Datacubes for Landslide Detection with SAR Imagery
Creators
- 1. University of California Berkeley
- 2. The Ohio State University
- 3. German Aerospace Center DLR
- 4. University of Valencia, National Observatory of Athens
- 5. Universidad de Antioquia
- 6. NVIDIA
- 7. University of Oxford
- 8. United Nations Satellite Centre
Description
Four analysis-ready datacubes with multiple layers of SAR time-series data and interferometric products (coherence, InSAR) and auxiliary topographic information (elevation, slope, aspect, curvature) for multiple landslide events along with the corresponding landslide labels.
Area | Cause | Date of event | Dimensions | Label Type | Label Source |
Hokkaido, Japan | Earthquake | 06-Sep-18 | {'y': 5382, 'x': 4398, 'timestep': 26, 'timepair': 16} | Segmentation | link |
Puerto Rico | Hurricane Maria | 16-09-2017 - 02-10-2017 | {'y': 7134, 'x': 19251, 'timestep': 6, 'timepair': 4} | Landslide heads | link |
Mt Talakmau, Indonesia | Earthquake | 25-Feb-22 | {'y': 4313, 'x': 3006, 'timestep': 20, 'timepair': 12} | Segmentation | link |
Kaikoura, New Zealand | Earthquake | 14-Nov-16 | {'y': 16973, 'x': 15930, 'timestep': 5, 'timepair': 9} | Landslide centroids | link |
Acknowledgements
This work has been enabled by the Frontier Development Lab Program (FDL). FDL is a collaboration between SETI Institute and Trillium Technologies Inc., in partnership with the Department of Energy (DOE) , National Aeronautics and Space Administration (NASA), and U.S. Geological Survey (USGS).The material is based upon work supported by NASA under award No(s) NNX14AT27A.