Quantification of annual settlement growth in rural mining areas using machine learning
Dietler, Dominik LU
; Farnham, Andrea
; de Hoogh, Kees
and Winkler, Mirko S.
(2020)
In Remote Sensing
12(2).
p.1-14
- Abstract
Studies on annual settlement growth have mainly focused on larger cities or incorporated data rarely available in, or applicable to, sparsely populated areas in sub-Saharan Africa, such as aerial photography or night-time light data. The aim of the present study is to quantify settlement growth in rural communities in Burkina Faso affected by industrial mining, which often experience substantial in-migration. A multi-annual training dataset was created using historic Google Earth imagery. Support vector machine classifiers were fitted on Landsat scenes to produce annual land use classification maps. Post-classification steps included visual quality assessments, majority voting of scenes of the same year and temporal consistency... (More)
Studies on annual settlement growth have mainly focused on larger cities or incorporated data rarely available in, or applicable to, sparsely populated areas in sub-Saharan Africa, such as aerial photography or night-time light data. The aim of the present study is to quantify settlement growth in rural communities in Burkina Faso affected by industrial mining, which often experience substantial in-migration. A multi-annual training dataset was created using historic Google Earth imagery. Support vector machine classifiers were fitted on Landsat scenes to produce annual land use classification maps. Post-classification steps included visual quality assessments, majority voting of scenes of the same year and temporal consistency correction. Overall accuracy in the four studied scenes ranged between 58.5% and 95.1%. Arid conditions and limited availability of Google Earth imagery negatively affected classification accuracy. Humid study sites, where training data could be generated in proximity to the areas of interest, showed the highest classification accuracies. Overall, by relying solely on freely and globally available imagery, the proposed methodology is a promising approach for tracking fast-paced population dynamics in rural areas where population data is scarce. With the growing availability of longitudinal high-resolution imagery, including data from the Sentinel satellites, the potential applications of the methodology presented will further increase in the future.
(Less)
- author
- Dietler, Dominik
LU
; Farnham, Andrea
; de Hoogh, Kees
and Winkler, Mirko S.
- publishing date
- 2020-01-01
- type
- Contribution to journal
- publication status
- published
- keywords
- Google Earth, Land use classification, Landsat, Machine learning, Migration, Mining, Remote sensing, Rural settlement
- in
- Remote Sensing
- volume
- 12
- issue
- 2
- article number
- 235
- pages
- 1 - 14
- publisher
- MDPI AG
- external identifiers
-
- scopus:85081079403
- ISSN
- 2072-4292
- DOI
- 10.3390/rs12020235
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2020 by the authors.
- id
- 0370f9c7-fdad-4301-a205-a2790b72d762
- date added to LUP
- 2023-10-12 12:16:04
- date last changed
- 2023-10-12 12:56:26
@article{0370f9c7-fdad-4301-a205-a2790b72d762,
abstract = {{<p>Studies on annual settlement growth have mainly focused on larger cities or incorporated data rarely available in, or applicable to, sparsely populated areas in sub-Saharan Africa, such as aerial photography or night-time light data. The aim of the present study is to quantify settlement growth in rural communities in Burkina Faso affected by industrial mining, which often experience substantial in-migration. A multi-annual training dataset was created using historic Google Earth imagery. Support vector machine classifiers were fitted on Landsat scenes to produce annual land use classification maps. Post-classification steps included visual quality assessments, majority voting of scenes of the same year and temporal consistency correction. Overall accuracy in the four studied scenes ranged between 58.5% and 95.1%. Arid conditions and limited availability of Google Earth imagery negatively affected classification accuracy. Humid study sites, where training data could be generated in proximity to the areas of interest, showed the highest classification accuracies. Overall, by relying solely on freely and globally available imagery, the proposed methodology is a promising approach for tracking fast-paced population dynamics in rural areas where population data is scarce. With the growing availability of longitudinal high-resolution imagery, including data from the Sentinel satellites, the potential applications of the methodology presented will further increase in the future.</p>}},
author = {{Dietler, Dominik and Farnham, Andrea and de Hoogh, Kees and Winkler, Mirko S.}},
issn = {{2072-4292}},
keywords = {{Google Earth; Land use classification; Landsat; Machine learning; Migration; Mining; Remote sensing; Rural settlement}},
language = {{eng}},
month = {{01}},
number = {{2}},
pages = {{1--14}},
publisher = {{MDPI AG}},
series = {{Remote Sensing}},
title = {{Quantification of annual settlement growth in rural mining areas using machine learning}},
url = {{http://dx.doi.org/10.3390/rs12020235}},
doi = {{10.3390/rs12020235}},
volume = {{12}},
year = {{2020}},
}