Disaggregating census data for population mapping using random forests with remotely-sensed and ancillary data.
Stevens FR, Gaughan AE, Linard C, Tatem AJ. · 2015
Read Disaggregating census data for population mapping using random forests with remotely-sensed and ancillary data. by Stevens FR, Gaughan AE, Linard C, Tatem AJ. (2015) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc4331277.txt.
Description
Forrest R Stevens, Andrea E Gaughan, Catherine Linard, Andrew J Tatem, and Luís A Nunes Amaral present a method for turning coarse census counts into fine maps of where people live. Their paper appeared in PLoS ONE in 2015. Planners need population density at street scale to judge growth impacts and deliver services, but censuses report only large blocks.
Their approach trains a random forest model on satellite imagery and geographic data. The model predicts how density varies inside each census unit. The counts are then spread accordingly, reaching about one hundred meter resolution. A case study compares the output with older mapping methods. The technique is semi-automated and built from widely available data, so statistical offices in data poor countries can adopt it.
Catalog record
| CREATOR | Stevens FR, Gaughan AE, Linard C, Tatem AJ. |
|---|---|
| YEAR | 2015 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |