The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLVIII-4/W1-2022
https://doi.org/10.5194/isprs-archives-XLVIII-4-W1-2022-449-2022
https://doi.org/10.5194/isprs-archives-XLVIII-4-W1-2022-449-2022
06 Aug 2022
 | 06 Aug 2022

SCALING-UP DEEP LEARNING PREDICTIONS OF HYDROGRAPHY FROM IFSAR DATA IN ALASKA

L. V. Stanislawski, E. J. Shavers, A. J. Duffy, P. Thiem, N. Jaroenchai, S. Wang, Z. Jiang, B. J. Kronenfeld, and B. P. Buttenfield

Keywords: elevation, hydrography, machine learning, U-net, transfer learning, National Hydrography Dataset

Abstract. The United States National Hydrography Dataset (NHD) is a database of vector features representing the surface water features for the country. The NHD was originally compiled from hydrographic content on U.S. Geological Survey topographic maps but is being updated with higher quality feature representations through flow-routing techniques that derive hydrography from high-resolution elevation data. However, deriving hydrography through flow-routing methods is a complex process that needs to be tailored to different geographic conditions, which can lead to varying solutions. To address this problem, this paper evaluates automated deep learning and its transferability to extract hydrography from interferometric synthetic aperture radar (IfSAR) elevation data spanning a range of geographic conditions in Alaska.