JPL Technical Report Server

Flood Mapping Using UAVSAR and Convolutional Neural Networks

Show simple item record

dc.contributor.author Denbina, Michael W
dc.contributor.author Towfic, Zaid J.
dc.contributor.author Thill, Matthew
dc.contributor.author Bue, Brian
dc.contributor.author Kasraee, Neda
dc.contributor.author Peacock, Annemarie
dc.contributor.author Lou, Yunling
dc.date.accessioned 2021-11-01T18:34:46Z
dc.date.available 2021-11-01T18:34:46Z
dc.date.issued 2020-07-19
dc.identifier.citation IGARSS 2020 - IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, Hawaii, July 19-24, 2020
dc.identifier.clearanceno CL#20-0462
dc.identifier.uri http://hdl.handle.net/2014/52316
dc.description.abstract We have mapped flooded areas in data collected by the NASA/JPL Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) using two convolutional neural network (CNN) image classifier architectures: U-Net and SegNet. Our study area was a region around Houston, TX, USA affected by widespread flooding in 2017 due to Hurricane Harvey. To train and test the classifiers, we manually labelled over 10000 image segments in two flight lines. Both U-Net and SegNet yielded higher accuracy than a previous non-machine learning classifier we used as a baseline. U-Net had slightly higher accuracy than SegNet. The classifiers performed better in areas with more homogeneous land cover. To independently validate the classifier accuracy we used NOAA aerial imagery, with overall accuracy around 80%. Future work includes assessing the classifier robustness in other study areas, assessing the classifier dependence on UAVSAR incidence angle, particularly for open water and bare ground, and collecting more training data, particularly in urban areas. This study demonstrates the potential of CNN image classifiers for mapping flooded areas in airborne polarimetric SAR imagery, and for land cover classification of polarimetric SAR imagery more generally.
dc.description.sponsorship NASA/JPL en_US
dc.language.iso en_US
dc.publisher Pasadena, CA: Jet Propulsion Laboratory, National Aeronautics and Space Administration, 2020
dc.title Flood Mapping Using UAVSAR and Convolutional Neural Networks
dc.type Preprint


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search


Browse

My Account