A methodology for the automated identification of building damage from post-disaster aerial images was developed based on convolutional neural network (CNN) and building damage inventories. The aerial images and the building damage data obtained in the 2016 Kumamoto, and the 1995 Kobe, Japan earthquakes were analyzed. Since the roofs of many moderately damaged houses are covered with blue tarps immediately after disasters, not only collapsed and non-collapsed buildings but also the buildings covered with blue tarps were identified by the proposed method. The CNN architecture developed in this study correctly classifies the building damage with the accuracy of approximately 95 % in both earthquake data. We applied the developed CNN model to aerial images in Chiba, Japan, damaged by the typhoon in September 2019. The result shows that more than 90 % of the building damage are correctly classified by the CNN model.

We propose a framework that estimates the inundation depth (maximum water level) and debris-flow-induced topographic deformation from remote sensing imagery by integrating deep learning and numerical simulation. A water and debris-flow simulator generates training data for various artificial disaster scenarios. We show that regression models based on Attention U-Net and LinkNet architectures trained on such synthetic data can predict the maximum water level and topographic deformation from a remote sensing-derived change detection map and a digital elevation model. The proposed framework has an inpainting capability, thus mitigating the false negatives that are inevitable in remote sensing image analysis. Our framework breaks limits of remote sensing and enables rapid estimation of inundation depth and topographic deformation, essential information for emergency response, including rescue and relief activities. We conduct experiments with both synthetic and real data for two disaster events that caused simultaneous flooding and debris flows and demonstrate the effectiveness of our approach quantitatively and qualitatively. Our code and data sets are available at https://github.com/nyokoya/dlsim .

Damage to individual buildings in an urban area of Port‐au‐Prince, Haiti, from the 2010 Haiti earthquake was assessed by means of high‐resolution synthetic aperture radar (SAR) intensity images and ancillary building footprints. A comparison of pre‐ and post‐event images and a building damage inventory showed that backscattering intensity between images was more significantly changed in collapsed buildings than in less damaged buildings. The linear discriminant function, based on the difference and correlation coefficient of the images was developed to detect collapsed buildings. The result showed that almost 75% of the buildings were correctly detected by discriminant analysis. An accuracy assessment revealed the difficulty of detecting small and congested buildings because the number of image pixels was too small and the buildings were obscured by neighboring buildings and other features in the images.

On 26 August 2020, a devastating flash flood struck Charikar city, Parwan province, Afghanistan, causing building damage and killing hundreds of people. Rapid identification and frequent mapping of the flood-affected area are essential for post-disaster support and rapid response. In this study, we used Google Earth Engine to evaluate the performance of automatic detection of flood-inundated areas by using the spectral index technique based on the relative difference in the Normalized Difference Vegetation Index (rdNDVI) between pre- and post-event Sentinel-2 images. We found that rdNDVI was effective in detecting the land cover change from a flash flood event in a semi-arid region in Afghanistan and in providing a reasonable inundation map. The result of the rdNDVI-based flood detection was compared and assessed by visual interpretation of changes in the satellite images. The overall accuracy obtained from the confusion matrix was 88%, and the kappa coefficient was 0.75, indicating that the methodology is recommendable for rapid assessment and mapping of future flash flood events. We also evaluated the NDVIs’ changes over the course of two years after the event to monitor the recovery process of the affected area. Finally, we performed a digital elevation model-based flow simulation to discuss the applicability of the simulation in identifying hazardous areas for future flood events.

The rapid and accurate mapping of large-scale landslides and other mass movement disasters is crucial for prompt disaster response efforts and immediate recovery planning. As such, remote sensing information, especially from synthetic aperture radar (SAR) sensors, has significant advantages over cloud-covered optical imagery and conventional field survey campaigns. In this work, we introduced an integrated pixel-object image analysis framework for landslide recognition using SAR data. The robustness of our proposed methodology was demonstrated by mapping two different source-induced landslide events, namely, the debris flows following the torrential rainfall that fell over Hiroshima, Japan, in early July 2018 and the coseismic landslide that followed the 2018 Mw6.7 Hokkaido earthquake. For both events, only a pair of SAR images acquired before and after each disaster by the Advanced Land Observing Satellite-2 (ALOS-2) was used. Additional information, such as digital elevation model (DEM) and land cover information, was employed only to constrain the damage detected in the affected areas. We verified the accuracy of our method by comparing it with the available reference data. The detection results showed an acceptable correlation with the reference data in terms of the locations of damage. Numerical evaluations indicated that our methodology could detect landslides with an accuracy exceeding 80%. In addition, the kappa coefficients for the Hiroshima and Hokkaido events were 0.30 and 0.47, respectively.