Estimation of mixed-layer depth from surface parameters
MetadataShow full item record
Mixed layer depth (MLD) is an important oceanographic parameter. However, the lack of direct observations of MLD hampers both specification and investigation of its spatial and temporal variability. An important alternative to direct observation would be the ability to estimate MLD from surface parameters easily available from satellites. In this study, we demonstrate estimation of MLD using Artificial Neural Network methods and surface meteorology from a surface mooring in the Arabian Sea. The estimated MLD had a root mean square error of 7.36 m and a coefficient of determination (R2) of 0.94. About 67% (91%) of the estimates lie within ± 5 m (± 10 m) of the MLD determined from temperature sensors on the mooring.
Author Posting. © Sears Foundation for Marine Research, 2006. This article is posted here by permission of Sears Foundation for Marine Research for personal use, not for redistribution. The definitive version was published in Journal of Marine Research 64 (2006): 745-758, doi:10.1357/002224006779367285.