1. Smallholder crop area mapped with wall-to-wall WorldView sub-meter panchromatic image texture: A test case for Tigray, Ethiopia
- Author
-
Mark L. Carroll, Gregory J. Husak, Markus Enenkel, Bristol Powell, Christopher S.R. Neigh, Jessica L. McCarty, Christopher Hain, and Margaret Wooten
- Subjects
Food security ,010504 meteorology & atmospheric sciences ,0211 other engineering and technologies ,Soil Science ,Geology ,02 engineering and technology ,Image segmentation ,01 natural sciences ,Panchromatic film ,Crop ,Image texture ,Metre ,Satellite imagery ,Computers in Earth Sciences ,Smoothing ,021101 geological & geomatics engineering ,0105 earth and related environmental sciences ,Remote sensing - Abstract
Global food production in the developing world occurs within sub-hectare fields that are difficult to identify with moderate resolution satellite imagery. Knowledge about the distribution of these fields is critical in food security programs. We developed a semi-automated image segmentation approach using wall-to-wall sub-meter imagery with high-performance computing to map crop area (CA) throughout Tigray, Ethiopia that encompasses over 41,000 km 2 . Multiple processing streams were tested to minimize mapping error while applying five unique smoothing kernels to capture differences in land surface texture associated to CA. Typically, very-small fields (mean
- Published
- 2018