Monitoring land cover change in urban and peri-urban areas using dense time stacks of Landsat satellite data and a data mining approach

摘要

Given the pace and scale of urban expansion in many parts of the globe, urban environments are playing an increasingly important role in daily quality-of-life issues, ecological processes, climate, material flows, and land transformations. Remote sensing has emerged as a powerful tool to monitor rates and patterns of urban expansion, but many early challenges - such as distinguishing new urban land from bare ground - remain unsolved. To deal with the high temporal and spatial variability as well as complex, multi-signature classes within settlements, this paper presents a new approach that exploits multi-seasonal information in dense time stacks of Landsat imagery using a multi-date composite change detection technique. The central premise of the approach is that lands withinear urban areas have distinct temporal trajectories both before and after change occurs, and that these lead to characteristic temporal signatures in several spectral regions. The method relies on a supervised classification that exploits training data of stable/changed areas interpreted from Google Earth images, and a 'brute force' approach of providing all available Landsat data as input, including scenes with data gaps due to the Scan Line Corrector (SLC) problem. Three classification algorithms (maximum likelihood, boosted decision trees, and support vector machines) were tested for their ability to monitor expansion across five time periods (1988-1995, 1996-2000, 2001-2003, 2004-2006, 2007-2009) in three study areas that differ in size, eco-climatic conditions, and rates/patterns of development. Both the decision trees and support vector machines outperformed the maximum likelihood classifier (overall accuracy of 90-93%, compared to 65%), but the decision trees were superior at handling missing data. Adding transformed features such as band metrics to the Landsat data stack increased accuracy 1-4%, while experiments with a reduced number of features (designed to mimic noisy or missing data) led to a drop in accuracy of 1-9%. The methodology also proved particularly effective for monitoring peri-urbanization outside the urban core, capturing > 98% of village settlements.