Date on Master's Thesis/Doctoral Dissertation

12-2021

Document Type

Master's Thesis

Degree Name

M.S.

Department

Geographic and Environmental Sciences

Degree Program

Geography (Applied), MS

Committee Chair

Gaughan, Andrea

Committee Member

Stevens, Forrest

Committee Member

Pricope, Narcisa

Author's Keywords

southern Africa; rural; human footprint; regional; land use

Abstract

The “human footprint” can be used as a general proxy to estimate human activities across the landscape. The human footprint in the Zambezi Region of Namibia is critically important for regional management of conservation efforts and land use planning. The land covers in the Zambezi Region are characteristically difficult to separate spectrally, due to a highly heterogeneous savanna landscape. Object Based Image Analysis (OBIA) and Random Forest (RF) methods are notable for their ability to improve classification accuracies of remotely sensed imagery. In this study, I investigate the extent of the human footprint in the Zambezi Region of Namibia, using OBIA, RF, and a hybrid Object-based Random Forest approach. Results highlight that Object-based approaches score 5-10% better than a pixel-based RF approach in overall accuracy. Further investigation into the human footprint of the Zambezi Region is necessary for regional and local conservation and sustainable development.

Download

Share

COinS