Publications
Jochem, Warren C.; Bird, Tomas J.; Tatem, Andrew J.
Identifying residential neighbourhood types from settlement points in a machine learning approach Journal Article
In: Computers, Environment and Urban Systems, vol. 69, pp. 104-113, 2018, ISSN: 0198-9715.
Abstract | Links | BibTeX | Tags: Big data, Land use, Machine learning, Point pattern analysis, Texture, Urban morphology
@article{JOCHEM2018104,
title = {Identifying residential neighbourhood types from settlement points in a machine learning approach},
author = {Warren C. Jochem and Tomas J. Bird and Andrew J. Tatem},
url = {https://www.sciencedirect.com/science/article/pii/S0198971517304210},
doi = {https://doi.org/10.1016/j.compenvurbsys.2018.01.004},
issn = {0198-9715},
year = {2018},
date = {2018-01-01},
journal = {Computers, Environment and Urban Systems},
volume = {69},
pages = {104-113},
abstract = {Remote sensing techniques are now commonly applied to map and monitor urban land uses to measure growth and to assist with development and planning. Recent work in this area has highlighted the use of textures and other spatial features that can be measured in very high spatial resolution imagery. Far less attention has been given to using geospatial vector data (i.e. points, lines, polygons) to map land uses. This paper presents an approach to distinguish residential settlement types (regular vs. irregular) using an existing database of settlement points locating structures. Nine data features describing the density, distance, angles, and spacing of the settlement points are calculated at multiple spatial scales. These data are analysed alone and with five common remote sensing measures on elevation, slope, vegetation, and nighttime lights in a supervised machine learning approach to classify land use areas. The method was tested in seven provinces of Afghanistan (Balkh, Helmand, Herat, Kabul, Kandahar, Kunduz, Nangarhar). Overall accuracy ranged from 78% in Kandahar to 90% in Nangarhar. This research demonstrates the potential to accurately map land uses from even the simplest representation of structures.},
keywords = {Big data, Land use, Machine learning, Point pattern analysis, Texture, Urban morphology},
pubstate = {published},
tppubtype = {article}
}
Mertes, C. M.; Schneider, A.; Sulla-Menashe, D.; Tatem, A. J.; Tan, B.
Detecting change in urban areas at continental scales with MODIS data Journal Article
In: Remote Sensing of Environment, vol. 158, pp. 331-347, 2015, ISSN: 0034-4257.
Abstract | Links | BibTeX | Tags: Change detection, Cities, Classification, Data fusion, Decision fusion, Decision trees, Land cover, Machine learning, Urban areas, Urbanization
@article{MERTES2015331,
title = {Detecting change in urban areas at continental scales with MODIS data},
author = {C. M. Mertes and A. Schneider and D. Sulla-Menashe and A. J. Tatem and B. Tan},
url = {https://www.sciencedirect.com/science/article/pii/S003442571400368X},
doi = {https://doi.org/10.1016/j.rse.2014.09.023},
issn = {0034-4257},
year = {2015},
date = {2015-01-01},
journal = {Remote Sensing of Environment},
volume = {158},
pages = {331-347},
abstract = {Urbanization is one of the most important components of global environmental change, yet most of what we know about urban areas is at the local scale. Remote sensing of urban expansion across large areas provides information on the spatial and temporal patterns of growth that are essential for understanding differences in socioeconomic and political factors that spur different forms of development, as well the social, environmental, and climatic impacts that result. However, mapping urban expansion globally is challenging: urban areas have a small footprint compared to other land cover types, their features are small, they are heterogeneous in both material composition and configuration, and the form and rates of new development are often highly variable across locations. Here we demonstrate a methodology for monitoring urban land expansion at continental to global scales using Moderate Resolution Imaging Spectroradiometer (MODIS) data. The new method focuses on resolving the spectral and temporal ambiguities between urban/non-urban land and stable/changed areas by: (1) spatially constraining the study extent to known locations of urban land; (2) integrating multi-temporal data from multiple satellite data sources to classify c. 2010 urban extent; and (3) mapping newly built areas (2000–2010) within the 2010 urban land extent using a multi-temporal composite change detection approach based on MODIS 250m annual maximum enhanced vegetation index (EVI). We test the method in 15 countries in East–Southeast Asia experiencing different rates and manifestations of urban expansion. A two-tiered accuracy assessment shows that the approach characterizes urban change across a variety of socioeconomic/political and ecological/climatic conditions with good accuracy (70–91% overall accuracy by country, 69–89% by biome). The 250m EVI data not only improve the classification results, but are capable of distinguishing between change and no-change areas in urban areas. Over 80% of the error in the change detection can be related to definitional issues or error propagation, rather than algorithm error. As such, these methods hold great potential for routine monitoring of urban change, as well as for providing a consistent and up-to-date dataset on urban extent and expansion for a rapidly evolving region.},
keywords = {Change detection, Cities, Classification, Data fusion, Decision fusion, Decision trees, Land cover, Machine learning, Urban areas, Urbanization},
pubstate = {published},
tppubtype = {article}
}