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

Abstract

This study introduces \textit{Landslide4Sense}, a reference benchmark for landslide detection from remote sensing. The repository features 3,799 image patches fusing optical layers from Sentinel-2 sensors with the digital elevation model and slope layer derived from ALOS PALSAR. The added topographical information facilitates the accurate detection of landslide borders, which recent researches have shown to be challenging using optical data alone. The extensive data set supports deep learning (DL) studies in landslide detection and the development and validation of methods for the systematic update of landslide inventories. The benchmark data set 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 labelled 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, 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 multi-source landslide benchmark data (Landslide4Sense) and the tested DL models publicly available at \url{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.

References in corpus (7)

• Deep learning in remote sensing: a review
• Fully Convolutional Networks for Semantic Segmentation
• Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art
• LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
• Improving Landslide Detection on SAR Data through Deep Learning
• Landslide Segmentation with U-Net: Evaluating Different Sampling Methods and Patch Sizes
• Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping

Cited by in corpus (4)

• Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks
• Tinto: Multisensor Benchmark for 3D Hyperspectral Point Cloud Segmentation in the Geosciences
• Auto-Prompting SAM for Weakly Supervised Landslide Extraction
• A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection