France Population Monthly Maps 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. (In Press). 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 population counts estimated from mobile phone records.

plot of chunk predict_density

France 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 mobile phone calls within each cell tower area (see Deville et al., 2014 for a detailed description of the method). These values are used as the dependent variable during model estimation.

France population monthly estimates in mobile phone cells, 2007

Folder: Census
File Name: Antennes_zones2.shp
Source: Orange France
Description: Mobile phone data cover the period May-October 2007. The total national population was adjusted
Class: polygon
Derived Covariates:
area, buff, zones,

class       : SpatialPolygonsDataFrame 
nfeatures : 17184
extent : -544118, 546158, 4579062, 5679604 (xmin, xmax, ymin, ymax)
coord. ref. : NA
nvariables : 14

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: 16

          Mean of squared residuals: 1.2
                    % Var explained: 80

plot of chunk random_forestplot of chunk random_forestplot of chunk random_forest

Covariate Metadata

France Classified Land Cover

Folder: Landcover
File Name: lc_fra06.tif
Source: CORINE 2006, 100m
Description: Landcover from the CORINE 2006 product resampled to 100m, reclassified to match AfriPop coding and eventually broken down into binary classifications by aggregated land cover type (see Linard, et al., 2010 and Gaughan, et al. 2013 for category information).
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 : 11207, 11104, 124442528, 1 (nrow, ncol, ncell, nlayers)
resolution : 100, 100 (x, y)
extent : -554198, 556202, 4568980, 5689680 (xmin, xmax, ymin, ymax)
coord. ref. : +proj=utm +zone=32 +datum=WGS84 +units=m +no_defs +ellps=WGS84 +towgs84=0,0,0
data source : D:\APRF\RF\data\FRA\Landcover\Derived\landcover.tif
names : landcover
min values : 11
max values : 250

plot of chunk covariate_reports


MODIS 17A3 2010 Estimated Net Primary Productivity, 1km

Folder: NPP
File Name: DEFAULT: MODIS 17A3 2010
Source: United States Geological Survey (USGS)
Description: MODIS 17A3 version-55 derived estimates of net primary productivity for the year 2010, estimated for 1km pixel sizes and subset and resampled to match the available land cover and final population map output requirements.
Class: raster
Derived Covariates:
,

class       : RasterBrick 
dimensions : 11207, 11104, 124442528, 1 (nrow, ncol, ncell, nlayers)
resolution : 100, 100 (x, y)
extent : -554198, 556202, 4568980, 5689680 (xmin, xmax, ymin, ymax)
coord. ref. : +proj=utm +zone=32 +datum=WGS84 +units=m +no_defs +ellps=WGS84 +towgs84=0,0,0
data source : D:\APRF\RF\data\FRA\NPP\Derived\npp.tif
names : npp
min values : 0
max values : 20023