Spatially Stratified and Multi-Stage Approach for National Land Cover Mapping Based on Sentinel-2 Data and Expert Knowledge

• Published in: Remote sensing (Basel, Switzerland) Vol. 14; no. 8; p. 1865
• Main Authors: Costa, Hugo, Benevides, Pedro, Moreira, Francisco D., Moraes, Daniel, Caetano, Mário
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2022
• Subjects: Accuracy; Classification; Confidence intervals; COSsim; Data analysis; Forestry; Land cover; land cover land use; Land use; machine learning; Mapping; multi-temporal; Plant species; Product development; random forest; Regions; Remote sensing; satellite image; Task complexity; Greece; Portugal; Europe; Spain
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs14081865

Portugal is building a land cover monitoring system to deliver land cover products annually for its mainland territory. This paper presents the methodology developed to produce a prototype relative to 2018 as the first land cover map of the future annual map series (COSsim). A total of thirteen land cover classes are represented, including the most important tree species in Portugal. The mapping approach developed includes two levels of spatial stratification based on landscape dynamics. Strata are analysed independently at the higher level, while nested sublevels can share data and procedures. Multiple stages of analysis are implemented in which subsequent stages improve the outputs of precedent stages. The goal is to adjust mapping to the local landscape and tackle specific problems or divide complex mapping tasks in several parts. Supervised classification of Sentinel-2 time series and post-classification analysis with expert knowledge were performed throughout four stages. The overall accuracy of the map is estimated at 81.3% (±2.1) at the 95% confidence level. Higher thematic accuracy was achieved in southern Portugal, and expert knowledge significantly improved the quality of the map.