective horizontal resolution of SRTM is coarser than the nominal 30 m, and highlight the errors in ASTER GDEM and ALOS AW3D30 due to mismatch between adjacent scenes in the photogrammetric process.

show abstract

Section: Resultsmentioning

confidence: 99%

Evaluation of TanDEM-X DEMs on selected Brazilian sites: Comparison with SRTM, ASTER GDEM and ALOS AW3D30

Grohmann¹

2018

Remote Sensing of Environment

155

101

View full text Add to dashboard Cite

show abstract

“…It is highlighted in Chini et al [22], that high backscattering values together with low co-event InSAR coherence allow the detection of flooded urban areas. Recent studies focus mainly on forest and vegetation mapping using bistatic InSAR coherence information of the TanDEM-X/TerraSAR-X pair [27][28][29]. However, to our knowledge there is no example in the recent literature that evaluates bistatic TDX/TSX InSAR coherence (Bist.…”

Section: Introductionmentioning

confidence: 99%

Flood Mapping in a Complex Environment Using Bistatic TanDEM-X/TerraSAR-X InSAR Coherence

et al. 2018

View full text Add to dashboard Cite

In this paper, we assess the flood mapping capabilities of the X-band Synthetic Aperture Radar (SAR) imagery acquired by the bistatic pair TanDEM-X/TerraSAR-X (TDX/TSX). The main objective is to investigate the added value of the bistatic TDX/TSX Interferometric Synthetic Aperture Radar (InSAR) coherence in addition to the SAR backscatter in the context of inundation mapping. As a classifier, we consider a Random Forest (RF) classification scheme using TDX/TSX SAR intensities and their bistatic InSAR coherence to extract the flood extent map. To evaluate the classification results and as no "ground truth" was available at the SAR data acquisition time, we set up a LISFLOOD-FP hydraulic model for simulating the temporal evolution of the flood water. The flood map simulated by the model shows good performances with an Overall Accuracy (OA) of 97.92% and a Critical Success Index (CSI) of 94.01%. The SAR-derived flood map is then compared to the LISFLOOD-FP extent map simulated at the SAR data acquisition time. As a test case, we consider the flooding event of the Richelieu River that occurred in the Montérégie region of Quebec (Canada) from April to June 2011. Experimental results highlight the potential of the bistatic InSAR coherence for more accurate flood mapping in a complex landscape with urban and vegetation areas. The classification results of the SAR-derived flood map with respect to the LISFLOOD-FP flood map reach an OA of 78.65% and a Precision of 82.08% when integrating the bistatic InSAR coherence. These classification OA and Precision values are 69.63% and 64.52%, respectively, using only the TDX/TSX SAR intensity.

show abstract

“…The use of the L 1 norm provides a negligible contribution, likely because the other two loss terms, based on cross-entropy and Jaccard distance, are directly related to ACC and IoU, respectively. It has to be remarked that for a fair comparison with the proposed methods, the baseline solution of [8] was used without masking any class, contrarily to what is done in the original formulation. Specifically, in [8] city and water classes are excluded by means of available masks, because forests, cities and water classes all exhibit a low volume correlation, the core feature proposed to classify forests.…”

Section: Resultsmentioning

confidence: 99%

“…In this work we exploit the same dataset used in [8], described in Section 3, including the ground-truth reference which is given in terms of density of forest in a squared area of 6×6 meters. In order to train the network we explored two different objective loss functions.…”

Section: Trainingmentioning

confidence: 99%

Deep Learning Solutions for Tandem-X-Based Forest Classification

Mazza

Sica²

2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

In the last few years, deep learning (DL) has been successfully and massively employed in computer vision for discriminative tasks, such as image classification or object detection. This kind of problems are core to many remote sensing (RS) applications as well, though with domain-specific peculiarities. Therefore, there is a growing interest on the use of DL methods for RS tasks. Here, we consider the forest/nonforest classification problem with TanDEM-X data, and test two state-of-the-art DL models, suitably adapting them to the specific task. Our experiments confirm the great potential of DL methods for RS applications.

show abstract

The global forest/non-forest map from TanDEM-X interferometric SAR data

Cited by 132 publications

References 33 publications

Evaluation of TanDEM-X DEMs on selected Brazilian sites: Comparison with SRTM, ASTER GDEM and ALOS AW3D30

Evaluation of TanDEM-X DEMs on selected Brazilian sites: Comparison with SRTM, ASTER GDEM and ALOS AW3D30

Flood Mapping in a Complex Environment Using Bistatic TanDEM-X/TerraSAR-X InSAR Coherence

Deep Learning Solutions for Tandem-X-Based Forest Classification

Contact Info

Product

Resources

About