The Venice Time Machine Project is a pioneer international Digital Humanities scientific programme launched by the EPFL and the University Ca’Foscari of Venice in 2012. It includes major Venetian patrimonial institutions: the State Archive in Venice, The Marciana Library, The Instituto Veneto and the Cini Foundation. The project is currently supported by the READ European eInfrastructure project, the SNF project Linked Books and ANR-SNF Project GAWS. The international board of the project includes scholars from Princeton, Stanford, Columbia and London Universities. Three hundred researchers and students from different disciplines (Basic Sciences, Engineering, Computer Science, Architecture, History and History of arts) have already collaborated to this international programme. A doctoral school is organized every year in Venice and several bachelor and master courses already use the data produced in the context of the project.
The Venice Time Machine project aims at building a multidimensional model of Venice and its evolution covering a period of more than 1000 years. Kilometers of archives are currently being digitized, transcribed and indexed setting the base of the largest database ever created on Venetian documents. Millions of photos are processed using machine vision algorithms and stored in a format adapted to high performance computing approaches. In addition to these primary sources, the content of thousands of monographs are indexed and made searchable. The information extracted from these diverse sources is organized in a semantic graph of linked data and unfolded in space and time as part of an historical geographical information system, based on high-resolution scanning of the city itself.
The diversity, amount and accuracy of the Venetian documents are unique in Western history. The Venice Time Machine puts in operation a technical pipeline to transform this heritage in Big Data of the Past. Fast document scanners produce a stream of digital images that are analyzed using deep learning networks. These algorithms find reoccurring patterns in hand-written documentation, maps but also paintings and musical scores extracting information about people, places and art works, creating a giant network of linked data. The information items extracted from the documents are intricately interweaved. By combining this mass of information, it is possible to reconstruct large segments of the city’s past. At a larger scale, the Venetian archives reveal a 1000 years of European circulations, offering new tools to study population and economical dynamics, linguistic evolution, disease spreading, and pattern migrations in the domains of visual arts, architecture and music.
Moreover, one of the major conceptual and technological challenges of this project is to provide intellectual accountability for all these various reconstitutions. The Venice Time Machine does not only aim at creating vivid representations of the past, but organizes transparent processes linking historical records and computer-based visualizations. Ambiguity and lack of precision in historical records and associated uncertainties in reconstructed maps and networks are systematically qualified and quantified. By maintaining a rigorous and constructive approach, the findings obtained through the Venice Time Machine are open to peer review and can be included in the scholarly debates of the humanities.