Estimation of catchment-scale soil moisture patterns from topography and reconstruction of a preserved ash-flow paleotopography
This dissertation consists of three parts, two of which examine methods for estimating spatial soil moisture patterns while the third investigates the reconstruction of a fluvially-eroded paleotopography. Part I of the dissertation evaluates unsupervised machine-learning techniques' effectiveness for estimating soil moisture patterns and compares them with linear regression. Physical processes that impact soil moisture are typically expressed as nonlinear functions, but most previous research on the estimation of soil moisture has relied on linear techniques. In the present work, two machine ...
(For more, see "View full record.")