Using Satellite Images and Deep Learning to Measure Health and Living Standards in India

Simple item page
dc.contributor.authorDaoud, Adel
dc.contributor.authorJordan, Felipe
dc.contributor.authorSharma, Makkunda
dc.contributor.authorJohansson, Fredrik
dc.contributor.authorDubhashi, Devdatt
dc.contributor.authorPaul, Sourabh
dc.contributor.authorBanerjee, Subhashis
dc.date.accessioned2025-01-20T20:15:01Z
dc.date.available2025-01-20T20:15:01Z
dc.date.issued2023
dc.description.abstractUsing deep learning with satellite images enhances our understanding of human development at a granular spatial and temporal level. Most studies have focused on Africa and on a narrow set of asset-based indicators. This article leverages georeferenced village-level census data from across 40% of the population of India to train deep models that predicts 16 indicators of human well-being from Landsat 7 imagery. Based on the principles of transfer learning, the census-based model is used as a feature extractor to train another model that predicts an even larger set of developmental variables-over 90 variables-included in two rounds of the National Family Health Survey (NFHS). The census-based-feature-extractor model outperforms the current standard in the literature for most of these NFHS variables. Overall, the results show that combining satellite data with Indian Census data unlocks rich information for training deep models that track human development at an unprecedented geographical and temporal resolution.
dc.description.funderLinkoping University
dc.fuente.origenWOS
dc.identifier.doi10.1007/s11205-023-03112-x
dc.identifier.eissn1573-0921
dc.identifier.issn0303-8300
dc.identifier.urihttps://doi.org/10.1007/s11205-023-03112-x
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/92235
dc.identifier.wosidWOS:000978510200001
dc.issue.numero1-3
dc.language.isoen
dc.pagina.final505
dc.pagina.inicio475
dc.revistaSocial indicators research
dc.rightsacceso restringido
dc.subjectMeasurement of health and living conditions
dc.subjectIndicators
dc.subjectDeep learning
dc.subjectSatellite images
dc.subjectIndia
dc.subjectSurvey
dc.subjectCensus
dc.subject.ods14 Life Below Water
dc.subject.ods15 Life on Land
dc.subject.ods13 Climate Action
dc.subject.ods03 Good Health and Well-being
dc.subject.ods11 Sustainable Cities and Communities
dc.subject.odspa14 Vida submarina
dc.subject.odspa15 Vida de ecosistemas terrestres
dc.subject.odspa13 Acción por el clima
dc.subject.odspa03 Salud y bienestar
dc.subject.odspa11 Ciudades y comunidades sostenibles
dc.titleUsing Satellite Images and Deep Learning to Measure Health and Living Standards in India
dc.typeartículo
dc.volumen167
sipa.indexWOS
sipa.trazabilidadWOS;2025-01-12
Files
Collections
Artículos de revistas