Abstract
Automated classification of building damage in remote sensing images enables the rapid and spatially extensive assessment of the impact of natural hazards, thus speeding up emergency response efforts. Convolutional neural networks (CNNs) can reach good performance on such a task in experimental settings. How CNNs perform when applied under operational emergency conditions, with unseen data and time constraints, is not well studied. This study focuses on the applicability of a CNN-based model in such scenarios. We performed experiments on 13 disasters that differ in natural hazard type, geographical location, and image parameters. The types of natural hazards were hurricanes, tornadoes, floods, tsunamis, and volcanic eruptions, which struck across North America, Central America, and Asia. We used 175,289 buildings from the xBD dataset, which contains human-annotated multiclass damage labels on high-resolution satellite imagery with red, green, and blue (RGB) bands. First, our experiments showed that the performance in terms of area under the curve does not correlate with the type of natural hazard, geographical region, and satellite parameters such as the off-nadir angle. Second, while performance differed highly between occurrences of disasters, our model still reached a high level of performance without using any labeled data of the test disaster during training. This provides the first evidence that such a model can be effectively applied under operational conditions, where labeled damage data of the disaster cannot be available timely and thus model (re-)training is not an option.
Highlights
Disasters caused by natural hazards affected 95 million people in 2019 alone and led to 140 billion USD in damage [1]
These differences could not be explained in terms of disaster- or image-specific characteristics, such as the damage type, geographical location, and satellite parameters
The results showed that it is possible to reach a high performance on a new, unseen disaster when training on different disasters with the same damage type
Summary
Disasters caused by natural hazards affected 95 million people in 2019 alone and led to 140 billion USD in damage [1]. High-quality information on the impact of disasters is essential [3] It can be used in the immediate response phase to identify areas and people affected as well as in the mitigation phase to improve urban planning, for example. Field surveys are costly, are time-consuming, and are typically only possible once the affected regions are accessible, causing a delay in their availability. They cannot be updated and are of varying quality. Damage assessments using remotely sensed data are already often included in DNAs, if suitable imagery is available. These assessments are currently done manually, either by relief workers themselves or by specialized agencies such as UNOSAT. The quality of these assessments is not consistent and can be insufficient [10], while their speed and scalability is limited (less than 100 buildings per hour per person)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
