Ratio-of-Collapse Evaluation after 2016 Kumamoto Earthquakes Using ALOS2-PALSAR2 Fully Polarimetric Synthetic Aperture Radar Data
Abstract
In this work, we make a case study on ratio-of-collapse evaluation after 2016 Kumamoto earthquakes by using ALOS2-PALSAR data. The worst-hit area Mashikimachi is selected as the observe area. We propose two types of methods for evaluating ratio-of-collapse after earthquake, i.e., supervised and unsupervised algorithm. The supervised method is developed by using quaternion neural network and Poincare sphere parameters. The unsupervised algorithm is based on seven models scattering power decomposition. The results of both methods well coincide with the survey result of ratio-of-collapse.
Fields of Study & Subjects
Synthetic Aperture Radar (SAR) Applications and Techniques
Landslides and related hazards
Advanced SAR Imaging Techniques
Publication details
- Journal / source
- IEICE Transactions on Communications
- Volume
- E109-B
- Issue
- 7
- Pages
- 973–982
- Publication date
- 2 February 2026