
Data Categories:Imagery & Land Cover
Data Source:University of Minnesota
Update Fequency:None Planned
Date Acquired:7/1/2018
Data Available:Yes
Metadata Available:Yes
Tags:impervious surfaces, Land Cover, LiDAR, remote sensing, satellites
This data layer is the 2013 UMN Land Cover and impervious surface classification. It was developed by the University of Minnesota using Landsat 8 data and Lidardata with object-based image analysis. Object-based analysis allowed for improved classification over pixel-based classification by incorporating spatial and contextual information of objects, such as shape, size, and texture. The impervious surface classification of identified urban and developed land cover classes was determined with a model relating Landsat greenness to percent impervious. Land cover data provides valuable information on the distribution of different types of vegetation, agricultural activities, water, and human development. The patterns of these distributions and the changes that can be tracked by comparing different time periods, can provide guidance to natural resource managers and planners.