Assessing spatially explicit long-term landscape dynamics based on automated production of land category layers from Danish late nineteenth-century topographic maps in comparison with contemporary maps

Historical topographical maps containvaluable, spatially and thematically detailed informa-tion about past landscapes. Yet, for analyses of land-scape dynamics through geographical informationsystems, it is necessary to “unlock” this informationvia map processing. For two study areas in northernand central Jutland, Denmark, we apply object-basedimage analysis, vector GIS, colour image segmen-tation, and machine learning processes to producemachine-readable layers for the land use and landcover categories forest, wetland, heath, dune sand,and water bodies from topographic maps from thelate nineteenth century. Obtained overall accuracywas 92.3%. A comparison with a contemporarymap revealed spatially explicit landscape dynamics