eduzhai > Applied Sciences > Engineering >

Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping

  • Save

... pages left unread,continue reading

Document pages: 14 pages

Abstract: We propose a framework that estimates inundation depth (maximum water level)and debris-flow-induced topographic deformation from remote sensing imagery byintegrating deep learning and numerical simulation. A water and debris flowsimulator generates training data for various artificial disaster scenarios. Weshow that regression models based on Attention U-Net and LinkNet architecturestrained on such synthetic data can predict the maximum water level andtopographic deformation from a remote sensing-derived change detection map anda digital elevation model. The proposed framework has an inpainting capability,thus mitigating the false negatives that are inevitable in remote sensing imageanalysis. Our framework breaks the limits of remote sensing and enables rapidestimation of inundation depth and topographic deformation, essentialinformation for emergency response, including rescue and relief activities. Weconduct experiments with both synthetic and real data for two disaster eventsthat caused simultaneous flooding and debris flows and demonstrate theeffectiveness of our approach quantitatively and qualitatively.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×