Quality assurance and assessment framework for large area land cover maps validation in the Copernicus high-resolution hot spot monitoring activity

European Journal of Remote Sensing

Conrad Bielski¹  Andrea Lupi²  Zoltan Szantoi³  Irina Carlan⁴  Petra Miletich⁵  Heinz Gallaun⁵  Willibald Croi⁶  Christian Kowalewski⁶  Helene Augu⁷  Andreas Brink⁸  Gabriel Jaffrain⁸  Anne-Cecile Giroux⁹  Karl Ruf^1,10 

[1] EOXPLORE, Weil am Rhein, German;European Commission, Joint Research Centre, Ispra, Ital;European Commission, Joint Research Centre, Ispra, Ital;Department of Geography and Environmental Studies, Stellenbosch University, Stellenbosch, South Afric;Gisbox, Bucharest Romani;Joanneum Research, Forschungsgesellschaft mbH, Graz, Austri;Luxspace Sàrl, R.C.S., Luxembourg B, Luxembour;Sword Group, Paris, Franc;l’Institut Géographique National (IGN) FI, Paris, Franc;l’Office National des Forêts International, Nogent sur Marne, Franc;space4environment sàrl, Niederanven, Luxembour;

关键词: validation;    map accuracy;    land cover;    key landscape for conservation;    Copernicus;   

DOI  :  10.1080/22797254.2021.1978001

来源: Taylor & Francis

【 摘 要 】

The Copernicus High-Resolution Hot Spot Monitoring activity (C-HSM) delivers a global dataset of Key Landscapes for Conservation (KLC), which are characterized by pronounced anthropogenic pressures that require high mapping accuracy. Detailed land cover and land cover change C-HSM map products are freely available, including map production accuracy assessments, to users and stakeholders in order to understand the map products’ confidence levels. Other similar regional or global land cover products provide limited accuracy assessment, which is a significant drawback for evidence-based decision-making, in particular. Without a complete understanding of the map product quality or quantified confidence levels, usability is reduced and can affect stakeholder decision-making and the implementation of sustainable solutions. To take advantage of very high-resolution imagery, time series of Sentinel-2, and historic satellite archives, we developed web-based temporal trajectory and seasonal matrix viewer tools. For the quantitative accuracy assessment we implemented a stratified random sampling approach, where we placed special emphasis on (i) allocation of sampling units for rare land cover change categories; (ii) effective and accurate labelling of large numbers of sampling units; (iii) accuracy and area estimation in one consistent approach; and (iv) derivation of confidence intervals for all accuracy measures and area estimates. To handle correlations, large uncertainties, and complex probability density functions, bootstrapping was applied instead of analytical equations, which are based on normality assumptions. This paper presents the Quality Assurance and Quality Control framework applied to validate all the C-HSM thematic map products. The Kundelungu-Upemba KLC product results are presented as our use case.

【 授权许可】

CC BY