A data-driven approach to mapping multidimensional poverty at residential block level in Mexico

Accurate, inexpensive and granular human poverty assessments are critical for data-driven policy decision-making. This research proposes a novel approach to computing poverty scores utilizing multispectral satellite images and indices calculated from census reference values. We show how this approach can leverage standard and sparse survey-based multidimensional poverty assessments at the municipal level to develop a deep learning architecture to obtain poverty scores at the residential block level. This method has the distinctive feature that the obtained inference corresponds to Multidimensional Measurement of Poverty generated by CONEVAL, the Mexican agency responsible for measuring poverty. We provide a reliable alternative to survey-based approaches with an $$R^2$$ R 2 of $$0.802\pm 0.022$$ 0.802 ± 0.022 for the lack of housing quality and spaces dimension. A convolutional neural network trained on multispectral satellite images and the lack of housing quality and spaces dimension, which is regressed from census reference variables corresponding to lack of water, electricity, sewage, concrete floor, toilet and occupancy level obtains an $$R^2$$ R 2 of 0.753. These results represent a significant step forward in including machine learning techniques to provide reliable information at reduced costs and a higher spatiotemporal frequency than traditional person-to-person surveys

Economic growth · Economics · Geography · Poverty · Impact of Light on Environment and Health · Land Use and Ecosystem Services · Mathematics

• A global poverty map derived from satellite data

  Open Access•Christopher D Elvidge, Peter C Sutton et al.•Computers & Geosciences•2009

  Incluir item

• The Challenge of Slums

  Open Access•Un-Habitat Un-Habitat, UN‐Habitat UN‐Habitat•Management of Environmental…•2004

  Incluir item

• A tutorial on support vector regression

  Open Access•Alex J Smola, Alex Smola et al.•Statistics and Computing•2004

  Incluir item

• Combining satellite imagery and machine learning to predict poverty

  Open Access•Neal Jean, Meghan Burke et al.•Science•2016

  Incluir item

• Backpropagation Applied to Handwritten Zip Code Recognition

  Yann LeCun, B Boser et al.•Neural Computation•1989

  Incluir item

• Identification of Poverty Areas by Remote Sensing and Machine Learning

  Open Access•Jian Yin, Yuanhong Qiu et al.•ISPRS International Journal of…•2020

  Incluir item

• Towards user-driven earth observation-based slum mapping

  Open Access•Maxwell Owusu, Monika Kuffer et al.•Computers Environment and Urban…•2021

  Incluir item

• Combining night time lights in prediction of poverty incidence at the county level

  Open Access•Jianbin Xu, Jie Song et al.•Applied Geography•2021

  Incluir item

• Transfer learning approach to map urban slums using high and medium resolution satellite imagery

  Open Access•Deepank Verma, Arpita Jana et al.•Habitat International•2019

  Incluir item

• An exploratory factor analysis model for slum severity index in Mexico City

  Open Access•Debraj Roy, David Bernal et al.•Urban Studies•2020

  Incluir item

• Mapping Poverty of Latin American and Caribbean Countries from Heaven Through Night-Light Satellite Images

  Open Access•Maria Simona Andreano, Roberto Benedetti et al.•Social Indicators Research•2021

  Incluir item