Using publicly available satellite imagery and deep learning to understand economic well-being in Africa

It is generally difficult to scale derived estimates and understand the accuracy across locations for passively-collected data sources, such as mobile phones and satellite imagery. Here the authors show that their trained deep learning models are able to explain 70% of the variation in ground-measur...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Christopher Yeh, Anthony Perez, Anne Driscoll, George Azzari, Zhongyi Tang, David Lobell, Stefano Ermon, Marshall Burke
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
Q
Acceso en línea:https://doaj.org/article/7795998e04994473a909cfaf24b6daf9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7795998e04994473a909cfaf24b6daf9
record_format dspace
spelling oai:doaj.org-article:7795998e04994473a909cfaf24b6daf92021-12-02T15:52:23ZUsing publicly available satellite imagery and deep learning to understand economic well-being in Africa10.1038/s41467-020-16185-w2041-1723https://doaj.org/article/7795998e04994473a909cfaf24b6daf92020-05-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-16185-whttps://doaj.org/toc/2041-1723It is generally difficult to scale derived estimates and understand the accuracy across locations for passively-collected data sources, such as mobile phones and satellite imagery. Here the authors show that their trained deep learning models are able to explain 70% of the variation in ground-measured village wealth in held-out countries, outperforming previous benchmarks from high-resolution imagery with errors comparable to that of existing ground data.Christopher YehAnthony PerezAnne DriscollGeorge AzzariZhongyi TangDavid LobellStefano ErmonMarshall BurkeNature PortfolioarticleScienceQENNature Communications, Vol 11, Iss 1, Pp 1-11 (2020)
institution DOAJ
collection DOAJ
language EN
topic Science
Q
spellingShingle Science
Q
Christopher Yeh
Anthony Perez
Anne Driscoll
George Azzari
Zhongyi Tang
David Lobell
Stefano Ermon
Marshall Burke
Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
description It is generally difficult to scale derived estimates and understand the accuracy across locations for passively-collected data sources, such as mobile phones and satellite imagery. Here the authors show that their trained deep learning models are able to explain 70% of the variation in ground-measured village wealth in held-out countries, outperforming previous benchmarks from high-resolution imagery with errors comparable to that of existing ground data.
format article
author Christopher Yeh
Anthony Perez
Anne Driscoll
George Azzari
Zhongyi Tang
David Lobell
Stefano Ermon
Marshall Burke
author_facet Christopher Yeh
Anthony Perez
Anne Driscoll
George Azzari
Zhongyi Tang
David Lobell
Stefano Ermon
Marshall Burke
author_sort Christopher Yeh
title Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
title_short Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
title_full Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
title_fullStr Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
title_full_unstemmed Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
title_sort using publicly available satellite imagery and deep learning to understand economic well-being in africa
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/7795998e04994473a909cfaf24b6daf9
work_keys_str_mv AT christopheryeh usingpubliclyavailablesatelliteimageryanddeeplearningtounderstandeconomicwellbeinginafrica
AT anthonyperez usingpubliclyavailablesatelliteimageryanddeeplearningtounderstandeconomicwellbeinginafrica
AT annedriscoll usingpubliclyavailablesatelliteimageryanddeeplearningtounderstandeconomicwellbeinginafrica
AT georgeazzari usingpubliclyavailablesatelliteimageryanddeeplearningtounderstandeconomicwellbeinginafrica
AT zhongyitang usingpubliclyavailablesatelliteimageryanddeeplearningtounderstandeconomicwellbeinginafrica
AT davidlobell usingpubliclyavailablesatelliteimageryanddeeplearningtounderstandeconomicwellbeinginafrica
AT stefanoermon usingpubliclyavailablesatelliteimageryanddeeplearningtounderstandeconomicwellbeinginafrica
AT marshallburke usingpubliclyavailablesatelliteimageryanddeeplearningtounderstandeconomicwellbeinginafrica
_version_ 1718385578828890112