The Machines Reading Maps project is pleased to announce a new one-year collaboration with the David Rumsey Map Collection, supported by The Alan Turing Institute.
This research will make the Rumsey Map Collection the first in the world to be fully searchable via the maps’ text.
The donation from David Rumsey will allow members of the Machines Reading Maps team to use the diverse, global collection of 60,000 digitised historical maps to expand the project’s tools and methods.
Countless features that were not previously recorded in a map’s library record will now be discoverable. Enriching a map’s text will also enable, for the first time, complex searches across groups of maps: for example, users could search for all the saloons in nineteenth-century California or businesses within two miles of British railway stations.
Working with the Rumsey Collection will refine the project’s tools, making them more flexible in new cartographic and linguistic contexts. The research will generate an unprecedented amount of free and reusable data, of great historical, geographical, and scientific value. It will also produce precious metadata that will improve the accessibility of the collection. By extending the collection’s online map viewer, Luna, with a public annotation interface, the collaboration supports active engagement with map enthusiasts.
Professor Mark Girolami, Chief Scientist of The Alan Turing Institute, said “David Rumsey’s support for this research demonstrates the advantages of interdisciplinary research between humanities researchers, heritage professionals, and scientists.
“The huge amount of open data that this collaboration will create offers the Turing a new opportunity to enhance research across many different disciplines.”
Dr Katie McDonough, Senior Research Associate at The Alan Turing Institute, said: “Working together with Yao-Yi Chiang at the University of Minnesota has unlocked the possibility of developing cutting-edge technologies for exploring the growing world of digitised maps.
“Our future goals for the project include bringing together the machine learning pipeline mapKurator with methods for analysing visual signals on large collections of maps developed in the Living with Machines project at the Turing (MapReader).”
This collaboration builds on ongoing Arts and Humanities Research Council (AHRC) and National Endowment for the Humanities (NEH) funded research with collections at the National Library of Scotland, The British Library and Library of Congress.
In early 2023 the research team will showcase their methods and data at a public event hosted at the David Rumsey Map Center at Stanford Libraries.
Find out more about this project in the blog: How can machine learning help us unlock historical maps?
Header image: Aphricae tabula quarta continent (1541), David Rumsey Historical Map Collection