TanDEM-X Forest Mapping Using Convolutional Neural Networks

Abstract

In this work, we face the problem of forest mapping from TanDEM-X data by means of Convolutional Neural Networks (CNNs). Our study aims to highlight the relevance of domain-related features for the extraction of the information of interest thanks to their joint nonlinear processing through CNN. In particular, we focus on the main InSAR features as the backscatter, coherence, and volume decorrelation, as well as the acquisition geometry through the local incidence angle. By using different state-of-the-art CNN architectures, our experiments consistently demonstrate the great potential of deep learning in data fusion for information extraction in the context of synthetic aperture radar signal processing and specifically for the task of forest mapping from TanDEM-X images. We compare three state-of-the-art CNN architectures, such as ResNet, DenseNet, and U-Net, obtaining a large performance gain over the baseline approach for all of them, with the U-Net solution being the most effective one.2 of 18 between the master and slave images, enabling high-resolution interferometric measurements with an unprecedented quality. The constellation comprises two twin satellites flying in a bistatic close-orbit configuration, which allows for a flexible selection of the acquisition geometries and, in particular, of the interferometric baselines [8]. The main goal of the mission was the generation of a global consistent high-resolution digital elevation model (DEM) with unprecedented accuracy, which has been successfully completed in 2016 [9]. Besides the nominal DEM product, for each bistatic interferometric TanDEM-X acquisition, additional quantities can be computed as by-pass products. Indeed, the bistatic acquisition is not affected by temporal decorrelation, allowing for an accurate isolation of volume scattering phenomena from the interferometric coherence. This feature was exploited in References [10,11], where the authors presented a framework for the development of a global TanDEM-X forest/non-forest map [12] as described more in details in Section 2.1.Deep learning approaches and, in particular, Convolutional Neural Networks (CNNs) have been massively used in computer vision and image processing in the last few years, since the publication of the breakthrough work of Krizhevsky et al. on image classification in 2012 [13]. Thanks to the CNNs capability to learn very complex nonlinear relationships from huge labeled datasets with the help of commercial GPUs, unprecedented results have been obtained for many typical tasks such as super-resolution [14,15], segmentation [16], denoising [17], object detection [18,19], classification [20][21][22], and many others.Recently, deep learning has started to significantly impact remote sensing applications as well, as testified by the recent survey of Zhu et al. [23]. Established techniques in remote sensing concern, e.g., pansharpening [24,25], vehicle detection [26] with optical images, crop classification [27,28], anomaly detection with hyperspectral data [29], despeckling [30,31],...

GEDI Elevation Accuracy Assessment: A Case Study of Southwest Spain

“…Several SAR satellites can be used for forest monitoring [30], such as SENTINEL 1 [31], ALOS PALSAR [32], ICESat GLAS [11], ENVISAT ASAR and RADARSAT [33] and one of the most used, TanDEM-X [34]. Since September 2010, a second satellite TanDEM-X (TDX) was added to TerraSAR-X (TSX) for the acquisition of a global digital elevation model (DEM) from bistatic X-band interferometric SAR acquisitions.…”

Situational Awareness of Large Infrastructures Using Remote Sensing: The Rome–Fiumicino Airport during the COVID-19 Lockdown

“…As a future activity, we aim at further extending the proposed methodology by exploiting Sentinel-1 interferometric capability and use the coherence parameter as an additional input feature. The S-1 interferometric coherence can be indeed used for finer change detection and to perform land cover classification as in [52], together with the application of deep learning approaches [53].…”

Deep Learning-Based Automated Forest Health Diagnosis From Aerial Images

“…Recent studies [25][26] [27] [28]showed CNN and FCN were used in sementic segmentation on forest mapping. In [25] a VGG neural network (an architecture of CNN) was proposed to classify pixels with a sliding window technique.…”