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 approac...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2024
|
| Online Access: | https://hdl.handle.net/1721.1/155801 |
| _version_ | 1811084645032263680 |
|---|---|
| author | Zea-Ortiz, Marivel Vera, Pablo Salas, Joaquín Manduchi, Roberto Villaseñor, Elio Figueroa, Alejandra Suárez, Ranyart R. |
| author_facet | Zea-Ortiz, Marivel Vera, Pablo Salas, Joaquín Manduchi, Roberto Villaseñor, Elio Figueroa, Alejandra Suárez, Ranyart R. |
| author_sort | Zea-Ortiz, Marivel |
| collection | MIT |
| description | 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 𝑅2
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 𝑅2
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. |
| first_indexed | 2024-09-23T12:54:50Z |
| format | Article |
| id | mit-1721.1/155801 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:54:50Z |
| publishDate | 2024 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1558012024-09-19T04:57:28Z A data-driven approach to mapping multidimensional poverty at residential block level in Mexico Zea-Ortiz, Marivel Vera, Pablo Salas, Joaquín Manduchi, Roberto Villaseñor, Elio Figueroa, Alejandra Suárez, Ranyart R. 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 𝑅2 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 𝑅2 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. 2024-07-29T20:21:10Z 2024-07-29T20:21:10Z 2024-07-21 2024-07-28T03:25:17Z Article http://purl.org/eprint/type/JournalArticle 1573-2975 https://hdl.handle.net/1721.1/155801 Zea-Ortiz, M., Vera, P., Salas, J. et al. A data-driven approach to mapping multidimensional poverty at residential block level in Mexico. Environ Dev Sustain (2024). PUBLISHER_CC en 10.1007/s10668-024-05230-z Environment, Development and Sustainability Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer Science and Business Media LLC Springer Netherlands |
| spellingShingle | Zea-Ortiz, Marivel Vera, Pablo Salas, Joaquín Manduchi, Roberto Villaseñor, Elio Figueroa, Alejandra Suárez, Ranyart R. A data-driven approach to mapping multidimensional poverty at residential block level in Mexico |
| title | A data-driven approach to mapping multidimensional poverty at residential block level in Mexico |
| title_full | A data-driven approach to mapping multidimensional poverty at residential block level in Mexico |
| title_fullStr | A data-driven approach to mapping multidimensional poverty at residential block level in Mexico |
| title_full_unstemmed | A data-driven approach to mapping multidimensional poverty at residential block level in Mexico |
| title_short | A data-driven approach to mapping multidimensional poverty at residential block level in Mexico |
| title_sort | data driven approach to mapping multidimensional poverty at residential block level in mexico |
| url | https://hdl.handle.net/1721.1/155801 |
| work_keys_str_mv | AT zeaortizmarivel adatadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT verapablo adatadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT salasjoaquin adatadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT manduchiroberto adatadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT villasenorelio adatadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT figueroaalejandra adatadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT suarezranyartr adatadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT zeaortizmarivel datadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT verapablo datadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT salasjoaquin datadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT manduchiroberto datadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT villasenorelio datadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT figueroaalejandra datadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico AT suarezranyartr datadrivenapproachtomappingmultidimensionalpovertyatresidentialblocklevelinmexico |