Mapping poverty using mobile phone and satellite data

Abstract

Poverty is one of the most important determinants of adverse health outcomes globally, a major cause of societal instability and one of the largest causes of lost human potential. Traditional approaches to measuring and targeting poverty rely heavily on census data, which in most low- and middle-income countries (LMICs) are unavailable or out-of-date. Alternate measures are needed to complement and update estimates between censuses. This study demonstrates how public and private data sources that are commonly available for LMICs can be used to provide novel insight into the spatial distribution of poverty. We evaluate the relative value of modelling three traditional poverty measures using aggregate data from mobile operators and widely available geospatial data. Taken together, models combining these data sources provide the best predictive power (highest r² = 0.78) and lowest error, but generally models employing mobile data only yield comparable results, offering the potential to measure poverty more frequently and at finer granularity. Stratifying models into urban and rural areas highlights the advantage of using mobile data in urban areas and different data in different contexts. The findings indicate the possibility to estimate and continually monitor poverty rates at high spatial resolution in countries with limited capacity to support traditional methods of data collection.

Keywords: Bayesian geostatistical modelling; mobile phone data; poverty mapping; remote sensing.

Figure 1.

Spatial structure of Voronoi polygons based on the configuration of mobile phone towers in Bangladesh. The zoom window shows the spatial detail of Dhaka.

Figure 2.

National level prediction maps for mean WI (a) with uncertainty (d); mean probability of households being below $2.50/day (b) with uncertainty (e); and mean USD income (c) with uncertainty (f). Maps were generated using call detail record features, remote sensing data and Bayesian geostatistical models. The maps show the posterior mean and standard deviation from CDR–RS models for the WI and income data (a,c), and the RS model for the PPI (b). Red indicates poorer areas in prediction maps, and higher error in uncertainty maps.

Figure 3.

Out-of-sample observed versus predicted values for (a) DHS WI using mobile phone and remote sensing data: r² = 0.76, n = 117, p < 0.001, RMSE = 0.394; (b) progress out of Poverty Index using remote sensing data: r² = 0.32, n = 100, p < 0.001, RMSE = 57.439; and (c) income using mobile phone and remote sensing data: r² = 0.27, n = 1384, p < 0.001, RMSE = 105.465.

Figure 4.

Comparison of predicted mean DHS WI values between slum and non-slum areas in Dhaka as delineated by Gruebner et al. [63] t₆₁₅ =−17.2, p < 0.001. The 95% confidence interval using Student's t-distribution with 615 degrees of freedom is (−0.48, −0.38).

Figure 5.

Comparison of the proportion of people falling below upper (circles) and lower (triangles) poverty lines estimated by Ahmad et al. [64] and (a) predicted mean WI using mobile phone and remote sensing data, (b) predicted probability of being below $2.50 per day using remote sensing data and (c) predicted income using mobile phone and remote sensing data. All models were predicted at the upazila scale (Admin unit 3). Pearson's r correlations: −0.91 and −0.86 for the WI; 0.99 and 0.97 for the PPI; and −0.96 and −0.94 for income, respectively (p < 0.001 for all models).