In order to investigate "ghost cities", we proposed a feasible framework by utilizing multi-source remote sensing datasets, including nighttime light imagery, land cover type products and population grid.
Explanatory variables included classical terrain factors (elevation, slope, curvature plan and profile, wetness index, etc)., various channels and combinations of channels from LANDSAT ETM imagery, land cover and lithology maps.
We used high-resolution aerial imagery, land cover data, and well point data to quantify shale gas development across four time periods (2010, 2012, 2014, 2016), including: the number of wells permitted, drilled, and producing gas (a measure of pipeline development); land use change; and forest fragmentation on both private and public land.
This population map was developed from a combination of Radarsat-1 and Landsat Enhanced Thematic Mapper satellite imagery, land cover maps and the distributions of populations in over 40,000 census enumeration polygons.
Ranjeet John (RJ) is a Research Associate at the Center for Global Change & Earth Observations, Michigan State University, whose expertise includes technical remote sensing imagery analysis, land use and land cover change, and its ecological implications.
A library of 308 models is trained using 77 machine learning methods and four datasets containing either a combination of topographic variables, satellite imagery, soil properties and land use information or principal components based on these variables.
We inventoried the total pteridophyte diversity in 82 forest patches of the Hochelaga Archipelago (Montréal area, Québec, Canada), and evaluated their level of integrity using landscape metrics (e.g., area, connectivity, matrix composition) calculated from satellite imagery and land use maps.
This map was constructed from a combination of satellite imagery and land cover maps which were used to develop models that identified the location of settlements [ 48, 49].
The United States Department of Agriculture's Cropland Data Layer (CDL), an annual satellite imagery-derived land cover map, has been increasingly used for this application since complete coverage of the conterminous United States became available in 2008.
A cloud environment can provide a decision-making platform at the PaaS layer that can compile non-spatial, spatial and temporal data from various sources in an urban environment (e.g. hard sources: data coordinates, signal frequency and location, video, imagery, buildings, land-use, event occurrence, socio-economic, demographic etc. and soft sources: social-networks on web, etc).
However, Elaalem et al. (2013) applied supervised classification using SPOT 5 imagery for evaluating land cover/land use in the north-west region of the Jeffara Plain.
