This article was submitted to IEEE Geoscience and Remote Sensing Magazine.Access to labeled reference data is one of the grand challenges in supervised machine learning endeavors. This is especially true for an automated analysis of remote sensing images on a global scale, which enables us to address global challenges such as urbanization and climate change using state-of-theart machine learning techniques. To meet these pressing needs, especially in urban research, we provide open access to a valuable benchmark dataset named "So2Sat LCZ42," which consists of local climate zone (LCZ) labels of about half a million Sentinel-1 and Sentinel-2 image patches in 42 urban agglomerations (plus 10 additional smaller areas) across the globe. This dataset was labeled by 15 domain experts following a carefully designed labeling work flow and evaluation process over a period of six months. As rarely done in other labeled remote sensing dataset, we conducted rigorous quality assessment by domain experts. The dataset achieved an overall confidence of 85%. We believe this LCZ dataset is a first step towards an unbiased globallydistributed dataset for urban growth monitoring using machine learning methods, because LCZ provide a rather objective measure other than many other semantic land use and land cover classifications. It provides measures of the morphology, compactness, and height of urban areas, which are less dependent on human and culture. This dataset can be accessed from

This is the pre-acceptance version, to read the final version please go to IEEE Geoscience and Remote Sensing Magazine on IEEE XPlore.Deep learning in remote sensing has become an international hype, but it is mostly limited to the evaluation of optical data. Although deep learning has been introduced in Synthetic Aperture Radar (SAR) data processing, despite successful first attempts, its huge potential remains locked. In this paper, we provide an introduction to the most relevant deep learning models and concepts, point out possible pitfalls by analyzing special characteristics of SAR data, review the state-of-the-art of deep learning applied to SAR in depth, summarize available benchmarks, and recommend some important future research directions. With this effort, we hope to stimulate more research in this interesting yet under-exploited research field and to pave the way for use of deep learning in big SAR data processing workflows.

Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity of building shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural networks (DCNNs) has made accurate pixel-level classification tasks possible. Yet one central issue remains: the precise delineation of boundaries. Deep architectures generally fail to produce finegrained segmentation with accurate boundaries due to their progressive down-sampling. Hence, we introduce a generic framework to overcome the issue, integrating the graph convolutional network (GCN) and deep structured feature embedding (DSFE) into an end-to-end workflow. Furthermore, instead of using a classic graph convolutional neural network, we propose a gated graph convolutional network, which enables the refinement of weak and coarse semantic predictions to generate sharp borders and fine-grained pixel-level classification. Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks. Our proposed framework with the new GCN architecture outperforms state-of-the-art approaches. Although our main task in this work is building footprint extraction, the proposed method can be generally applied to other binary or multi-label segmentation tasks.

The well-known polar R3MTQ7 is a large family of noncentrosymmetric chalcogenides, and despite of adopting the same crystal structure type, its members show distinctively different nonlinear optical (NLO) properties, which is quite unusual. Yet, the intrinsic reason remains unknown. Herein, we report the discovery of six new members, La3Ga0.5(Ge0.5/Ga0.5)­S7 (1), La3In0.5(Ge0.5/In0.5)­S7 (2), Sm3Ga0.5(Ge0.5/Ga0.5)­S7 (3), La3In0.33GeS7 (4), Sm3In0.33GeS7 (5), and Gd3In0.33GeS7 (6). Remarkably, polycrystalline 1 and 2 show the strongest second harmonic generation (SHG) of this family, 4.8 and 1.8 times that of the benchmark AgGaS2 at 2.05 μm in the same particle size of 74–106 μm. For the first time we reveal that for the R3MTQ7 family the atomic distribution mainly determines the NLO property, and members showing strong SHG must have a formula of R3M0.5TQ7. Furthermore, we illustrate whether the building unit MS6 octahedron is half occupied (1–3) or one-third occupied (4–6) is total energy driven and charge balance controlled.