Automated production of spatial datasets for land categories from historical maps: Method development and results for a pilot study of Danish late-1800s topographical maps

Gregor Levin, Geoffrey Brian Groom, Stig Roar Svenningsen, Mads Linnet Perner

Publikation: Bog/antologi/afhandling/rapportRapportForskningpeer review


This report records the methods and the results of a pilot project aimed at automatedproduction of machine-readable spatial datasets for land categories from Danishtopographical maps from the late 1800s. The study was undertaken for two studyareas in Jutland, covering around 300 km². Target land categories were: heath, sanddune, wetland, forest and water bodies. The automated geo-data productioncomprised a combination of object based image analysis, vector GIS, coloursegmentation and machine learning processes. Results of an accuracy assessmentindicate accuracies that for most categories are around 90 % or higher. A changeassessment for the period from the late 1800s until today, revealed a dynamiccharacterised by decrease in open habitat types due to cultivation and afforestation.We conclude, that automated production of LULC category digital geo-data fromhistorical maps offers a less time consuming and consequently more resourceefficient alternative to traditional manual vectorisation
ForlagAarhus Universitet, DCE – Nationalt Center for Miljø og Energi
Antal sider124
ISBN (Trykt)978-87-7156-511-9
StatusUdgivet - 2020
Udgivet eksterntJa
NavnScientific Report from DCE


  • landscape change
  • automated production
  • object based image processing
  • Høje Målebordsblade
  • topographical maps
  • Historical maps

Citer dette