Urban areas in Lima, Peru, grow fast and with almost no control. Furthermore, resources to monitor urban areas are limited in Peru. Thus, the evolution of exposure of urban areas to natural hazards is highly uncertain. In this paper, we report a practical use of deep learning-based land use and land cover mapping to quantify, with unprecedented accuracy, the increment in exposure against floods in the District of Ate, Lima, Peru. We use Google Satellite imagery recorded in 2002 and 2023, generate land use maps, and quantify the increment of urban areas in the floodplain of the Rimac River. Results show an increment of exposure to floods of about 10.3% after 21 years.

After a major disaster, a rapid assessment of building damage is highly required for emergency response and prompt recovery. Remote sensing technologies have been widely applied for building damage mapping. Combining machine-learning algorithms (e.g., deep learning) and satellite images has recently demonstrated success in boosting damage recognition methods. Although previous techniques have shown great success, they primarily adopt supervised settings, often requiring a minimum number of training samples to achieve acceptable accuracy. Moreover, previous methods also are developed for specific target areas, which makes it challenging to apply them to other regions in case of future disasters. This paper presents a novel unsupervised approach for building damage mapping, focusing on collapsed structures, using modern convolutional neural network (CNN) models and high-resolution remote sensing imagery. We apply our mapping framework to revise the building damage following the 2007 Peru-Pisco Earthquake and the recent 2023 Turkey and Syria Earthquakes.

Detection, monitoring, and evaluations of the scope and severity of the wildfire are critical for post-disaster management efforts. In this study, we use the rdNDVI technique to identify a wildfire that occurred on 24 May 2022 in Nuristan, Afghanistan, using pre- and post-event Sentinel-2 images based on Google Earth Engine (GEE) to assess the potential of Sentinel-2 and GEE to capture forest fire-induced land-use and land-cover changes. Wildfire detection, monitoring, and accuracy evaluation are presented. Wildfires ravaged using current methodology was estimated 58 acres. With a single free post-event image, the recommended technique can accurately identify forest fires with a 90% accuracy and 0.79 Kappa coefficient. For fire risk assessment and fire damage estimation this effective framework's outcome is beneficial.

This study presents a methodology for building damage identification in natural disasters using interferometric SAR coherence and machine learning technique. We used ALOS/PALSAR-2 images observed at before and after natural disasters in Japan such as earthquakes, landslides, debris flows and flooding. We confirmed that the interferometric coherences were significantly decreased in collapsed buildings compared to non-damaged buildings due to debris of the damaged buildings. Supervised learning based on convolutional neural network (CNN) was performed to the coherence images to identify the collapsed buildings. The results show that the severely damaged areas in the disasters were accurately identified in the building damage mapping although some of intact buildings were falsely classified especially in mountainous areas because the coherences were significantly lower due to radar shadowing effect in SAR and misalignment of two images in steep slopes.

UAV (Unmanned aerial vehicle) observations were performed at damaged areas by heavy rain-induced debris flows in Hiroshima, Japan on August 2021. Digital surface models (DSM) and ortho-rectified images were developed from the UAV-derived aerial images. Scars of surface grounds in the mountains produced by the debris flows were clearly identified in the ortho images. Difference of elevations were calculated from the post-event UAV-based DSMs and pre-event DEMs. Soil volumes produced by the debris flows were estimated by aggregating the elevation changes in the eroded areas identified as scars in the ortho images. We revealed that the relationships between eroded areas of the debris flows and volumes obtained in this study agree with those of previous studies.

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 athttps://github.com/nyokoya/dlsim.

Evaluations of the extent and the volume of the displaced materials are vital for post-disaster management activities. In this study, we present a nonlinear geometric correction technique for identifying landslide affected areas and estimating the volume by using pre-and post-event digital elevation models (DEMs) generated from high-resolution stereo pair satellite imagery of the Abe Barek landslide, which was a devastating landslide that occurred On May 2, 2014, in the northern part of Afghanistan. The proposed method consists of shifting vector generation in subareas of the DEMs, consensus operations, and interpolation of the shifting vectors. The quality assessment confirmed that the proposed method outperformed simple DEMs of difference technique by eliminating a large scale of geometric errors in unaffected areas. We estimated the landslide volume as 1.06 x 106m3from the pre-and post-event DEMs corrected by the proposed method. Finally, the building damage assessment on the landslide-affected area has been carried out in terms of the deposition depths obtained in this analysis.

This study examined a methodology for urban flood mapping based on discrimination analysis of pre- and co-event interferometric coherences obtained from multitemporal Sentinel-1 SAR images. The method was applied to the areas in Kumamoto prefecture, Kyushu Island, Japan affected by the heavy rain in July 2020. Two pre-event images, one post-event image, and existing land cover map were analyzed with the help of inundation inventory data estimated from aerial photos. We revealed that the co-event coherences in the inundation urban areas were significantly decreased from the pre-event coherences. The result of the discriminant analysis of the pre- and co-event coherences shows the inundation areas were well extracted, and the inundation areas not identified in the inventory were also extracted in the coastal areas.

Disasters such as earthquakes, hurricanes, and flooding are responsible for large-scale infrastructure damages and loss of human lives. Immediately after disaster strikes, one of the most critical and difficult tasks is accurately assessing the extent and severity of the disaster. This task is especially challenging in areas isolated by the disaster; in such cases, remote sensing information provides the best alternative to tackle this problem. This paper presents a damage mapping framework using remote sensing imagery acquired from previous disasters. The proposed deep learning-based framework is trained to learn features related to building damage using imagery from previous disasters that were collected from different regions around the world. Then, it is tested to recognize damage from a different urban environment.