Toward Model-Generated Household Listing in Low- and Middle-Income Countries Using Deep Learning
| Autor: | Justine Allpress, Jennifer Joan Unangst, Kasey Jones, Karol P. Krotki, Rob Chew, Safaa Amer, James Cajka |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
010504 meteorology & atmospheric sciences
Computer science Geography Planning and Development Big data 0211 other engineering and technologies household enumeration lcsh:G1-922 02 engineering and technology 01 natural sciences remote sensing Survey methodology sustainable development goals (SDGs) Earth and Planetary Sciences (miscellaneous) Leverage (statistics) Computers in Earth Sciences Sampling frame 021101 geological & geomatics engineering 0105 earth and related environmental sciences Sustainable development business.industry object detection Environmental economics Object detection machine learning survey statistics Test set business International development lcsh:Geography (General) |
| Zdroj: | ISPRS International Journal of Geo-Information, Vol 7, Iss 11, p 448 (2018) ISPRS International Journal of Geo-Information Volume 7 Issue 11 |
| ISSN: | 2220-9964 |
| DOI: | 10.3390/ijgi7110448 |
| Popis: | 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&rsquo 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of persons or households for sampling, conducting household surveys in LMICs is complicated due to incomplete, outdated, or inaccurate sampling frames.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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|