Assessing vegetation recovery in reclaimed opencast mines of the Teruel coalfield (Spain) using Landsat time series and boosted regression trees.

Opencast mining is an activity that caters to many economic sectors; however, it has a large impact on society and the environment. After mining, the major concern is to restore the previous land cover, which was generally a natural vegetation cover. Establishing permanent vegetation cover can restore landscape connectivity and previous ecosystem functions, enhance aesthetic values and prevent off-side effects associated with post-mining landscapes. Opencast mining reclamation deals with these issues with several strategies that aim to develop a vegetation cover after mining activity has stopped. However, not all reclamation actions are effective, and assessing their efficiency by monitoring vegetation development at reclaimed sites is a time-consuming task because it usually involves extensive field work. In this study, we present a semi-automatic approach based on analysing satellite data (Landsat) time series and using a machine learning technique to identify suitable conditions for vegetation development at reclaimed opencast mines. We analysed the Teruel coalfield (Aragón, central-eastern Spain). This area is a representative Mediterranean-Continental region that is of particular interest due the diversity of reclamation actions that have been applied and the increase in drier conditions during the last decades. Conditions were described with topography derived variables, technical reclamation features and drought-occurrence variables as potential explanatory factors. The implemented approach allowed us to identify the main abiotic filters for vegetation of this geographic region: the water availability and soil retention (both controlled by the topographic slope), and the proximity to seed sources. The analysis evidenced the negative influence of drought occurrence on vegetation development, and different responses were found depending on the timescale at which drought is calculated. Our results indicate that the reclamation landform model is the main key factor influencing vegetation development. A model such as the smooth berm-slope increases water availability and controls soil erosion, and hence, improves vegetation development. In addition, we found that further than 500-600 m from the mine, the effect of seed source declines dramatically. Therefore, all these issues should be considered in future reclamation designs in a Mediterranean-Continental environment. Our methodology could be adapted to other geographic regions where spatial environmental data are available.