Applying Multiple Testing Procedures to Detect Changes in East-African Vegetation Data

• Activity Number: 251
• Type: Contributed
• Date/Time: Monday, July 30, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Nicolle Clements*+ and Sanat Sarkar and Zhigen Zhao
• Companies: Temple University and Temple University and Temple University
• Keywords: Multiple Testing ; False Discovery Rate ; Vegetation ; NDVI ; Eastern Africa

Abstract

The study of vegetation fluctuations in a particular region is an important scientific problem, as it gives valuable information towards effective land use and development. We consider this problem for the East African region based on the Normalized Difference Vegetation Index (NDVI) series from satellite remote sensing data collected between 1982 and 2006 over 56,000 8-kilometer grid points in that region. We detect areas with significant vegetation changes using multiple testing procedures controlling mixed directional and non-directional false detections. The performances of these procedures are studied though simulations before applying to the vegetation data. Our analysis shows increasing Northern hemisphere and generally decreasing Southern hemisphere vegetation trends, which are consistent with historical evidence. Developing mathematical models describing specific types of vegetation changes in the detected East African locations will be a future goal.