Combining satellite imagery and machine learning to predict poverty
Abstract
Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries--Nigeria, Tanzania, Uganda, Malawi, and Rwanda--we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Differences between urban and rural subpopulations have been well-documented.
“Differences between urban and rural subpopulations have also been well-documented (Jean et al., 2016; Yeh et al., 2020).”
From WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020) · cites this paper as Jean et al., 2016
The PovertyMap-wilds results corroborate performance drops seen in previous out-of-country generalization tests for poverty prediction from satellite imagery.
“These results corroborate performance drops seen in previous out-of-country generalization tests for poverty prediction from satellite imagery (Jean et al., 2016).”
From WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020) · cites this paper as Jean et al., 2016
The R2 values in Table 2 are generally slightly lower than ranges reported in previous studies.
“Compared to previous studies of economic activity and nightlights, 𝑅 2 in Table 2 are in general slightly lower than ranges in previous studies [7, 15, 18, 29].”
From Under the Radar -- Auditing Fairness in ML for Humanitarian Mapping (2021) · cites this paper as [15]
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · see citing works
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · see citing works
Measuring Economic Growth from Outer Space
Henderson, J. V., Storeygard, A., & Weil, D. N. (2012) · American Economic Review · doi:10.1257/aer.102.2.994 · Cited by 2,596 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
The role of artificial intelligence in achieving the Sustainable Development Goals
Vinuesa, R., Azizpour, H., Leite, I., Balaam, M., Dignum, V., Domisch, S., Felländer, A., Langhans, S. D., Tegmark, M., & Fuso Nerini, F. (2020) · Nature Communications · doi:10.1038/s41467-019-14108-y · Cited by 3,294 · see citing works
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676 · see citing works
Self-citationMachine Learning: An Applied Econometric Approach
Mullainathan, S., & Spiess, J. (2017) · Journal of Economic Perspectives · doi:10.1257/jep.31.2.87 · Cited by 1,989 · see citing works
A future for the world's children? A WHO–UNICEF–Lancet Commission
Clark, H., Coll-Seck, A. M., Banerjee, A., Peterson, S., Dalglish, S. L., Ameratunga, S., Balabanova, D., Bhan, M. K., Bhutta, Z. A., Borrazzo, J., et al. (2020) · The Lancet · doi:10.1016/s0140-6736(19)32540-1 · Cited by 1,105 · see citing works
Gebru, T., Krause, J., Wang, Y., Chen, D., Deng, J., Aiden, E. L., & Fei-Fei, L. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1700035114 · Cited by 518 · see citing works
Farming and the geography of nutrient production for human use: a transdisciplinary analysis
Herrero, M., Thornton, P. K., Power, B., Bogard, J. R., Remans, R., Fritz, S., Gerber, J. S., Nelson, G., See, L., Waha, K., et al. (2017) · The Lancet Planetary Health · doi:10.1016/s2542-5196(17)30007-4 · Cited by 455 · see citing works
Yu, J., Wang, Z., Majumdar, A., & Rajagopal, R. (2018) · Joule · doi:10.1016/j.joule.2018.11.021 · Cited by 362 · see citing works
SatMAE: Pre-Training Transformers for Temporal and Multi-Spectral Satellite Imagery
Cong, Y., Khanna, S., Meng, C., Liu, P., Rozi, E., He, Y., Burke, M., Lobell, D., & Ermon, S. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-0015 · Cited by 303 · see citing works
Self-citationMartin-Shields, C. P., & Stojetz, W. (2019) · World Development · doi:10.1016/j.worlddev.2018.07.011 · Cited by 302 · see citing works
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Koh, P. W., Sagawa, S., Marklund, H., Xie, S. M., Zhang, M., Balsubramani, A., Hu, W., Yasunaga, M., Phillips, R. L., Gao, I., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.07421 · Cited by 518 · see citing works
“…efforts in applications such as tracking deforestation (Hansen et al., 2013), population density mapping (Tiecke et al., 2017), poverty mapping (Abelson et al., 2014; Jean et al., 2016), crop yield prediction (Wang et al., 2020), and other economic tracking applications (Katona et al., 2018).”
InfluentialSelf-citationNighttime lights as a proxy for human development at the local level
Bruederle, A., & Hodler, R. (2018) · PLOS ONE · doi:10.1371/journal.pone.0202231 · Cited by 259 · see citing works
Armed conflict and child mortality in Africa: a geospatial analysis
Wagner, Z., Heft-Neal, S., Bhutta, Z. A., Black, R. E., Burke, M., & Bendavid, E. (2018) · The Lancet · doi:10.1016/s0140-6736(18)31437-5 · Cited by 200 · see citing works
Self-citationUpscaling urban data science for global climate solutions
Creutzig, F., Lohrey, S., Bai, X., Baklanov, A., Dawson, R., Dhakal, S., Lamb, W. F., McPhearson, T., Minx, J., Munoz, E., et al. (2019) · Global Sustainability · doi:10.1017/sus.2018.16 · Cited by 137 · see citing works
Blumenstock, J. E. (2016) · Science · doi:10.1126/science.aah5217 · Cited by 131 · see citing works
Human and artificial cognition
Siemens, G., Marmolejo-Ramos, F., Gabriel, F., Medeiros, K., Marrone, R., Joksimovic, S., & de Laat, M. (2022) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2022.100107 · Cited by 133 · see citing works
Computational sustainability: computing for a better world and a sustainable future
Gomes, C., Dietterich, T., Barrett, C., Conrad, J., Dilkina, B., Ermon, S., Fang, F., Farnsworth, A., Fern, A., Fern, X., et al. (2019) · Communications of the ACM · doi:10.1145/3339399 · Cited by 126 · see citing works
Self-citationThe Tyranny of Data? The Bright and Dark Sides of Data-Driven Decision-Making for Social Good
Lepri, B., Staiano, J., Sangokoya, D., Letouzé, E., & Oliver, N. (2017) · Studies in Big Data · doi:10.1007/978-3-319-54024-5_1 · Cited by 111 · see citing works
Rechkemmer, A., & Yin, M. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501967 · Cited by 97 · see citing works
Lyu, H., Lu, H., Mou, L., Li, W., Wright, J., Li, X., Li, X., Zhu, X., Wang, J., Yu, L., et al. (2018) · Remote Sensing · doi:10.3390/rs10030471 · Cited by 70 · see citing works
Don't forget people in the use of big data for development
Blumenstock, J. (2018) · Nature · doi:10.1038/d41586-018-06215-5 · Cited by 60 · see citing works
Using Spatial Reinforcement Learning to Build Forest Wildfire Dynamics Models From Satellite Images
Ganapathi Subramanian, S., & Crowley, M. (2018) · Frontiers in ICT · doi:10.3389/fict.2018.00006 · Cited by 56 · see citing works
Rana, P., & Miller, D. C. (2019) · Environmental Research Letters · doi:10.1088/1748-9326/aafa8f · Cited by 41 · see citing works
Machine Learning from Schools about Energy Efficiency
Burlig, F., Knittel, C., Rapson, D., Reguant, M., & Wolfram, C. (2017) · doi:10.3386/w23908 · Cited by 39 · see citing works
Predictive analytics approach to evaluate wage inequality in engineering organizations
Jafari, A., Rouhanizadeh, B., Kermanshachi, S., & Murrieum, M. (2020) · Journal of Management in Engineering · doi:10.1061/(asce)me.1943-5479.0000841 · Cited by 24 · see citing works
Predicting and explaining with machine learning models: Social science as a touchstone
Buchholz, O., & Grote, T. (2023) · Studies in History and Philosophy of Science · doi:10.1016/j.shpsa.2023.10.004 · Cited by 15 · see citing works
1.5 Degrees of Separation: Computer Science Education in the Age of the Anthropocene
Pollock, I., Alshaigy, B., Bradley, A., Krogstie, B. R., Kumar, V., Ott, L., Peters, A.-K., Riedesel, C., & Wallace, C. (2019) · Proceedings of the Working Group Reports on Innovation and Technology in Computer Science Education · doi:10.1145/3344429.3372500 · Cited by 10 · see citing works
Infrastructure Resilience for Climate Adaptation
Gupta, A., Robinson, C., & Dilkina, B. (2018) · Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies · doi:10.1145/3209811.3209859 · Cited by 6 · see citing works
Under the Radar -- Auditing Fairness in ML for Humanitarian Mapping
Kondmann, L., & Zhu, X. X. (2021) · arXiv · doi:10.48550/arxiv.2108.02137 · Cited by 3 · see citing works
Water Stress and Migration in Asia
Wrathall, D. J., & Van Den Hoek, J. (2022) · International Handbooks of Population · doi:10.1007/978-3-030-76433-3_9 · Cited by 1 · see citing works
- Authors
- Jean, N., Burke, M., Xie, M., Davis, W. M., Lobell, D. B., & Ermon, S.
- Affiliations
- Stanford University (US)
- National Bureau of Economic Research (US)
- Department of Computer Science, Stanford University, Stanford, CA, USA.
- Corresponding author
- Jean, Neal
- Burke, Marshall
- Venue
- Science
- Published
- 2016-08-19
- Volume
- 353
- Issue
- 6301
- Pages
- 790-794
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W2513506629
- Cited by
- 1,664
- References
- 5
- Citations by year
- 2026: 146 · 2025: 176 · 2024: 171 · 2023: 170 · 2022: 186 · 2021: 227 · 2020: 232 · 2019: 171 · 2018: 110 · 2017: 72 · 2016: 2 · 2015: 1
- FWCI
- 87.53
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Science (publishedVersion)
- PubMed (publishedVersion)
- Funders
- NSF (1522054)
- Topics
- Physical Sciences › Environmental Science › Global and Planetary Change › Impact of Light on Environment and Health
- Social Sciences › Sociology and Political Science › Income, Poverty, and Inequality
- Physical Sciences › Environmental Science › Ecology › Remote Sensing in Agriculture
- Keywords
- poverty prediction, consumer spending, asset wealth, satellite imagery, convolutional neural networks, economic livelihoods, poverty targeting, limited training data
- MeSH terms
- Machine Learning, Developing Countries, Humans, Income, Malawi, Nigeria, Poverty, Rwanda, Tanzania, Uganda, Satellite Imagery
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
