View in EDS HTML Full Text PDF Full Text

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

Saved in:
Bibliographic Details
Title: A data-driven approach to mapping multidimensional poverty at residential block level in Mexico.
Authors: Zea-Ortiz, Marivel1 (AUTHOR), Vera, Pablo1 (AUTHOR), Salas, Joaquín1,2 (AUTHOR) jsalasr@ipn.mx, Manduchi, Roberto3 (AUTHOR), Villaseñor, Elio1 (AUTHOR), Figueroa, Alejandra4 (AUTHOR), Suárez, Ranyart R.4 (AUTHOR)
Source: Environment, Development & Sustainability. Mar2026, Vol. 28 Issue 3, p6467-6490. 24p.
Subject Terms: *Deep learning, *Convolutional neural networks, *Remote-sensing images, *Poverty rate, *Census, *Evidence-based policy
Geographic Terms: Mexico
Abstract: 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 of 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 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. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 192418035
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A data-driven approach to mapping multidimensional poverty at residential block level in Mexico.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zea-Ortiz%2C+Marivel%22">Zea-Ortiz, Marivel</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Vera%2C+Pablo%22">Vera, Pablo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Salas%2C+Joaquín%22">Salas, Joaquín</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> jsalasr@ipn.mx</i><br /><searchLink fieldCode="AR" term="%22Manduchi%2C+Roberto%22">Manduchi, Roberto</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Villaseñor%2C+Elio%22">Villaseñor, Elio</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Figueroa%2C+Alejandra%22">Figueroa, Alejandra</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Suárez%2C+Ranyart+R%2E%22">Suárez, Ranyart R.</searchLink><relatesTo>4</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Environment%2C+Development+%26+Sustainability%22">Environment, Development & Sustainability</searchLink>. Mar2026, Vol. 28 Issue 3, p6467-6490. 24p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Remote-sensing+images%22">Remote-sensing images</searchLink><br />*<searchLink fieldCode="DE" term="%22Poverty+rate%22">Poverty rate</searchLink><br />*<searchLink fieldCode="DE" term="%22Census%22">Census</searchLink><br />*<searchLink fieldCode="DE" term="%22Evidence-based+policy%22">Evidence-based policy</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Mexico%22">Mexico</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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 of 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 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. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=192418035
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10668-024-05230-z
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 6467
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Remote-sensing images
        Type: general
      – SubjectFull: Poverty rate
        Type: general
      – SubjectFull: Census
        Type: general
      – SubjectFull: Evidence-based policy
        Type: general
      – SubjectFull: Mexico
        Type: general
    Titles:
      – TitleFull: A data-driven approach to mapping multidimensional poverty at residential block level in Mexico.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zea-Ortiz, Marivel
      – PersonEntity:
          Name:
            NameFull: Vera, Pablo
      – PersonEntity:
          Name:
            NameFull: Salas, Joaquín
      – PersonEntity:
          Name:
            NameFull: Manduchi, Roberto
      – PersonEntity:
          Name:
            NameFull: Villaseñor, Elio
      – PersonEntity:
          Name:
            NameFull: Figueroa, Alejandra
      – PersonEntity:
          Name:
            NameFull: Suárez, Ranyart R.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 03
              Text: Mar2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 1387585X
          Numbering:
            – Type: volume
              Value: 28
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Environment, Development & Sustainability
              Type: main
ResultId 1