Busia K-Means Cluster Map

Listed in Datasets

By Joshua Minai1, Darrell Schulze1

Purdue University

Map that mimics the geometry of 'fully developed slopes'.

Version 1.0 - published on 18 Nov 2019 doi:10.4231/4Q9T-FT90 - cite this Content may change until committed to the archive on 18 Dec 2019

Licensed under CC0 1.0 Universal


Six terrain attributes were subjected to K-means clustering performed in SAGA-GIS using the hill-climbing method (Rubin, 1967) using a terrain attribute combination of multiresolution valley bottom flatness, multiresolution ridgetop flatness, planform curvature, profile curvature, SAGA wetness index, and topographic position index. This process was intended to mimic the geometry of ‘fully developed slopes’ observed within the landscape. (Wood, 1942; King, 1957). Examination of 5-cluster map by overlaying it on the satellite imagery showed that clustered correspond to different slope positions viz summit, shoulder, backslope, toeslope, and footslope and was used to predict soil properties and disaggregated for the Busia area.

King, C. (1957). The uniformitarian nature of hillslopes. Transactions of the Edinburgh Geological Society, 17:81-102.

Rubin, J. (1967). Optimal classification into groups: an approach for solving the taxonomy problem. Journal of Theoretical Biology, 15:103-144.

Wood, A. (1942): The development of hillslopes. Geologists Association Proceedings 53:128-138.

Cite this work

Researchers should cite this work as follows:


The Purdue University Research Repository (PURR) is a university core research facility provided by the Purdue University Libraries, the Office of the Executive Vice President for Research and Partnerships, and Information Technology at Purdue (ITaP).