Mapping and Classifying Settlement Locations

This is an update to the earlier version of a paper with the same title, “Mapping and Classifying Settlement Locations”. This version paper has the following corrections: - Updated Table of Contents on page 2 - Removed map under Polio immunisation microplan for Dundubus Ward in Jigawa State, Nigeria on page 19. It is a measles fixed post cluster map created by Novel-T. - Updated logos and About the Partners section on page 25 The paper discusses GRID3’s work on collecting and analyzing settlements data. GRID3’s settlements work has two areas of focus: creating a comprehensive settlement layer that enables a real-world picture of communities, and using building footprints, geospatial data layers, and machine learning algorithms to classify structures and local areas within settlements. The paper also discusses the applications of GRID3’s methods in Nigeria, the Democratic Republic of the Congo, and Zambia. GRID3 works with countries to generate, validate and use geospatial data on population, settlements, infrastructure, and subnational boundaries. For more information, see grid3.org. Keywords: area-level classification; building footprints; comprehensive settlement layer; extent; intra-settlement categorisation; machine learning; polygon layer; point layer; settlement; settlement data; settlement layer; settlement mapping; settlement point; ; GRID3; database schema; geospatial data; neighbourhood classification; open-source; health zones; participatory cartography; GIS; vaccination; immunisation; census; micro-plans; CIESIN; UNFPA; Flowminder; WorldPop; probability model; areal; built-up areas; small settlements; hamlets; hamlet areas; polio; Africa