Coastal Bathymetry from Hyperspectral Observations of Water Radiance

• Published in: Remote sensing of environment 1998-09, Vol.65 (3), p.341-352
• Main Authors: Sandidge, Juanita C., Holyer, Ronald J.
• Format: Article
• Language: English
• Subjects: Bathymetry; Coastal zones; Error analysis; Fluorescence; Infrared imaging; Infrared spectrometers; Light absorption; Light scattering; Marine; Neural networks; Spectrum analysis
• ISSN: 0034-4257; 1879-0704
• DOI: 10.1016/S0034-4257(98)00043-1

Water depth, bottom reflectance, inherent optical properties of the water column (scattering, absorption, and fluorescence), and illumination conditions combine to determine the upwelling spectral radiance of coastal waters. If these complex optical relationships could be quantified, it would be possible to extract coastal information from spectral radiance data. We use data from the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) in a neural network system to establish quantitative, empirical relationships between one of these parameters, depth, and remotely sensed spectral radiance. Data are analyzed for two areas: the western coast of Florida in the Tampa Bay area and the Florida Keys between Upper Matecumbe and Plantation Keys. The neural network approach results in retrieval of reasonable depths from spectral radiance in both cases over a depth range of 0 to 6 m. Retrieved depths for Tampa Bay are accurate to a RMS error of 0.84 m relative to depths in the National Ocean Survey (NOS) Hydrographic Database, and the Keys retrievals have an RMS error of 0.39 m relative to a bathymetric survey conducted to support this study. A neural network trained on a combination of the two data sets results in a combined RMS error of 0.48 m, nearly the same performance as neural networks trained individually. The ability of the neural network to generalize, producing algorithms with some degree of universality among diverse coastal environments is, thereby, demonstrated. The result of the generalization analysis is of practical importance because it indicates that the neural network may not require an extensive training set of water depth data in order to be “tuned” for each location where depth retrievals are desired. While empirical, the neural network is in some sense a model of the inversion of the radiative transfer problem within the marine environment. The neural network approach, therefore, operates on a higher level than more traditional statistical curve fitting solutions for retrieval of remotely sensed information.