Poverty rate prediction using multi-modal survey and earth observation data

This work presents an approach for combining household demographic and living standards survey questions with features derived from satellite imagery to predict the poverty rate of a region. Our approach utilizes visual features obtained from a single-step featurization method applied to freely available 10m/px Sentinel-2 surface reflectance satellite imagery. These visual features are combined with ten survey questions in a proxy means test (PMT) to estimate whether a household is below the poverty line. We show that the inclusion of visual features reduces the mean error in poverty rate estimates from 4.09% to 3.88% over a nationally representative out-of-sample test set. In addition to including satellite imagery features in proxy means tests, we propose an approach for selecting a subset of survey questions that are complementary to the visual features extracted from satellite imagery. Specifically, we design a survey variable selection approach guided by the full survey and image features and use the approach to determine the most relevant set of small survey questions to include in a PMT. We validate the choice of small survey questions in a downstream task of predicting the poverty rate using the small set of questions. This approach results in the best performance – errors in poverty rate decrease from 4.09% to 3.71%. We show that extracted visual features encode geographic and urbanization differences between regions.

[1]  Thorsteinn S. Rögnvaldsson,et al.  A review of explainable AI in the satellite data, deep machine learning, and human poverty domain , 2022, Patterns.

[2]  D. Matteson,et al.  Predicting poverty with vegetation index , 2021, Applied Economic Perspectives and Policy.

[3]  Yunming Ye,et al.  An Investigation on Deep Learning Approaches to Combining Nighttime and Daytime Satellite Imagery for Poverty Prediction , 2021, IEEE Geoscience and Remote Sensing Letters.

[4]  Guanghua Chi,et al.  Microestimates of wealth for all low- and middle-income countries , 2021, Proceedings of the National Academy of Sciences.

[5]  Chiara Ledesma,et al.  Interpretable Poverty Mapping using Social Media Data, Satellite Images, and Geospatial Information , 2020, ArXiv.

[6]  Esther Rolf,et al.  A generalizable and accessible approach to machine learning with global satellite imagery , 2020, Nature Communications.

[7]  G. Davis.  End Poverty in All Its Forms Everywhere , 2020, Mining, Materials, and the Sustainable Development Goals (SDGs).

[8]  S. Ermon,et al.  Using publicly available satellite imagery and deep learning to understand economic well-being in Africa , 2020, Nature Communications.

[9]  M. Fatehkia,et al.  MAPPING POVERTY IN THE PHILIPPINES USING MACHINE LEARNING, SATELLITE IMAGERY, AND CROWD-SOURCED GEOSPATIAL INFORMATION , 2019 .

[10]  Rachel Wells,et al.  Household poverty classification in data-scarce environments: a machine learning approach , 2017, 1711.06813.

[11]  Andrew Head,et al.  Can Human Development be Measured with Satellite Imagery? , 2017, ICTD.

[12]  Neeti Pokhriyal,et al.  Combining disparate data sources for improved poverty prediction and mapping , 2017, Proceedings of the National Academy of Sciences.

[13]  Xin Lu,et al.  Mapping poverty using mobile phone and satellite data , 2017, Journal of The Royal Society Interface.

[14]  M. Ravallion,et al.  A Poor Means Test? Econometric Targeting in Africa , 2016, Journal of Development Economics.

[15]  Sang Michael Xie,et al.  Combining satellite imagery and machine learning to predict poverty , 2016, Science.

[16]  Stefan Sperlich,et al.  Generalized Additive Models , 2014 .

[17]  Johannes Gehrke,et al.  Intelligible models for classification and regression , 2012, KDD.

[18]  Bruce E. Kaufman,et al.  Minimum Wage Channels of Adjustment , 2011, SSRN Electronic Journal.

[19]  M. Mowafi,et al.  Poverty , 2005, Journal of Epidemiology and Community Health.

[20]  G. Subsol,et al.  Assessment of CNN-Based Methods for Poverty Estimation from Satellite Images , 2020, ICPR Workshops.

[21]  G. Chiara.  EUROPEAN SPACE AGENCY , 2001 .