Mapping and detection of land use change in a coal mining area using object-based image analysis

Abstract

Object-based image analysis was used to map land use in the Panxie coal mining area, East China, where long-term underground coal mines have been exploited since the 1980s. A rule-based classification approach was developed for a Pleiades image to identify the desired land use classes, and the same rule-based classification strategies, after the threshold values had been modified slightly, were applied to the Landsat series images. Five land use classes were successfully captured with overall accuracies of between 80 and 94%. The classification approach was validated for its flexibility and robustness. Multitemporal classification results indicated that land use changed considerably in the Panxie coal mining area from 1989 to 2013. The urban, coal and coal gangue, and water areas increased rapidly in line with the growth in mine production. Urban areas increased from 9.38 to 20.92% and showed a tendency to increase around the coal mines. From 1989 to 2013 the coal and coal gangue area increased by 40-fold, from 0.02 to 0.58%. Similarly, the water area increased from 2.77 to 7.84% over this time period, mainly attributable to the spread of waterlogged areas. The waterlogged areas increased to about 2900 ha in 2013, which was about 80 times more than their area in 1989. In contrast, the area of cultivated land was negatively related to the increase in mine production and decreased from 73.11 to 57.25%. The results of this study provide a valuable basis for sustainable land management and environmental planning in the Panxie coal mining area.