Leveraging the Science of Geographic Information Systems

International Journal of Applied Geospatial Research, 2(2), 33-38, April-June 2011

Rick Bunch, Anna Tapp, and Prasad Pathak

“The Center for Geographic Information Science (CGISc) at the University of North Carolina Greensboro (UNCG) was established in the Summer of 2006. CGISc is an educational research entity that relies on the use of GIS and the science of geographic information to conduct research on human and natural phenomena distributed on the Earth’s surface. CGISc welcomes interdisciplinary collaboration, and emphasizes the development of public-private sector partnerships. CGISc also places a high priority on research that involves students. This paper first provides an overview of the CGISc. This section is followed by a discussion on the fundamental approach to conducting geographic research using GIS. The paper concludes with several significant projects and a discussion on future directions.”

Change Detection Using Historical Aerial Photography in Bighorn Sheep Habitat of the Sierra Nevada

Proceedings of Spatial Knowledge and Information – Canada (SKI-Canada) 2011, March 3-6 in Fernie, BC, Canada

Erin Latham, Lacey Greene, Tom Stephenson, Greg McDermid, and Mark Hebblewhite

“The principal goal of this research project was to evaluate the changes in Sierra-Nevada bighorn sheep habitat over the past 75 years using historical aerial photography. We hypothesized that changes in bighorn sheep habitat could be characterized by spatial and terrain-related variables such as low elevations, northern aspects, and north latitudes. Our analysis specifically focused on winter habitat ranges with substantial low elevation forest. The application of geographic information science and remote sensing will be useful for managers of the SNBSRP in restoring lost or vulnerable habitat to further aid the recovery of the subspecies.”

Developing a Multi-network Urbanization Model: A Case Study of Urban Growth in Denver, Colorado

International Journal of Geographical Information Science, Volume 25, Issue 2, 2011

Jida Wang; Giorgos Mountrakis

“Urbanization is an important issue concerning diverse scientific and policy communities. Computational models quantifying locations and quantities of urban growth offer numerous environmental and socioeconomic benefits. Traditional urban growth models are based on a single-algorithm fitting procedure and thus restricted on their ability to capture spatial heterogeneity. Accordingly, a GIS-based modeling framework titled multi-network urbanization (MuNU) model is developed that integrates multiple neural networks. The MuNU model enables a filtering approach where input data patterns are automatically reallocated into appropriate neural networks with targeted accuracies. We hypothesize that observations classified by individual neural networks share greater homogeneity, and thus modeling accuracy will increase with the integration of multiple targeted algorithms. Land use and land cover data sets of two time snapshots (1977 and 1997) covering the Denver Metropolitan Area are used for model training and validation. Compared to a single-step algorithm – either a stepwise logistic regression or a single neural network – several improvements are evident in the visual output of the MuNU model. Statistical validations further quantify the superiority of the MuNU model and support our hypothesis of effective incorporation of spatial heterogeneity.”