People could soon take a virtual reality “walk” around their hometown as it looked 50 or even 150 years ago – thanks to artificial intelligence.
But the digital models will be more than just a novelty – they will give researchers a chance to conduct studies that would have been nearly impossible before, such as estimating the economic loss caused by the demolition of former streets.
The research, published in the journal PLOS One, began with Sanborn Fire Insurance maps.
They were created to allow fire insurance companies to assess their liability in about 12,000 cities and towns in the United States during the 19th and 20th Centuries.
Study co-author Professor Harvey Miller, of Ohio State University, said: “The story here is we now have the ability to unlock the wealth of data that is embedded in Sanborn fire atlases.
“It enables a whole new approach to urban historical research that we could never have imagined before machine learning. It is a game changer.”
The problem for researchers was that trying to manually collect usable data from the maps was tedious and time-consuming – at least until the maps were digitised.
Study co-author Yue Lin, a doctoral student in geography at Ohio State, developed machine learning tools that can extract details about individual buildings from the maps, including their locations and footprints, the number of floors, the building materials and their primary use, such as dwelling or business.
She said: “We are able to get a very good idea of what the buildings look like from data we get from the Sanborn maps.”
The researchers tested their machine learning technique on two adjacent neighborhoods on the near east side of Columbus, Ohio, that were largely demolished in the 1960s.
One of the neighborhoods, Hanford Village, was developed in 1946 to house returning black World War Two veterans.
Study co-author Gerika Logan said: “The GI bill gave returning veterans funds to purchase homes, but they could only be used on new builds.
“So most of the homes were lost to the highway not long after they were built.”
The other neighborhoods in the study was Driving Park, which also once housed a thriving black community.
The researchers used 13 Sanborn maps for the two neighborhoods, produced in 1961.
Machine learning techniques were able to extract the data from the maps and create digital models.
Comparing data from the Sanford maps to today showed that a total of 380 buildings were demolished in the two neighborhoods for a new highway, including 286 houses, 86 garages, five apartments and three stores.
Analysis of the results showed that the machine learning model was very accurate in recreating the information contained in the maps – about 90 percent accurate for building footprints and construction materials.
Miller said: “The accuracy was impressive.
“We can actually get a visual sense of what these neighborhoods looked like that wouldn’t be possible in any other way.
“We want to get to the point in this project where we can give people virtual reality headsets and let them walk down the street as it was in 1960 or 1940 or perhaps even 1881.”
He said that using the machine learning techniques developed for the study, researchers could develop similar 3D models for nearly any of the 12,000 cities and towns that have Sanborn maps.
That will allow them to re-create neighborhoods lost to natural disasters such as floods, as well as urban renewal, depopulation and other types of change.
Because the Sanborn maps include information on businesses that occupied specific buildings, researchers could also re-create digital neighborhoods to determine the economic impact of losing them to urban renewal or other factors.
Prof Miller added: “There’s a lot of different types of research that can be done.
“This will be a tremendous resource for urban historians and a variety of other researchers.
“Making these 3D digital models and being able to reconstruct buildings adds so much more than what you could show in a chart, graph, table or traditional map. There’s just incredible potential here.”
Produced in association with SWNS Talker
Edited by Saba Fatima and Asad Ali
