Residential scene classification for gridded population sampling in developing countries using deep convolutional neural networks on satellite imagery

Autor: Safaa Amer, Rob Chew, Justine Allpress, Jennifer Joan Unangst, James Cajka, Kasey Jones, Mark Bruhn
Rok vydání: 2018
Předmět:
Satellite Imagery
Geospatial analysis
Geographic information system
010504 meteorology & atmospheric sciences
General Computer Science
Computer science
0211 other engineering and technologies
Nigeria
02 engineering and technology
lcsh:Computer applications to medicine. Medical informatics
computer.software_genre
01 natural sciences
Clustering
Residence Characteristics
Machine learning
Humans
Cluster analysis
Developing Countries
Sampling frame
Demography
021101 geological & geomatics engineering
0105 earth and related environmental sciences
Data collection
Scene classification
business.industry
Data Collection
Deep learning
Methodology
Public Health
Environmental and Occupational Health
Sampling (statistics)
Remote sensing
GIS
Guatemala
General Business
Management and Accounting
Complex sample design
Visual inspection
Probability based
lcsh:R858-859.7
Neural Networks
Computer
Artificial intelligence
Data mining
business
computer
Zdroj: International Journal of Health Geographics
International Journal of Health Geographics, Vol 17, Iss 1, Pp 1-17 (2018)
ISSN: 1476-072X
DOI: 10.1186/s12942-018-0132-1
Popis: Background Conducting surveys in low- and middle-income countries is often challenging because many areas lack a complete sampling frame, have outdated census information, or have limited data available for designing and selecting a representative sample. Geosampling is a probability-based, gridded population sampling method that addresses some of these issues by using geographic information system (GIS) tools to create logistically manageable area units for sampling. GIS grid cells are overlaid to partition a country’s existing administrative boundaries into area units that vary in size from 50 m × 50 m to 150 m × 150 m. To avoid sending interviewers to unoccupied areas, researchers manually classify grid cells as “residential” or “nonresidential” through visual inspection of aerial images. “Nonresidential” units are then excluded from sampling and data collection. This process of manually classifying sampling units has drawbacks since it is labor intensive, prone to human error, and creates the need for simplifying assumptions during calculation of design-based sampling weights. In this paper, we discuss the development of a deep learning classification model to predict whether aerial images are residential or nonresidential, thus reducing manual labor and eliminating the need for simplifying assumptions. Results On our test sets, the model performs comparable to a human-level baseline in both Nigeria (94.5% accuracy) and Guatemala (96.4% accuracy), and outperforms baseline machine learning models trained on crowdsourced or remote-sensed geospatial features. Additionally, our findings suggest that this approach can work well in new areas with relatively modest amounts of training data. Conclusions Gridded population sampling methods like geosampling are becoming increasingly popular in countries with outdated or inaccurate census data because of their timeliness, flexibility, and cost. Using deep learning models directly on satellite images, we provide a novel method for sample frame construction that identifies residential gridded aerial units. In cases where manual classification of satellite images is used to (1) correct for errors in gridded population data sets or (2) classify grids where population estimates are unavailable, this methodology can help reduce annotation burden with comparable quality to human analysts.
Databáze: OpenAIRE
Externí odkaz: