Improving Landslide Detection on SAR Data through Deep Learning

TL;DR

This study demonstrates that deep learning CNNs can effectively detect landslides using optical and SAR satellite data, with optical data achieving higher accuracy but SAR data enabling rapid mapping under cloud cover.

Contribution

The paper introduces a CNN-based approach for landslide detection that combines optical and SAR data, showing SAR's potential for rapid, cloud-penetrating landslide mapping.

Findings

Optical CNNs achieved 99.20% accuracy in landslide detection.

SAR-based CNNs reached over 94% accuracy, comparable to optical methods.

Integrated SAR and optical data enable effective landslide mapping during adverse weather.

Abstract

In this letter, we use deep-learning convolution neural networks (CNNs) to assess the landslide mapping and classification performances on optical images (from Sentinel-2) and SAR images (from Sentinel-1). The training and test zones used to independently evaluate the performance of the CNNs on different datasets are located in the eastern Iburi subprefecture in Hokkaido, where, at 03.08 local time (JST) on September 6, 2018, an Mw 6.6 earthquake triggered about 8000 coseismic landslides. We analyzed the conditions before and after the earthquake exploiting multi-polarization SAR as well as optical data by means of a CNN implemented in TensorFlow that points out the locations where the Landslide class is predicted as more likely. As expected, the CNN run on optical images proved itself excellent for the landslide detection task, achieving an overall accuracy of 99.20% while CNNs based on the combination of ground range detected (GRD) SAR data reached overall accuracies beyond 94%. Our findings show that the integrated use of SAR data may also allow for rapid mapping even during storms and under dense cloud cover and seems to provide comparable accuracy to classical optical change detection in landslide recognition and mapping.