Depth Mapping in Turbid and Deep Waters Using AVIRIS-NG Imagery: A Study
in Wax Lake Delta, Louisiana, USA
Abstract
Remote sensing has been widely applied to investigate fluvial processes,
but depth retrievals face significant constraints in deep and turbid
conditions. This study evaluates the potential for depth retrievals
under such challenging conditions using NASA’s Airborne Visible/Infrared
Imaging Spectrometer-Next Generation (AVIRIS-NG) imagery. We employ
interpretable machine learning to construct a hyperspectral regressor
for water depth and explore the spectral characteristics of deep and
turbid waters in Wax Lake Delta (WLD), LA. The reflectance spectra of
WLD show minor effects from depth differences due to turbidity.
Nevertheless, a Random Forest with Recursive Feature Elimination
(RF-RFE) effectively generalizes high and low turbid cases in a single
model, achieving a R² of 0.94 ± 0.005. Moreover, this model shows a
maximum detectable depth of approximately 30 m, outperforming other
methods. A spectral analysis using Shapley additive explanations (SHAP)
points out the importance of learning various spectral bands and
non-linear relationships between depth and reflectance. Specifically,
the short blue and Near-InfraRed (NIR) bands, with high attenuation
coefficients, play a crucial role. This finding highlights the
attenuation as the key process for deep-depth retrievals. The depth maps
of WLD captured by this model distinctly represent the spatial
distribution of deep river and shallow delta regions. However, the high
dependency on short blue and NIR bands leads to discontinuous areas due
to the noise sensitivity of these bands. This result highlights a
drawback of remote sensing using empirical models. Future research will
focus on correcting such discontinuities by integrating data from
multiple remote sensing sources.