{"type":"ScholarlyArticle","title":"Time Series of Satellite Imagery Improve Deep Learning Estimates of Neighborhood-Level Poverty in Africa","authors":[{"name":"Markus B. Pettersson","slug":"markus-b-pettersson","given":"Markus B.","family":"Pettersson","affiliation":"Data Science and AI Division , Chalmers University of Technology , Sweden; The AI and Global Development Lab"},{"name":"Mohammad Kakooei","slug":"mohammad-kakooei","given":"Mohammad","family":"Kakooei","affiliation":"Data Science and AI Division , Chalmers University of Technology , Sweden; The AI and Global Development Lab"},{"name":"Julia Ortheden","slug":"julia-ortheden","given":"Julia","family":"Ortheden","affiliation":"Data Science and AI Division , Chalmers University of Technology , Sweden"},{"name":"Fredrik D. Johansson","slug":"fredrik-d-johansson","given":"Fredrik D.","family":"Johansson","affiliation":"Data Science and AI Division , Chalmers University of Technology , Sweden"},{"name":"Adel Daoud","slug":"adel-daoud","given":"Adel","family":"Daoud","affiliation":"Data Science and AI Division , Chalmers University of Technology , Sweden; Institute for Analytical Sociology , Linköping University , Sweden; Center for Advanced Study in the Behavioral Sciences , Stanford University , United States; The AI and Global Development Lab"}],"abstract":"To combat poor health and living conditions, policymakers in Africa require temporally and geographically granular data measuring economic well-being. \r\nMachine learning (ML) offers a promising alternative to expensive and time-consuming survey measurements by training models to predict economic conditions from freely available satellite imagery. However,  previous efforts have failed to utilize the temporal information available in earth observation (EO) data, which may capture developments important to standards of living. In this work, we develop an EO-ML method for inferring neighborhood-level material-asset wealth using multi-temporal imagery and recurrent convolutional neural networks. Our model outperforms state-of-the-art models in several aspects of generalization, explaining  72% of the variance in wealth across held-out countries and 75%  held-out time spans. Using our geographically and temporally aware models, we created spatio-temporal material-asset data maps covering the entire continent of Africa from 1990 to 2019, making our data product the largest dataset of its kind. We showcase these results by analyzing which neighborhoods are likely to escape poverty by the year 2030, which is the deadline for when the Sustainable Development Goals (SDG) are evaluated.","doi":"10.24963/ijcai.2023/684","url":"https://ijcai.org/proceedings/2023/684","pdf":"https://ijcai.org/proceedings/2023/0684.pdf","markdown":"https://ijcai.org/proceedings/2023/684.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/684","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"AI for Good","track":"AI for Good","number":684,"pages":{"first":6165,"last":6173},"keywords":["AI for Good: Computer Vision","AI for Good: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Blumenstock, 2018] Joshua E. Blumenstock. Estimating Economic Characteristics with Phone Data. AEA Papers and Proceedings, 108:72-76, 2018.","title":"Estimating Economic Characteristics with Phone Data","authors":"Joshua E Blumenstock","year":"2018","venue":"AEA Papers and Proceedings","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Burgert et al., 2013] Clara R. Burgert, Josh Colston, Thea Roy, and Blake Zachary. Geographic displacement proce- dure and georeferenced data release policy for the demo- graphic and health surveys. Technical report, ICF Interna- tional, Calverton, Maryland, USA, 2013.","title":"Geographic displacement procedure and georeferenced data release policy for the demographic and health surveys","authors":"Clara R Burgert, Josh Colston, Thea Roy, Blake Zachary","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Burke et al., 2021] Marshall Burke, Anne Driscoll, David B. Lobell, and Stefano Ermon. Using satellite im- agery to understand and promote sustainable development. Science, 371(6535):eabe8628, March 2021.","title":"Using satellite imagery to understand and promote sustainable development","authors":"Marshall Burke, Anne Driscoll, David B Lobell, Stefano Ermon","year":"2021","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chi et al., 2022] Guanghua Chi, Han Fang, Sourav Chatter- jee, and Joshua E. Blumenstock. Microestimates of wealth for all low-and middle-income countries. Proceedings of the National Academy of Sciences, 119(3):e2113658119, January 2022.","title":"Microestimates of wealth for all low-and middle-income countries","authors":"Chi","year":"2022","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Daoud and Dubhashi, 2023] Adel Daoud and Devdatt Dub- hashi. Statistical Modeling: The Three Cultures. Harvard Data Science Review, 5(1), jan 26 2023. https://hdsr.mitpress.mit.edu/pub/uo4hjcx6.","title":"Statistical Modeling: The Three Cultures","authors":"Adel Daoud, Devdatt Dubhashi","year":"2023","venue":"Harvard Data Science Review","doi":null,"url":"https://hdsr.mitpress.mit.edu/pub/uo4hjcx6","internal_url":null},{"position":6,"raw":"[Daoud et al., 2016] Adel Daoud, Björn Halleröd, and De- barati Guha-Sapir. What is the association between ab- solute child poverty, poor governance, and natural disas- ters? a global comparison of some of the realities of cli- mate change. PLOS ONE, 11(4):1-20, 04 2016.","title":"What is the association between absolute child poverty, poor governance, and natural disasters? a global comparison of some of the realities of climate change","authors":"Adel Daoud, Björn Halleröd, Debarati Guha-Sapir","year":"2016","venue":"PLOS ONE","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Daoud et al., 2023] Adel Daoud, Felipe Jordán, Makkunda Sharma, Fredrik Johansson, Devdatt Dubhashi, Sourabh Paul, and Subhashis Banerjee. Using satellite images and deep learning to measure health and living standards in india. Social Indicators Research, Apr 2023.","title":"Using satellite images and deep learning to measure health and living standards in india","authors":"Adel Daoud, Felipe Jordán, Makkunda Sharma, Fredrik Johansson, Devdatt Dubhashi, Sourabh Paul, Subhashis Banerjee","year":"2023","venue":"Social Indicators Research","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Daoud, 2011] Adel Daoud. Scarcity, Abundance, and Suf- ficiency: Contributions to Social and Economic Theory. Gothenburg Studies in Sociology. Gothenburg Studies in Sociology, Department of Sociology & Geson Hyltetryck, Gothenburg, 2011.","title":"Scarcity, Abundance, and Sufficiency: Contributions to Social and Economic Theory","authors":"Adel Daoud","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248-255, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[DHS, 2022] DHS. Demographic and Health Surveys web- site. www.dhsprogram.com, 2022. Accessed: 2022-12-30.","title":"DHS. Demographic and Health Surveys website","authors":null,"year":"2022","venue":null,"doi":null,"url":"www.dhsprogram.com","internal_url":null},{"position":11,"raw":"[Ekbrand, 2019] Hans Ekbrand. DHSharmonisation. https:// bitbucket.org/hansekbrand/dhsharmonisation/, 2019. Ac- cessed: 2022-12-13.","title":"Hans Ekbrand. DHSharmonisation","authors":"Ekbrand","year":"2019","venue":null,"doi":null,"url":"-cessed:2022-12-13","internal_url":null},{"position":12,"raw":"[Elvidge et al., 2017] Christopher D Elvidge, Kimberly Baugh, Mikhail Zhizhin, Feng Chi Hsu, and Tilottama Ghosh. Viirs night-time lights. International Journal of Remote Sensing, 38:5860-5879, 2017.","title":"Viirs night-time lights","authors":"Kimberly Christopher D Elvidge, Mikhail Baugh, Feng Zhizhin, Chi Hsu, Tilottama Ghosh","year":"2017","venue":"International Journal of Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Glorot and Bengio, 2010] Xavier Glorot and Yoshua Ben- gio. Understanding the difficulty of training deep feed- forward neural networks. In Yee Whye Teh and Mike Tit- terington, editors, Proceedings of the Thirteenth Interna- tional Conference on Artificial Intelligence and Statistics, volume 9 of Proceedings of Machine Learning Research, pages 249-256, Chia Laguna Resort, Sardinia, Italy, 13- 15 May 2010. PMLR.","title":"Xavier Glorot and Yoshua Bengio. Understanding the difficulty of training deep feedforward neural networks","authors":"Bengio Glorot","year":"2010","venue":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[González et al., 2016] Jonatan A. González, Francisco J. Rodríguez-Cortés, Ottmar Cronie, and Jorge Mateu. Spatio-temporal point process statistics: A review. Spa- tial Statistics, 18:505-544, November 2016.","title":"Spatio-temporal point process statistics: A review","authors":"Jonatan A González, J Francisco, Ottmar Rodríguez-Cortés, Jorge Cronie, Mateu","year":"2016","venue":"Spatial Statistics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Gorelick et al., 2017] Noel Gorelick, Matt Hancher, Mike Dixon, Simon Ilyushchenko, David Thau, and Rebecca Moore. Google earth engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 202, 2017.","title":"Google earth engine: Planetary-scale geospatial analysis for everyone","authors":"Noel Gorelick, Matt Hancher, Mike Dixon, Simon Ilyushchenko, David Thau, Rebecca Moore","year":"2017","venue":"Remote Sensing of Environment","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Groves and Lyberg, 2010] Robert M. Groves and Lars Ly- berg. Total Survey Error: Past, Present, and Future. Public Opinion Quarterly, 74(5):849-879, January 2010.","title":"Total Survey Error: Past, Present, and Future","authors":"Robert M Groves, Lars Lyberg","year":"2010","venue":"Public Opinion Quarterly","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Halleröd et al., 2013] Björn Halleröd, Bo Rothstein, Adel Daoud, and Shailen Nandy. Bad Governance and Poor Children: A Comparative Analysis of Government Ef- ficiency and Severe Child Deprivation in 68 Low-and Middle-income Countries. World Development, 48(0):19- 31, 2013.","title":"Bad Governance and Poor Children: A Comparative Analysis of Government Efficiency and Severe Child Deprivation in 68 Low-and Middle-income Countries","authors":"Halleröd","year":"2013","venue":"World Development","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Identity mappings in deep residual net- works. In European conference on computer vision, pages 630-645. Springer, 2016.","title":"Identity mappings in deep residual networks","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"European conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Henderson et al., 2012] J. Vernon Henderson, Adam Storeygard, and David N. Weil. Measuring economic growth from outer space. American Economic Review, 102(2):994-1028, April 2012.","title":"Measuring economic growth from outer space","authors":"J Vernon Henderson, Adam Storeygard, David N Weil","year":"2012","venue":"American Economic Review","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Hsu et al., 2015] Feng-Chi Hsu, Kimberly E Baugh, Tilot- tama Ghosh, Mikhail Zhizhin, and Christopher D Elvidge. Dmsp-ols radiance calibrated nighttime lights time se- ries with intercalibration. Remote Sensing, 7:1855-1876, 2015.","title":"Dmsp-ols radiance calibrated nighttime lights time series with intercalibration","authors":"Hsu","year":"2015","venue":"Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Jean et al., 2016] Neal Jean, Marshall Burke, Michael Xie, W. Matthew Davis, David B. Lobell, and Stefano Ermon. Combining satellite imagery and machine learning to pre- dict poverty. Science, 353, 2016.","title":"Combining satellite imagery and machine learning to predict poverty","authors":"Neal Jean, Marshall Burke, Michael Xie, W Matthew Davis, David B Lobell, Stefano Ermon","year":"2016","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Jerzak et al., 2022] Connor T. Jerzak, Fredrik Johansson, and Adel Daoud. Estimating Causal Effects Under Im- age Confounding Bias with an Application to Poverty in Africa. arXiv:2206.06410 [cs.LG], June 2022.","title":"Estimating Causal Effects Under Image Confounding Bias with an Application to Poverty in Africa","authors":"Connor T Jerzak, Fredrik Johansson, Adel Daoud","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Jerzak et al., 2023a] Connor T. Jerzak, Fredrik Johansson, and Adel Daoud. Image-based treatment effect hetero- geneity. Forthcoming in Proceedings of the Second Con- ference on Causal Learning and Reasoning (CLeaR), Pro- ceedings of Machine Learning Research (PMLR), 2023.","title":"Image-based treatment effect heterogeneity","authors":"Jerzak","year":"2023","venue":"Forthcoming in Proceedings of the Second Conference on Causal Learning and Reasoning (CLeaR), Proceedings of Machine Learning Research (PMLR)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Jerzak et al., 2023b] Connor T. Jerzak, Fredrik Johansson, and Adel Daoud. Integrating earth observation data into causal inference: Challenges and opportunities. arXiv:2206.06410 [cs.LG, stat.AP], January 2023.","title":"Integrating earth observation data into causal inference: Challenges and opportunities","authors":"Jerzak","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Kingma and Ba, 2014] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv:1412.6980, 12 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Kino et al., 2021] Shiho Kino, Yu-Tien Hsu, Koichiro Shiba, Yung-Shin Chien, Carol Mita, Ichiro Kawachi, and Adel Daoud. A scoping review on the use of ma- chine learning in research on social determinants of health: Trends and research prospects. SSM -Population Health, 15:100836, September 2021.","title":"A scoping review on the use of machine learning in research on social determinants of health: Trends and research prospects","authors":"Kino","year":"2021","venue":"SSM -Population Health","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Lavrakas, 2008] Paul Lavrakas. Encyclopedia of Survey Research Methods. Sage Publications, Inc., 2455 Teller Road, Thousand Oaks California 91320 United States of America, 2008.","title":"Encyclopedia of Survey Research Methods","authors":"Paul Lavrakas","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Li et al., 2019] Ang Li, Ola Spyra, Sagi Perel, Valentin Dal- ibard, Max Jaderberg, Chenjie Gu, David Budden, Tim Harley, and Pramod Gupta. A generalized framework for population based training. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discov- ery & Data Mining, KDD '19, page 1791-1799, New York, NY, USA, 2019. Association for Computing Ma- chinery. [Mahler et al., 2021]","title":"A generalized framework for population based training","authors":"Ang Li, Ola Spyra, Sagi Perel, Valentin Dalibard, Max Jaderberg, Chenjie Gu, David Budden, Tim Harley, Pramod Gupta","year":"2019","venue":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD '19","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"Daniel Gerszon Mahler, Nishant Yon- zan, Christoph Lakner, R. Andres Castaneda Aguilar, and Haoyu Wu. Updated estimates of the impact of covid-19 on global poverty: Turning the corner on the pandemic in 2021? World Bank Data Blog, 2021.","title":"Updated estimates of the impact of covid-19 on global poverty: Turning the corner on the pandemic in 2021?","authors":"Nishant Daniel Gerszon Mahler, Christoph Yonzan, R Andres Lakner, Haoyu Castaneda Aguilar, Wu","year":"2021","venue":"World Bank Data Blog","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Rolf et al., 2021] Esther Rolf, Jonathan Proctor, Tamma Carleton, Ian Bolliger, Vaishaal Shankar, Miyabi Ishihara, Benjamin Recht, and Solomon Hsiang. A generalizable and accessible approach to machine learning with global satellite imagery. Nature Communications, 12(1):4392, July 2021.","title":"A generalizable and accessible approach to machine learning with global satellite imagery","authors":"Esther Rolf, Jonathan Proctor, Tamma Carleton, Ian Bolliger, Vaishaal Shankar, Miyabi Ishihara, Benjamin Recht, Solomon Hsiang","year":"2021","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Shiba et al., 2022] Koichiro Shiba, Adel Daoud, Hiroyuki Hikichi, Aki Yazawa, Jun Aida, Katsunori Kondo, and Ichiro Kawachi. Uncovering Heterogeneous Associations Between Disaster-Related Trauma and Subsequent Func- tional Limitations: A Machine-Learning Approach. Amer- ican Journal of Epidemiology, page kwac187, October 2022. [Smits and Steendijk, 2015] Jeroen Smits and Roel Steendijk. The international wealth index (iwi). So- cial Indicators Research, 122:65-85, 2015.","title":"Uncovering Heterogeneous Associations Between Disaster-Related Trauma and Subsequent Functional Limitations: A Machine-Learning Approach","authors":"Koichiro Shiba, Adel Daoud, Hiroyuki Hikichi, Aki Yazawa, Jun Aida, Katsunori Kondo, Ichiro Kawachi","year":"2015","venue":"(iwi). Social Indicators Research","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Tatem, 2017] Andrew J. Tatem. Worldpop, open data for spatial demography. Scientific Data, 4(1):170004, Jan 2017.","title":"Worldpop, open data for spatial demography","authors":"Andrew J Tatem","year":"2017","venue":"Scientific Data","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[World Bank, 2022] World Bank. Poverty and inequality platform (version 20220909 2011 02 02 prod). www.pip. worldbank.org, 2022. Accessed on 2022-12-13.","title":"World Bank. Poverty and inequality platform","authors":null,"year":"2022","venue":null,"doi":null,"url":"www.pip.worldbank.org","internal_url":null},{"position":35,"raw":"[Yeh et al., 2020] Christopher Yeh, Anthony Perez, Anne Driscoll, George Azzari, Zhongyi Tang, David Lobell, Ste- fano Ermon, and Marshall Burke. Using publicly avail- able satellite imagery and deep learning to understand eco- nomic well-being in africa. Nature Communications, 11, 2020.","title":"Using publicly available satellite imagery and deep learning to understand economic well-being in africa","authors":"Christopher Yeh, Anthony Perez, Anne Driscoll, George Azzari, Zhongyi Tang, David Lobell, Stefano Ermon, Marshall Burke","year":"2020","venue":"Nature Communications","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}