Land cover monitoring using remotely sensed data requires robust classification methods which allow for the accurate mapping of complex land cover and land use categories. Random forest (RF) is a powerful machine learning classifier that is relatively unknown in land remote sensing and has not been evaluated thoroughly by the remote sensing community compared to more conventional pattern recognition techniques. Key advantages of RF include: their non-parametric nature; high classification accuracy; and capability to determine variable importance.

This study compares the ASTER Global DEM version 1 (GDEMv1) and version 2 (GDEMv2) for two study sites with distinct terrain and land cover characteristics in western Africa. The effects of land cover, slope, relief, and stack number are evaluated through both absolute and relative DEM statistical comparisons. While GDEMv2 at times performed better than GDEMv1, this improvement was not consistent, revealing the complex nature and interaction of terrain and land cover characteristics, which influences the accuracy of GDEM tiles on local and regional scales.

Quantifying and mapping ecosystem services (ES), their indicators and their relationships is of crucial importance for environmental management. In this article, we analyze the spatial distribution of multiple-ES indicators at three locations on the pioneer fronts of the Brazilian Amazon. We identify trade-offs and synergies between six ES indicators for soil, vegetation and biodiversity characterization.

In a closed landfill, we investigated the diversity and ecological characters of carabid beetles to understand the ecological importance of closed landfills that have the potential as a multi-functional habitat for improving biodiversity in urbanized areas. In addition, we studied the influence of environmental factors (vegetation structure, soil) on distribution and diversity of carabid beetles. A total of 92,495 individuals representing 15 carabid species were collected from the closed landfill.

Because most land-cover types have distinct seasonal changes and corresponding reflectance characteristics in remotely sensed images, the signatures in time-series data are useful for discriminating different land covers. Although temporal signatures have been used to classify different land-cover types, they have not been fully exploited to classify specific crops, and the influence of low resolution should be evaluated.

We evaluated the response of male Reeves's pheasants Syrmaticus reevesii to different forest edges in a fragmented forest landscape in central China using radio-telemetry. Our fieldwork was carried out from April 2000 to August 2003 in the Dongzhai National Nature Reserve within the Dabie Mountains, China. We identified four major types of forest edges: shrub, farmland, road and residential edge.

Arctic ecosystems at the forest-tundra ecotone are particularly sensitive to climate-driven vegetation changes. Many recent studies have observed shifts in vegetation cover, particularly an increase in shrub growth. Here, vegetation changes were assessed at the local scale near Umiujaq, northern Quebec (Canada, 56.55°N, 76.55°W) using colour aerial photographs (1994 and 2010). By applying semi-automated image classification methods and change-detection analysis, we were able to detect and map the dominant vegetation cover changes.

Context Coyotes (Canis latrans) have adapted successfully to human landscape alteration in the past 150 years and in recent decades have successfully moved into urban areas. While this causes concern about human–wildlife conflicts, research also suggests that coyotes tend to avoid humans and human activity in urban areas. For improving management, a better understanding of space use by coyotes is needed. Aims To study how coyote social behaviour influences fine-scale space use in urban areas we present results from an extensive, multi-year GPS telemetry study (2005–13).

Increasing land utilization through diverse forms of human activities, such as agriculture, forestry, urban growth, and industrial development, has led to negative impacts on the water quality of rivers. To find out how catchment attributes, such as land use, hydrologic soil groups, and lithology, can affect water quality variables (Ca²⁺, Mg²⁺, Na⁺, Cl⁻, HCO₃⁻, pH, TDS, EC, SAR), a spatio-statistical approach was applied to 23 catchments in southern basins of the Caspian Sea.

Spatially distributed air temperature is desired for various scientific studies, including climatalogical, hydrological, agricultural, environmental and ecological studies. In this study, empirical models with regard to land cover and spatial scale were introduced and compared to estimate air temperature from satellite-derived land surface temperature and other environmental parameters. Aqua MODIS (Moderate Resolution Imaging Spectroradiometer) data and meteorological data obtained throughout 2005 in the Yangtze River Delta were adopted to develop statistical algorithms of air temperature.

The Kalahari ecosystem is characterized by natural resource conflicts and land-use pressure resulting from intensification of human activities. This paper addresses three issues of concern associated with the Kalahari ecosystem resource management: (i) the major land-use/land cover shifts in the Kalahari ecosystem since 1970 and the resulting pattern in vegetation species composition, cover and density; (ii) the possible explanations for the observed shifts; and (iii) the possible resource conflicts likely to arise.