Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection

This study introduces Landslide4Sense, a reference benchmark for landslide detection from remote sensing. The repository features 3799 image patches fusing optical layers from Sentinel-2 sensors with the digital elevation model and slope layer derived from Advanced Land Observing Satellite (ALOS) phased array-type
$L$
-band SAR (PALSAR). The added topographical information facilitates an accurate detection of landslide borders, in which recent research has shown to be challenging using optical data alone. The extensive dataset supports deep learning (DL) studies in landslide detection and the development and validation of methods for the systematic update of landslide inventories. The benchmark dataset has been collected at four different times and geographical locations: Iburi (September 2018), Kodagu (August 2018), Gorkha (April 2015), and Taiwan (August 2009). Each image pixel is labeled as belonging to a landslide or not, incorporating various sources and thorough manual annotation. We then evaluate the landslide detection performance of 11 state-of-the-art DL segmentation models: U-Net, ResU-Net, pyramid scene parsing network (PSPNet), ContextNet, DeepLab-v2, DeepLab-v3+, FCN-8s, LinkNet, FRRN-A, FRRN-B, and SQNet. All models were trained from scratch on patches from one-quarter of each study area and tested on independent patches from the other three quarters. Our experiments demonstrate that ResU-Net outperformed the other models for the landslide detection task. We make the multisource landslide benchmark data (Landslide4Sense) and the tested DL models publicly available at
https://www.iarai.ac.at/landslide4sense
, establishing an important resource for remote sensing, computer vision, and machine learning communities in studies of image classification in general and applications to landslide detection in particular.