Satellite Ocean Color Research for Water Quality Applications

(NOAA Collaborators:Paul DiGiacomo)

This research covers three main components: phytoplankton composition in the Great Lakes, phytoplankton phenology in the Chesapeake Bay, and satellite detection of surface cover types using deep learning techniques. I plan to develop an approach to detect phytoplankton community composition in the Great Lakes, which is important to monitor potential changes in phytoplankton associated with invasive quagga mussels. I will finish the study of phytoplankton seasonal and interannual variability in the Chesapeake Bay using the new chlorophyll algorithm developed recently, which provides more reliable estimates of chlorophyll concentration than standard reflectance band ratio algorithms. I will also further explore the use of deep learning techniques in water quality remote sensing, starting with a project to detect surface cover types from VIIRS data.