Abstract

An ArcGIS tool for comparing and validating land cover products
Track: Environmental Management
Authors: Nasser Alsaaran

Land cover data is required for a wide range of applications in many scientific disciplines. Many remote sensing-based land cover products at the global, continental, regional and national scales have been produced using different remotely-sensed data, classification systems, spatial resolution, and classification algorithms. Their accuracies are usually quite different and need to be evaluated before using them in land surface modeling and other applications. The objective of this paper is to develop an ArcGIS-based script tool for comparing and validating land cover products. The tool prepares the data for validation by reclassifing the different products and the reference data to a common classification legend, clipping data to the desired extent, resampling the rasters to the same pixel size and aligning their pixels. Then it performs areal and per-pixel comparisons and validations including overall accuracy, Kappa statistics and individual class accuracy for the different land cover products.