Toward Model-Generated Household Listing in Low- and Middle-Income Countries Using Deep Learning

While governments, researchers, and NGOs are exploring ways to leverage big data sources for sustainable development, household surveys are still a critical source of information for dozens of the 232 indicators for the Sustainable Development Goals (SDGs) in low- and middle-income countries (LMICs). Though some countries’ statistical agencies maintain databases of persons or households for sampling, conducting household surveys in LMICs is complicated due to incomplete, outdated, or inaccurate sampling frames. As a means to develop or update household listings in LMICs, this paper explores the use of machine learning models to detect and enumerate building structures directly from satellite imagery in the Kaduna state of Nigeria. Specifically, an object detection model was used to identify and locate buildings in satellite images. In the test set, the model attained a mean average precision (mAP) of 0.48 for detecting structures, with relatively higher values in areas with lower building density (mAP = 0.65). Furthermore, when model predictions were compared against recent household listings from fieldwork in Nigeria, the predictions showed high correlation with household coverage (Pearson = 0.70; Spearman = 0.81). With the need to produce comparable, scalable SDG indicators, this case study explores the feasibility and challenges of using object detection models to help develop timely enumerated household lists in LMICs.

[1]  Jonathan Krause,et al.  Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States , 2017, Proceedings of the National Academy of Sciences.

[2]  Dorota Temple,et al.  Unmanned Aircraft Systems Can Improve Survey Data Collection , 2018 .

[3]  Xuefei Hu,et al.  Impervious surface area extraction from IKONOS imagery using an object-based fuzzy method , 2011 .

[4]  P. Biemer.  Total Survey Error: Design, Implementation, and Evaluation , 2010 .

[5]  S. Doocy,et al.  Mortality after the 2003 invasion of Iraq: a cross-sectional cluster sample survey , 2006, The Lancet.

[6]  Yanfei Liu,et al.  SatCNN: satellite image dataset classification using agile convolutional neural networks , 2017 .

[7]  Robert M. Groves,et al.  Total Survey Error: Past, Present, and Future , 2010 .

[8]  Xiaoqiang Lu,et al.  Remote Sensing Image Scene Classification: Benchmark and State of the Art , 2017, Proceedings of the IEEE.

[9]  Sang Michael Xie,et al.  Combining satellite imagery and machine learning to predict poverty , 2016, Science.

[10]  James Cajka,et al.  Geo-sampling in developing nations , 2018, International Journal of Social Research Methodology.

[11]  D. French,et al.  Sustainable Development Goals , 2021, Encyclopedia of the UN Sustainable Development Goals.

[12]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[13]  Liangpei Zhang,et al.  Pre-Trained AlexNet Architecture with Pyramid Pooling and Supervision for High Spatial Resolution Remote Sensing Image Scene Classification , 2017, Remote. Sens..

[14]  Andrew Zisserman,et al.  Microscopy cell counting and detection with fully convolutional regression networks , 2018, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[15]  Rachel Harter,et al.  The CHUM: A frame supplementation procedure for address-based sampling , 2016 .

[16]  Shawn D. Newsam,et al.  Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval , 2016, Remote. Sens..

[17]  Thomas Blaschke,et al.  Ontology-Based Classification of Building Types Detected from Airborne Laser Scanning Data , 2014, Remote. Sens..

[18]  Marco J Haenssgen,et al.  Satellite-aided survey sampling and implementation in low- and middle-income contexts: a low-cost/low-tech alternative , 2015, Emerging Themes in Epidemiology.

[19]  Juan Antonio Álvarez,et al.  Evaluation of deep neural networks for traffic sign detection systems , 2018, Neurocomputing.

[20]  C. Ho,et al.  Implications of Present Land Use Plan on Urban Growth and Environmental Sustainability in a Sub Saharan Africa City , 2017 .

[21]  Kasey Jones,et al.  Residential scene classification for gridded population sampling in developing countries using deep convolutional neural networks on satellite imagery , 2018, International Journal of Health Geographics.

[22]  H. Shannon,et al.  Choosing a survey sample when data on the population are limited: a method using Global Positioning Systems and aerial and satellite photographs , 2012, Emerging Themes in Epidemiology.

[23]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[24]  Gui-Song Xia,et al.  Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery , 2015, Remote. Sens..