Coastal Change Analysis Program (C-CAP)

Beginning in 2015, C-CAP embarked on operational high resolution land cover development effort that utilized geographic object-based image analysis and ML algorithms such as Random Forest to classify coastal land cover from 1m multispectral imagery. More recently, C-CAP has been relying on a CNN approach for the deriving the impervious surface component of their land cover products. The majority of the work is accomplished through external contracts. Prior to the high-res effort, C-CAP focused on developing Landsat based moderate resolution multi-date land cover for the coastal U.S. In 2002, C-CAP adopted a methodology that employed Classification and Regression Trees for land cover data development.