ISSLIDE: A New InSAR Dataset for Slow SLIding Area DEtection With Machine Learning

Due to the high data demand of machine-learning algorithms, multiple datasets are emerging in remote sensing. However, these datasets are costly and time-consuming to annotate especially for change detection or natural phenomena monitoring. In particular, early warning systems for slow-moving disasters lack training datasets as they require both geomorphological and SAR interferometry expertise. In this letter: 1) we propose a novel interferometric SAR (InSAR) dataset for Slow SLIding area DEtection (ISSLIDE) with machine-learning algorithms. The latter consists of manually annotated patches of generated interferograms over slow-moving areas; and 2) we implement the segmentation of ISSLIDE interferograms with classical deep-learning approaches. FCN, DeepLabV3, and U-Net-like architectures are explored to serve as a baseline for future works. To the best of our knowledge, this is the first dataset adapted to machine learning and targeting slow sliding area detection.