Sentinel-1 satellites provide temporally dense and high spatial resolution synthetic aperture radar (SAR) imagery. The open data policy and global coverage of Sentinel-1 make it a valuable data source for a wide range of SAR-based applications. In this regard, the Google Earth Engine is a key platform for large area analysis with preprocessed Sentinel-1 backscatter images available within a few days after acquisition. To preserve the information content and user freedom, some preprocessing steps (e.g., speckle filtering) are not applied on the ingested Sentinel-1 imagery as they can vary by application. In this technical note, we present a framework for preparing Sentinel-1 SAR backscatter Analysis-Ready-Data in the Google Earth Engine that combines existing and new Google Earth Engine implementations for additional border noise correction, speckle filtering and radiometric terrain normalization. The proposed framework can be used to generate Sentinel-1 Analysis-Ready-Data suitable for a wide range of land and inland water applications. The Analysis Ready Data preparation framework is implemented in the Google Earth Engine JavaScript and Python APIs.

A humid tropical forest disturbance alert using Sentinel-1 radar data is presented for the Congo Basin. Radar satellite signals can penetrate through clouds, allowing Sentinel-1 to provide gap-free observations for the tropics consistently every 6–12 days at 10 m spatial scale. In the densely cloud covered Congo Basin, this represents a major advantage for the rapid detection of small-scale forest disturbances such as subsistence agriculture and selective logging. Alerts were detected with latest available Sentinel-1 images and results are presented from January 2019 to July 2020. We mapped 4 million disturbance events during this period, totalling 1.4 million ha with nearly 80% of events smaller than 0.5 ha. Monthly distribution of alert totals varied widely across the Congo Basin countries and can be linked to regional differences in wet and dry season cycles, with more forest disturbances in the dry season. Results indicated high user’s and producer’s accuracies and the rapid confirmation of alerts within a few weeks. Our disturbance alerts provide confident detection of events larger than or equal to 0.2 ha but do not include smaller events, which suggests that disturbance rates in the Congo Basin are even higher than presented in this study. The new alert product can help to better study the forest dynamics in the Congo Basin with improved spatial and temporal detail and near real-time detections, and highlights the value of dense Sentinel-1 time series data for large-area tropical forest monitoring. The research contributes to the Global Forest Watch initiative in providing timely and accurate information to support a wide range of stakeholders in sustainable forest management and law enforcement. The alerts are available via the https://www.globalforestwatch.org and http://radd-alert.wur.nl.

This article provides an angular-based radiometric slope correction routine for Sentinel-1 SAR imagery on the Google Earth Engine platform. Two established physical reference models are implemented. The first model is optimised for vegetation applications by assuming volume scattering on the ground. The second model is optimised for surface scattering, and therefore targeted at urban environments or analysis of soil characteristics. The framework of both models is extended to simultaneously generate masks of invalid data in active layover and shadow affected areas. A case study, using openly available and reproducible code, exemplarily demonstrates the improvement of the backscatter signal in a mountainous area of the Austrian Alps. Furthermore, suggestions for specific use cases are discussed and drawbacks of the method with respect to pixel-area based methods are highlighted. The radiometrically corrected radar backscatter products are overcoming current limitations and are compliant with recent CEOS specifications for SAR backscatter over land. This improves a wide range of potential usage scenarios of the Google Earth Engine platform in mapping various land surface parameters with Sentinel-1 on a large scale and in a rapid manner. The provision of an openly accessible Earth Engine module allows users a smooth integration of the routine into their own workflows.

Deep learning (DL) has proven to be a suitable approach for despeckling synthetic aperture radar (SAR) images. So far, most DL models are trained to reduce speckle that follows a particular distribution, either using simulated noise or a specific set of real SAR images, limiting the applicability of these methods for real SAR images with unknown noise statistics. In this article, we present a DL method, deSpeckNet,1 that estimates the speckle noise distribution and the despeckled image simultaneously. Since it does not depend on a specific noise model, deSpeckNet generalizes well across SAR acquisitions in a variety of landcover conditions. We evaluated the performance of deSpeckNet on single polarized Sentinel-1 images acquired in Indonesia, The Democratic Republic of Congo, and The Netherlands, a single polarized ALOS-2/PALSAR-2 image acquired in Japan and an Iceye X2 image acquired in Germany. In all cases, deSpeckNet was able to effectively reduce speckle and restore the images in high quality with respect to the state of the art.

Deep learning has successfully improved the classification accuracy of optical remote sensing images. Recent works attempted to transfer the success of these techniques to the microwave domain to classify Polarimetric SAR data. So far, most deep learning networks separate amplitude and phase as separate input images. In this article, we present a deep fully convolutional network that uses real-valued weight kernels to perform pixel-wise classification of complex-valued images. We evaluated the performance of this network by comparing it with support vector machine, Random Forest, complex-valued convolutional neural network (CV-CNN), and a network that uses amplitude and phase information separately as real channels. The evaluation was done on a quad-polarized AIRSAR image and a dual-polarimetric multitemporal Sentinel-1 data acquired over Flevoland, the Netherlands. The proposed method achieved higher accuracy compared to all other networks with the same architecture.

A polarimetric synthetic aperture radar (PolSAR) sensor is able to collect images in different polarization states, making it a rich source of information for target characterization. PolSAR images are inherently affected by speckle. Therefore, before deriving ad hoc products from the data, the polarimetric covariance matrix needs to be estimated by reducing speckle. In recent years, deep learning-based despeckling methods have started to evolve from single-channel SAR images to PolSAR images. To this aim, deep learning-based approaches separate the real and imaginary components of the complex-valued covariance matrix and use them as independent channels in standard convolutional neural networks (CNNs). However, this approach neglects the mathematical relationship that exists between the real and imaginary components, resulting in suboptimal output. Here, we propose a multistream complex-valued fully convolutional network (FCN) (CV-deSpeckNet https://github.com/adugnag/CV-deSpeckNet ) to reduce speckle and effectively estimate the PolSAR covariance matrix. To evaluate the performance of CV-deSpeckNet, we used Sentinel-1 dual polarimetric SAR images to compare against its real-valued counterpart that separates the real and imaginary parts of the complex covariance matrix. CV-deSpeckNet was also compared against the state of the art PolSAR despeckling methods. The results show that CV-deSpeckNet was able to be trained with a fewer number of samples, has a higher generalization capability, and resulted in higher accuracy than its real-valued counterpart and state-of-the-art PolSAR despeckling methods. These results showcase the potential of complex-valued deep learning for PolSAR despeckling.