TY - JOUR
T1 - A census from heaven
T2 - Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments
AU - Georganos, Stefanos
AU - Hafner, Sebastian
AU - Kuffer, Monika
AU - Linard, Catherine
AU - Ban, Yifang
N1 - Funding Information:
The work has been supported by a Digital Futures postdoctoral fellowship grant and a Swedish National Space Agency under Grant dnr 155/15 . We also thank the Belgian Science Policy for allowing us to use the Pleiades imagery of Dakar, in the framework of the REACT STEREO III project. The authors gratefully thank the ASSESS project ( http://assess-sn.org/ ), funded by the ARES-CDD ( https://www.ares-ac.be ), which provided the access to the population data for Dakar. The authors sincerely acknowledge the reviewers for their relevant comments which helped improve this manuscript.
Publisher Copyright:
© 2022 The Author(s)
PY - 2022/11
Y1 - 2022/11
N2 - Urban population distribution maps are vital elements for monitoring the Sustainable Development Goals, appropriately allocating resources such as vaccination campaigns, and facilitating evidence-based decision making. Typically, population distribution maps are derived from census data from the region of interest. Nevertheless, in several low- and middle-income countries, census information may be unreliable, outdated or unsuitable for spatial analysis at the intra-urban level, which poses severe limitations in the development of urban population maps of adequate quality. To address these shortcomings, we deploy a novel framework utilizing multisource Earth Observation (EO) information such as Sentinel-2 and very-high-resolution Pleiades imagery, openly available building footprint datasets, and deep learning (DL) architectures, providing end-to-end solutions to the production of high quality intra-urban population distribution maps in data scarce contexts. Using several case studies in Sub-Saharan Africa, namely Dakar (Senegal), Nairobi (Kenya) and Dar es Salaam (Tanzania), our results emphasize that the combination of DL and EO data is very potent and can successfully capture relationships between the retrieved image features and population counts at fine spatial resolutions (100 meter). Moreover, for the first time, we used state-of-the-art domain adaptation methods to predict population distributions in Dar es Salaam and Nairobi (R2 = 0.39, 0.60) that did not require national census or survey data from Kenya or Tanzania, but only a sample of training locations from Dakar. The DL architecture is based on a modified ResNet-18 model with dual-streams to analyze multi-modal data. Our findings have strong implications for the development of a new generation of urban population products that are an output of end-to-end solutions, can be updated frequently and rely completely on open data.
AB - Urban population distribution maps are vital elements for monitoring the Sustainable Development Goals, appropriately allocating resources such as vaccination campaigns, and facilitating evidence-based decision making. Typically, population distribution maps are derived from census data from the region of interest. Nevertheless, in several low- and middle-income countries, census information may be unreliable, outdated or unsuitable for spatial analysis at the intra-urban level, which poses severe limitations in the development of urban population maps of adequate quality. To address these shortcomings, we deploy a novel framework utilizing multisource Earth Observation (EO) information such as Sentinel-2 and very-high-resolution Pleiades imagery, openly available building footprint datasets, and deep learning (DL) architectures, providing end-to-end solutions to the production of high quality intra-urban population distribution maps in data scarce contexts. Using several case studies in Sub-Saharan Africa, namely Dakar (Senegal), Nairobi (Kenya) and Dar es Salaam (Tanzania), our results emphasize that the combination of DL and EO data is very potent and can successfully capture relationships between the retrieved image features and population counts at fine spatial resolutions (100 meter). Moreover, for the first time, we used state-of-the-art domain adaptation methods to predict population distributions in Dar es Salaam and Nairobi (R2 = 0.39, 0.60) that did not require national census or survey data from Kenya or Tanzania, but only a sample of training locations from Dakar. The DL architecture is based on a modified ResNet-18 model with dual-streams to analyze multi-modal data. Our findings have strong implications for the development of a new generation of urban population products that are an output of end-to-end solutions, can be updated frequently and rely completely on open data.
KW - Deep learning
KW - Domain adaptation
KW - Earth Observation
KW - Global South
KW - Population mapping
KW - Urban sustainability
UR - http://www.scopus.com/inward/record.url?scp=85139229532&partnerID=8YFLogxK
U2 - 10.1016/j.jag.2022.103013
DO - 10.1016/j.jag.2022.103013
M3 - Article
AN - SCOPUS:85139229532
SN - 1569-8432
VL - 114
JO - International Journal of Applied Earth Observation and Geoinformation
JF - International Journal of Applied Earth Observation and Geoinformation
M1 - 103013
ER -