Multi-Temporal Satellite Image Composites in Google Earth Engine for Improved Landslide Visibility: A Case Study of a Glacial Landscape

Abstract

Regional early warning systems for landslides rely on historic data to forecast future events and to verify and improve alarms. However, databases of landslide events are often spatially biased towards roads or other infrastructure, with few reported in remote areas. In this study, we demonstrate how Google Earth Engine can be used to create multi-temporal change detection image composites with freely available Sentinel-1 and -2 satellite images, in order to improve landslide visibility and facilitate landslide detection. First, multispectral Sentinel-2 images were used to map landslides triggered by a summer rainstorm in Jølster (Norway), based on changes in the normalised difference vegetation index (NDVI) between pre- and post-event images. Pre- and post-event multi-temporal images were then created by reducing across all available images within one month before and after the landslide events, from which final change detection image composites were produced. We used the mean of backscatter intensity in co- (VV) and cross-polarisations (VH) for Sentinel-1 synthetic aperture radar (SAR) data and maximum NDVI for Sentinel-2. The NDVI-based mapping increased the number of registered events from 14 to 120, while spatial bias was decreased, from 100% of events located within 500 m of a road to 30% close to roads in the new inventory. Of the 120 landslides, 43% were also detectable in the multi-temporal SAR image composite in VV polarisation, while only the east-facing landslides were clearly visible in VH. Noise, from clouds and agriculture in Sentinel-2, and speckle in Sentinel-1, was reduced using the multi-temporal composite approaches, improving landslide visibility without compromising spatial resolution. Our results indicate that manual or automated landslide detection could be significantly improved with multi-temporal image composites using freely available earth observation images and Google Earth Engine, with valuable potential for improving spatial bias in landslide inventories. Using the multi-temporal satellite image composites, we observed significant improvements in landslide visibility in Jølster, compared with conventional bi-temporal change detection methods, and applied this for the first time using VV-polarised SAR data. The GEE scripts allow this procedure to be quickly repeated in new areas, which can be helpful for reducing spatial bias in landslide databases.

Landslides Triggered by Medicane Ianos in Greece, September 2020: Rapid Satellite Mapping and Field Survey

“…Histograms of the detection results of Table 2 are presented in Figure 17. The highest success ratio is achieved by the methods of [44] and [46] with almost comparable results, as expected due to the similarities in the calculated change detection data (Sentinel-2 10 m) and parameters (time-series of normalized difference vegetation index). The worst percentage was achieved by ALDI [47], probably due to the lower resolution data used (Landsat multispectral bands with 30 m resolution instead of 10 m for Sentinel-2).…”

“…We present a comparison of our manual rapid mapping using Sentinel-2 images, with a series of recent workflows and codes that use the multi-temporal analysis of satellite imagery in Google Earth Engine [44][45][46][47]. While this comparison is not straightforward due to the different workflow, data and time frame used by either rapid manual mapping or automated multi-temporal analysis, this is an interesting case study to compare them.…”

“…We selected four change detection techniques, that use multi-temporal analysis of open satellite data (Sentinel-1, Sentinel-2, Landsat); (a) method from [46] that calculates relative difference in the normalized difference vegetation index (rdNDVI) calculated from cloud-free composites of Sentinel-2, (b) HazMapper code by [44] that is based on the normalized difference vegetation index (dNDVI) calculated from cloud-free composites of Sentinel-2 [48], (c) ALDI, automated landslide detection index algorithm based on normalized difference vegetation index (NDVI) differencing of Landsat time series within Google Earth Engine taking into account seasonality [47] and (d) a SAR backscatter and amplitude change approach that uses multi-temporal stacks of Copernicus Sentinel-1 images [45].…”

Globally- vs Locally-trained Machine Learning Models for Land-slide Detection: A Case Study of a Glacial Landscape

“…In July 2019, an extremely heavy rainfall event triggered multiple landslides in the (formerly named) Jølster municipality in Western Norway [34]. The road authority reported 14 landslides on this date, while mapping from Sentinel-2 images detected 120 events, with only 30% being located within 500 m of a road, compared to 100% of those registered by the road authority [35]. NVE used aerial and satellite images to manually map polygons representing the landslide and performed a quality control of the existing landslide point data.…”

“…There is a strong need for improved landslide mapping techniques in Norway, which can provide objective and accurate spatial information, and also allowing the detection of events that occur away from populated areas and transport routes. Recent studies have demonstrated there is great potential to improve detection of landslides in remote areas using satellite images [34,35].…”