Using Satellite Images and Deep Learning to Measure Health and Living Standards in India
Artikel i vetenskaplig tidskrift, 2023

Using 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.

Measurement of health and living conditions

Deep learning

Satellite images

Indicators

Census

Survey

India

Författare

Adel Daoud

Göteborgs universitet

Linköpings universitet

Felipe Jordán

Pontificia Universidad Catolica de Chile

Makkunda Sharma

Indian Institute of Technology Delhi

Wadhwani AI

Fredrik Johansson

Chalmers, Data- och informationsteknik, Data Science och AI

Devdatt Dubhashi

Chalmers, Data- och informationsteknik, Data Science och AI

Sourabh Paul

Indian Institute of Technology Delhi

Subhashis Banerjee

Ashoka University

Indian Institute of Technology Delhi

Social Indicators Research

0303-8300 (ISSN) 1573-0921 (eISSN)

Vol. 167 1-3 475-505

Ämneskategorier

Annan data- och informationsvetenskap

Bioinformatik (beräkningsbiologi)

Datorseende och robotik (autonoma system)

Folkhälsovetenskap, global hälsa, socialmedicin och epidemiologi

DOI

10.1007/s11205-023-03112-x

Mer information

Senast uppdaterat

2024-03-07