Building up user confidence for the spaceborne derived global and continental land cover products for the Mediterranean region: the case of Thessaly

TL;DR

This study evaluates and compares global and continental land cover products for the Mediterranean, using accuracy measures and confidence levels to enhance user trust in these spaceborne data products.

Contribution

It introduces a systematic accuracy assessment and confidence-based validation framework for land cover products, improving credibility and comparability.

Findings

Minimum weighted overall accuracy of 84% for the products

Performance deviations identified for specific land cover classes

Confidence levels enhance validation objectivity

Abstract

Across globe and space agencies nations recognize the importance of homogenized land cover information, prone to regular updates, both in the context of thematic and spatial resolutions. Recent sensor advances and the free distribution policy promote the utilization of spaceborne products in an unprecedented pace into an increasingly wider range of applications. Ensuring credibility to the users is a major enabler in this process. To this end this study contributes with a systematic accuracy performance measurement and continental/global land cover layers' inter-comparison moving towards confidence built up. Confidence levels during validation and a weighted overall accuracy assessment were applied. Google Earth imagery was employed to assess the accuracy of three land cover products, i.e., Globeland30, HRLs and CLC 2012, for the years 2010 and 2012. Reported rates indicate a minimum weighted overall accuracy of 84%. Specific classes' performance deviations from the general trend were noted and discussed on the basis of an unbiased sampling approach. By integrating confidence levels during the ground truth annotation, stratified sampling on the several Corine Level 3 subclasses and the weighted overall accuracy assessment, the different aspects of the considered land cover products can be highlighted more objectively.