全球变化知识资源中心

Mapping urban dynamics at the global scale becomes a pressing task with the increasing pace of urbanization and its important environmental and ecological impacts. In this study, we proposed a new approach to mapping global urban areas from 2000 to 2012 by applying a region-growing support vector machine classifier and a bidirectional Markov random field model to time-series nighttime light data. In this approach, both spectrum and spatial-temporal contextual information are employed for an improved urban area mapping. Our results indicate that at the global level, the urban area increased from 625,000 to 1,039,000 km(2) during 2000-2012. Most urban areas are concentrated in the region between 30 degrees N and 60 degrees N latitudes. The latitudinal distribution of urban areas from this study is consistent with three land-cover products, including European Space Agency Climate Change Initiative Land Cover dataset, Finer Resolution Observation and Monitoring Global Land Cover, and 30-m Global Land Cover dataset. We found that for several major cities, such as Shanghai, urban areas from our study contain some nonurban land-cover types with intensive human activities. The validation using Landsat 7 ETM+ imagery indicates that the overall accuracies of the mapped urban areas for 2000, 2005, 2008, and 2010 are 86.0%, 88.6%, 89.8%, and 88.7%, respectively, and the Kappa coefficients are 0.72, 0.77, 0.79, and 0.78, respectively. This study also demonstrates that the integration of the spatial-temporal contextual information and the use of bidirectional Markov random field model are effective in improving the accuracy and temporal consistency of urban area mapping using time-series nighttime light data.