Research Expericence for Undergraduates for Ocean, Marine, and Polar Science
Elizabeth City State University Summer 2012

Spectroscopic Image Signature Classification of Land Cover Types using Multi-Spectral Data within a Neural Network

Abstract:
Through improvements in technology, high resolution multi-spectral imaging allowed new capabilities to become available in the remote sensing field.  Hyper-spectral technologies existed in the chemical spectroscopy field to identify minerals by way of active systems (Green et al., 1998). The theory of this paper surrounded the premise that passive systems can provide spectral signatures of objects within images from satellite platforms. Specifically this paper targeted land cover types from the Kittyhawk, North Carolina area. Multi-spectral signals presented up to seven individual readings per pixel. As the decision support system, a neural network was trained to decide the type of land cover based on the band readings. In an effort to determine specific landcover types based on need, ground truthed spectral readings would also be classified using a linear model to convert the readings into approximate satellite readings. The converted readings would then be classified by the trained neural network. A minimal r-squared valued of 86% would be required to be considered a viable method of image classification.

Remote Sensing Team Webpage

Research Experience for Undergraduates
University of Maryland Eastern Shore Summer 2011


Analysis of Contaminants of Emerging Concerns in Wastewater and the Maryland Coastal Bays

Research Poster

Student Research
Spelman College Spring 2011

Machine Guns vs. Spears Was Never A Fair Fight

Advisor: Soraya Mekerta, Ph.D.

Research Link