Synthetic aperture radar (SAR) imagery is invaluable for assessing disaster-induced changes due to its capacity to capture detailed surface information despite varying environmental conditions. However, the scarcity of high-resolution (HR) SAR imagery before disasters presents significant challenges for accurately recognizing changes in damaged buildings, particularly in scenarios requiring pre- and post-disaster image pairs for machine-learning methods that rely on large samples. To address this challenge, our study proposes an innovative solution utilizing simulated SAR imagery generated through ray tracing-based SAR simulation, we generated high-quality predisaster SAR images that closely replicate the scattering properties of authentic SAR imagery using the same sensor orientation as postdisaster image. In this study, to evaluate the feasibility of using simulated SAR images for deep learning-based building damage classification, we investigate three different scenarios: 1) authentic pre- and post-disaster image pairs; 2) simulated predisaster images and authentic postdisaster images; and 3) postdisaster images alone. The methodology was applied in Mashiki, Japan, which was heavily impacted by the 2016 Kumamoto earthquake. Our classification results showed that the simulated predisaster SAR data produced outcomes comparable with those of using authentic image pairs and were clearly superior to the approach that utilized only postevent images. These findings illustrate that simulated SAR imagery is a reliable alternative when authentic predisaster data are unavailable, enabling fast, and accurate damage assessments to support emergency decision-making.

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.

The lack of pre-disaster data often poses challenges for reliable building damage predictions in disaster response using remote sensing. To address this limitation, we propose a framework that leverages Synthetic Aperture Radar (SAR) simulators to generate high-resolution simulated SAR images. Assessing the realism of these simulated images is crucial for their reliability in representing authentic SAR data. However, obtaining pre-disaster SAR images for city-scale areas can be challenging.In this study, we utilized Google 3D Tiles and Blender-GIS model to recreate scenes for simulating pre-disaster SAR images. We conducted a comprehensive analysis, evaluating the similarity between simulated and authentic SAR images through similarity assessments. Preliminary results suggest that the SAR simulator successfully produces distinct signatures for different 3D models in simulated SAR imagery. This approach holds promise for use in disaster response scenarios.

Remote sensing and deep learning have been integrated to solve multiple problems, including building damage assessment. With rapid development in both fields, deep learning and remote sensing can play a greater role in damage mapping, specifically in rapid damage assessment, to support emergency response efforts. Deep learning model evaluation is generally based on a statistical split separating training and testing sets of the same data distribution. Although this enables the evaluation of the model performance, this scheme does not disclose the ability of the model to perform in data obtained from different distributions, which is often the case in real-context disaster emergency response. This study evaluates the model generalization in emergency response scenarios. The results show that the current deep learning model has a high performance in in-domain testing yet experiences a drop of up to 53(%) in F1in realistic applications. Future studies should focus on enhancing the model transferability, including using domain adaptation techniques and harnessing multi-modal features.

In recent years, unmanned aerial vehicles (UAVs) have played an increasingly crucial role in supporting disaster emergency response efforts by analyzing aerial images. While current deep-learning models focus on improving accuracy, they often overlook the limited computing resources of UAVs. This study recognizes the imperative for real-time data processing in disaster response scenarios and introduces a lightweight and efficient approach for aerial video understanding. Our methodology identifies redundant portions within the video through policy networks and eliminates this excess information using frame compression techniques. Additionally, we introduced the concept of a station point, which leverages future information in the sequential policy network, thereby enhancing accuracy. To validate our method, we employed the wildfire FLAME dataset. Compared to the baseline, our approach reduces computation costs by more than 10 times while improving accuracy by 3%. Moreover, our method can intelligently select salient frames from the video, refining the dataset. This feature enables sophisticated models to be effectively trained on a smaller dataset, significantly reducing the time spent during the training process.

Deep learning models are generally less able to maintain their performance in out-of-domain testing. Model transferability is crucial, especially when a model needs to be applied to a new dataset, such as in disaster emergency response, where the training samples are scarce. To solve the aforementioned issues, we propose a semi-supervised framework to improve model generalization by utilizing unlabelled samples from the target domain. The framework consists of two main steps: model initialization, which incorporates past events, and iterative fine-tuning. The latter step relies heavily on the pseudo-labels inferred with high confidence from the former step. We tested our framework on the 2024 Noto Peninsula Earthquake. Our framework shows an improvement in the model generalization indicated by higher scores in the tuned model compared to the initial model. The effect is even greater when the local context from the past event is included in the initial learning step. In this case, the score has increased by about 21% from 0.62 to 0.75. The proposed framework offers a promising solution for rapid disaster damage mapping.

Remote sensing has been used extensively to identify the extent of floods. However, few studies have addressed the estimation of inundation depth, which would provide a deeper understanding of the affected areas. This paper reports a step-by-step application of a novel method to estimate inundation depths during a flood in Mabi town, Okayama Prefecture, Japan 2018. The method is based on the solution of a nonlinear programming problem, in which the flood extent, computed from SAR imagery, is represented as a sparse linear combination of water bodies calculated from a digital elevation model. The results show a good agreement with observations on the field survey and can be implemented in a fully automatic framework.

We show the application of an automatic collection of training samples for the identification of flooded buildings. The method is based on a near real time estimation of the flooded area using in-place sensors and a numerical simulation. Then, microwave remote sensing images are used to improve the accuracy of the extent of the flooded area. The floods produced during the 2018 heavy rainfalls in the town of Mabi is reported as case study. The results are consistent with the flood map provided by a third party.

Previous applications of machine learning in remote sensing for the identification of damaged buildings in the aftermath of a large-scale disaster have been successful. However, standard methods do not consider the complexity and costs of compiling a training data set after a large-scale disaster. In this article, we study disaster events in which the intensity can be modeled via numerical simulation and/or instrumentation. For such cases, two fully automatic procedures for the detection of severely damaged buildings are introduced. The fundamental assumption is that samples that are located in areas with low disaster intensity mainly represent nondamaged buildings. Furthermore, areas with moderate to strong disaster intensities likely contain damaged and nondamaged buildings. Under this assumption, a procedure that is based on the automatic selection of training samples for learning and calibrating the standard support vector machine classifier is utilized. The second procedure is based on the use of two regularization parameters to define the support vectors. These frameworks avoid the collection of labeled building samples via field surveys and/or visual inspection of optical images, which requires a significant amount of time. The performance of the proposed method is evaluated via application to three real cases: the 2011 Tohoku-Oki earthquake–tsunami, the 2016 Kumamoto earthquake, and the 2018 Okayama floods. The resulted accuracy ranges between 0.85 and 0.89, and thus, it shows that the result can be used for the rapid allocation of affected buildings.

Near real-time building damage mapping is an indispensable prerequisite for governments to make decisions for disaster relief. With high-resolution synthetic aperture radar (SAR) systems, such as TerraSAR-X, the provision of such products in a fast and effective way becomes possible. In this letter, a deep learning-based framework for rapid regional tsunami damage recognition using post-event SAR imagery is proposed. To perform such a rapid damage mapping, a series of tile-based image split analysis is employed to generate the data set. Next, a selection algorithm with the SqueezeNet network is developed to swiftly distinguish between built-up (BU) and nonbuilt-up regions. Finally, a recognition algorithm with a modified wide residual network is developed to classify the BU regions into wash away, collapsed, and slightly damaged regions. Experiments performed on the TerraSAR-X data from the 2011 Tohoku earthquake and tsunami in Japan show a BU region extraction accuracy of 80.4% and a damage-level recognition accuracy of 74.8%, respectively. Our framework takes around 2 h to train on a new region, and only several minutes for prediction.

In this study, a practical methodology was presented to map damaged buildings using high resolution synthetic aperture radar (SAR) images and post-event building damage data from the 2013 Super Typhoon Haiyan, in Tacloban city, the Philippines. To detect destroyed structures, we focused on the changes in the radar signal within footprints of buildings between pre- and post-event SAR images. The method was tested using a 1.0 m resolution COSMO-SkyMed SAR images taken over Tacloban city, the Philippines. The method proves, with 73% accuracy in this case, to be suitable for estimating destroyed buildings.

In this study, the extent of the flooded areas by the Super Typhoon Haiyan in the Philippines were extracted using ASTER VNIR images taken over Tacloban city in the Visayas. In order to constraint the affected area, we employed the normalize difference vegetation and water indices (NDVI and NDWI) from the pre- and post-event images. The extension of the flooded area was determined by comparing the index characteristics before and after the event. A phase-based change detection method indices was applied to classify the affected area into three classes according to the changes between the pre- and post-images. Through NDWI the flooded areas were detected despite the moderate resolution of ASTER images. In addition, the phase-based analysis successfully detected level of change within the affected area that may be correlated to the damage observed on field surveys. The results from the phase-based analysis were verified with damage levels obtained through visual damage inspection using high resolution satellite images.

A strong typhoon “Haiyan” affected Southeast Asia on November 8, 2013, caused gigantic destruction in the Philippines. In this study, two pre- and one post-event COSMO-SkyMed SCSB data were used to detect the damaged area around Tacloban City, Leyte Island. First, the severe damaged areas were detected according to the difference between the pre- and post-event speckle divergence values. Then the pre- and co-event coherence (NDCI) and correlation coefficient (NDCOI) were calculated from the three temporal data. The relationships between the four building damage levels and NDCI or NDCOI value were obtained by introducing the visual interoperation result. Using this relationship, the possibility of each damage class was estimated in the whole urban area.