Ukraine Population Map Metadata Report

Prediction Weighting Layer Used in Population Redistribution

The data presented below represent the predicted number of people per ~100 m pixel as estimated using the random forest (RF) model as described in Stevens, et al. (2015). The following pages contain a description of the RF model and its covariates, their sources and any metadata collected for each covariate. The prediction weighting layer is used to dasymetrically redistribute the census counts and project counts to match estimated populations based on UN estimates for the final population maps provided by WorldPop.

Stevens, F. R., Gaughan, A. E., Linard, C., & Tatem, A. J. (2015). Disaggregating Census Data for Population Mapping Using Random Forests with Remotely-Sensed and Ancillary Data. PLOS ONE, 10(2), e0107042. doi:10.1371/journal.pone.0107042

plot of chunk predict_density

Ukraine Census Data and Observed Population Density

These data are the population density values used to estimate the RF model used to create the prediction weighting layer you see above. Values represent population density as measured by people per hectare and calculated from population counts within each census unit. These values are used as the dependent variable during model estimation.

Ukraine Raion Admin 2

Folder: Census
File Name: census.shp
Source: Ukraine Geohive
Description: These high spatial resolution census block data were attained through GDAM.
Class: polygon
Derived Covariates:
area, buff, zones,

class       : SpatialPolygonsDataFrame 
nfeatures   : 629 
extent      : 884320, 2144747, 1913591, 2773444  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 17

plot of chunk census_data


Random Forest Model and Diagnostics

These output and figures outline the estimated RF model that is used to predict the population density weighting layer. The model is fitted to the population density values for the preceding census data using covariates aggregatedfrom the ancillary data sources summarized following the model diagnostics.


Call:
 randomForest(x = x_data, y = y_data, ntree = popfit$ntree, mtry = popfit$mtry,      nodesize = length(y_data)/1000, importance = TRUE, proximity = TRUE) 
               Type of random forest: regression
                     Number of trees: 500
No. of variables tried at each split: 10

          Mean of squared residuals: 0.24
                    % Var explained: 92

plot of chunk random_forestplot of chunk random_forestplot of chunk random_forest

Covariate Metadata

Remotely-sensed, Classified Landcover

Folder: Landcover
File Name: ukrlc.tif
Source: Globcover with Schneider Extents
Description: LC Processed by Alessandro
Class: raster
Derived Covariates:
prp011, cls011, dst011, prp040, cls040, dst040, prp130, cls130, dst130, prp140, cls140, dst140, prp150, cls150, dst150, prp160, cls160, dst160, prp190, cls190, dst190, prp200, cls200, dst200, prp210, cls210, dst210, prp230, cls230, dst230, prp240, cls240, dst240, prp250, cls250, dst250, prpBLT, clsBLT, dstBLT,

class       : RasterBrick 
dimensions  : 8800, 12805, 112684000, 1  (nrow, ncol, ncell, nlayers)
resolution  : 100, 100  (x, y)
extent      : 874262, 2154762, 1903526, 2783526  (xmin, xmax, ymin, ymax)
coord. ref. : +proj=lcc +lat_1=43 +lat_2=62 +lat_0=30 +lon_0=10 +x_0=0 +y_0=0 +ellps=intl +units=m +no_defs 
data source : E:\RF.1.0\data\UKR\Landcover\Derived\landcover.tif 
names       : landcover 
min values  :         0 
max values  :       240 

plot of chunk covariate_reports


Suomi NPP VIIRS-Derived 2012 Lights at Night, 15 arc-second

Folder: Lights
File Name: DEFAULT: VIIRS 2012
Source: http://ngdc.noaa.gov/eog/viirs/download_viirs_ntl.html
Description: These 'Lights at Night' data were derived from imagery collected by the Suomi National Polar-orbiting Partnership (NPP) Visible Infrared Imaging Radiometer Suite (VIIRS) sensor. Data were collected in 2012 on moonless nights and though background noise associated with fires, gas-flares, volcanoes or aurora have not been removed it represents the best-available data for night-time light production.
Class: raster
Derived Covariates:
,

class       : RasterBrick 
dimensions  : 8801, 12807, 112714407, 1  (nrow, ncol, ncell, nlayers)
resolution  : 100, 100  (x, y)
extent      : 874162, 2154862, 1903526, 2783626  (xmin, xmax, ymin, ymax)
coord. ref. : +proj=lcc +lat_1=43 +lat_2=62 +lat_0=30 +lon_0=10 +x_0=0 +y_0=0 +ellps=intl +units=m +no_defs 
data source : E:\RF.1.0\data\UKR\Lights\Derived\lights.tif 
names       : lights 
min values  :      0 
max values  :   3929 

plot of chunk covariate_reports


WorldClim/BioClim Mean Annual Temperature 1950-2000, 30 arc-second

Folder: Temp
File Name: DEFAULT: BIO1
Source: http://www.worldclim.org/current
Description: WorldClim/BioClim 1950-2000 mean annual precipitation (BIO12) and mean annual temperature (BIO1) estimates (Hijmans et al., 2005) were downloaded, mosaicked and subset to match the extent of our land cover data for the mapping of this region.
Class: raster
Derived Covariates:
,

class       : RasterBrick 
dimensions  : 8801, 12807, 112714407, 1  (nrow, ncol, ncell, nlayers)
resolution  : 100, 100  (x, y)
extent      : 874162, 2154862, 1903526, 2783626  (xmin, xmax, ymin, ymax)
coord. ref. : +proj=lcc +lat_1=43 +lat_2=62 +lat_0=30 +lon_0=10 +x_0=0 +y_0=0 +ellps=intl +units=m +no_defs 
data source : E:\RF.1.0\data\UKR\Temp\Derived\temp.tif 
names       : temp 
min values  :    0 
max values  :  137 

plot of chunk covariate_reports


WorldClim/BioClim Mean Annual Precipitation 1950-2000, 30 arc-second

Folder: Precip
File Name: DEFAULT: BIO12
Source: http://www.worldclim.org/current
Description: WorldClim/BioClim 1950-2000 mean annual precipitation (BIO12) and mean annual temperature (BIO1) estimates (Hijmans et al., 2005) were downloaded, mosaicked and subset to match the extent of our land cover data for the mapping of this region.
Class: raster
Derived Covariates:
,

class       : RasterBrick 
dimensions  : 8801, 12807, 112714407, 1  (nrow, ncol, ncell, nlayers)
resolution  : 100, 100  (x, y)
extent      : 874162, 2154862, 1903526, 2783626  (xmin, xmax, ymin, ymax)
coord. ref. : +proj=lcc +lat_1=43 +lat_2=62 +lat_0=30 +lon_0=10 +x_0=0 +y_0=0 +ellps=intl +units=m +no_defs 
data source : E:\RF.1.0\data\UKR\Precip\Derived\precip.tif 
names       : precip 
min values  :    311 
max values  :   1068 

plot of chunk covariate_reports


Roads (OSM), 2013

Folder: Roads
File Name: roads.shp
Source: Open Street Map, Downloaded 2013-03-04, http://extract.bbbike.org/
Description: These data were downloaded as part of a per-country package of data layers made availalble as shapefiles through the http://extract.bbbike.org website, extracted from the Open Street Map (OSM) database.
Class: linear
Derived Covariates:
prp, cls, dst,

class       : SpatialLinesDataFrame 
nfeatures   : 616936 
extent      : 874326, 2154745, 1903724, 2782630  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 7

plot of chunk covariate_reports


Rivers (OSM), 2013

Folder: Rivers
File Name: rivers.shp
Source: Open Street Map, Downloaded 2013-03-04, http://extract.bbbike.org/
Description: These data were downloaded as part of a per-country package of data layers made availalble as shapefiles through the http://extract.bbbike.org website, extracted from the Open Street Map (OSM) database.
Class: linear
Derived Covariates:
prp, cls, dst,

class       : SpatialLinesDataFrame 
nfeatures   : 26530 
extent      : 874693, 2154688, 1912019, 2783443  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 4

plot of chunk covariate_reports


Populated Places

Folder: Populated
File Name: DEFAULT: Merged pop/builtupp, pop/builtupa, pop/mispopp
Source: National Geospatial-Intelligence Agency (NGA), http://geoengine.nga.mil/geospatial/SW_TOOLS/NIMAMUSE/webinter/rast_roam.html
Description: The VMAP0 data area downloaded as separate files, grouped roughly by continent, and merged into individual shapefiles for subsetting and further processing for population mapping efforts. These data were obtained directly from the original VMAP0 data sources provided by the NGA and pre-processed using Military Analyst in ArcGIS 10.0. Point data sources are buffered to 100 m and then all polygon data sources are merged to a single shapefile prior to processing.
Class: polygon
Derived Covariates:
cls, dst, prp,

class       : SpatialPolygonsDataFrame 
nfeatures   : 3612 
extent      : 878534, 2154668, 1904786, 2780042  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 12

plot of chunk covariate_reports


Inland Waterbodies

Folder: Waterbodies
File Name: DEFAULT: hydro/watrcrsl
Source: National Geospatial-Intelligence Agency (NGA), http://geoengine.nga.mil/geospatial/SW_TOOLS/NIMAMUSE/webinter/rast_roam.html
Description: The VMAP0 data area downloaded as separate files, grouped roughly by continent, and merged into individual shapefiles for subsetting and further processing for population mapping efforts. These data were obtained directly from the original VMAP0 data sources provided by the NGA and pre-processed using Military Analyst in ArcGIS 10.0.
Class: polygon
Derived Covariates:
cls, dst, prp,

class       : SpatialPolygonsDataFrame 
nfeatures   : 1227 
extent      : 921378, 2153204, 1910136, 2760368  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 10

plot of chunk covariate_reports


Protected Areas

Folder: Protected
File Name: DEFAULT: WDPAfgdb_Sept2012.gdb
Source: World Database on Protected Areas, Downloaded September, 2012, UNEP, http://www.wdpa.org, http://protectedplanet.net
Description: These data are compiled by UNEP and distributed via the Protected Planet website. All protected areas were downloaded regardless of International Union for Conservation of Nature (IUCN) or any other designation, so they include sanctuaries, national parks, game reserves, World Heritage Sites, etc.
Class: polygon
Derived Covariates:
cls, dst, prp,

class       : SpatialPolygonsDataFrame 
nfeatures   : 1436 
extent      : 874491, 2139081, 1903592, 2774044  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 26

plot of chunk covariate_reports


Elevation and Derived Slope, 3 second

Folder: Elevation
File Name: DEFAULT: Void-Filled DEM.gdb
Source: HydroSHEDS Void-Filled DEM (Lehnert, et al., 2006), http://hydrosheds.cr.usgs.gov/dataavail.php
Description: The HydroSHEDS data are the result of an effort to provide a globally consistent dataset consisting of NASA's Shuttle Radar Topography Mission (SRTM) data and have been processed, void-filled and corrected for use at large scales.
Class: raster
Derived Covariates:
, slope,

class       : RasterBrick 
dimensions  : 8801, 12807, 112714407, 1  (nrow, ncol, ncell, nlayers)
resolution  : 100, 100  (x, y)
extent      : 874162, 2154862, 1903526, 2783626  (xmin, xmax, ymin, ymax)
coord. ref. : +proj=lcc +lat_1=43 +lat_2=62 +lat_0=30 +lon_0=10 +x_0=0 +y_0=0 +ellps=intl +units=m +no_defs 
data source : E:\RF.1.0\data\UKR\Elevation\Derived\elevation.tif 
names       : elevation 
min values  :      -283 
max values  :      2258 

plot of chunk covariate_reports


Digitized Building Locations (OSM), 2013

Folder: Buildings
File Name: buildings.shp
Source: Open Street Map, Downloaded 2013-03-04, http://extract.bbbike.org/
Description: These data were downloaded as part of a per-country package of data layers made availalble as shapefiles through the http://extract.bbbike.org website, extracted from the Open Street Map (OSM) database.
Class: polygon
Derived Covariates:
prp, cls, dst,

class       : SpatialPolygonsDataFrame 
nfeatures   : 1170078 
extent      : 874324, 2153574, 1909879, 2780817  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 3

plot of chunk covariate_reports


Points of Interest Locations (OSM), 2013

Folder: Points
File Name: points.shp
Source: Open Street Map, Downloaded 2013-03-04, http://extract.bbbike.org/
Description: These data were downloaded as part of a per-country package of data layers made availalble as shapefiles through the http://extract.bbbike.org website, extracted from the Open Street Map (OSM) database.
Class: point
Derived Covariates:
prp, cls, dst,

class       : SpatialPointsDataFrame 
nfeatures   : 77141 
extent      : 875430, 2153542, 1906255, 2780795  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 4

plot of chunk covariate_reports


Delineated Land Uses (OSM), 2013

Folder: Uses
File Name: uses.shp
Source: Open Street Map, Downloaded 2013-03-04, http://extract.bbbike.org/
Description: These data were downloaded as part of a per-country package of data layers made availalble as shapefiles through the http://extract.bbbike.org website, extracted from the Open Street Map (OSM) database.
Class: polygon
Derived Covariates:
prp, cls, dst,

class       : SpatialPolygonsDataFrame 
nfeatures   : 90992 
extent      : 874320, 2154743, 1903634, 2782640  (xmin, xmax, ymin, ymax)
coord. ref. : NA 
nvariables  : 3

plot of chunk covariate_reports