Engineering Commons^™

Manifold Learning Based Spectral Unmixing Of Hyperspectral Remote Sensing Data, Jun-Hwa Chi

Open Access Dissertations

Nonlinear mixing effects inherent in hyperspectral data are not properly represented in linear spectral unmixing models. Although direct nonlinear unmixing models provide capability to capture nonlinear phenomena, they are difficult to formulate and the results are not always generalizable. Manifold learning based spectral unmixing accommodates nonlinearity in the data in the feature extraction stage followed by linear mixing, thereby incorporating some characteristics of nonlinearity while retaining advantages of linear unmixing approaches. Since endmember selection is critical to successful spectral unmixing, it is important to select proper endmembers from the manifold space. However, excessive computational burden hinders development of manifolds for …

An Evaluation Of Spatial Variability Of Water Stress Index Across The United States: Implications Of Supply And Demand In The East Vs The West, Jennifer Ann Roath

Open Access Theses

In order to support both human and environmental needs, high quality fresh water must be available when and where it is required. As a metric for indicating unsustainable water usage, WSI is only useful when the values reflect accurate interactions between supply and demand; however, the complexity of temporal and spatial variability of available fresh water complicates the analysis of water stress.

The overall goal of this project was to investigate the spatial variability of water stress across the United States and the appropriate spatial scale for management decisions. To accomplish this, a national dataset describing spatial distribution and breakdown …