Ancient-times maps give us a slight glimpse of how landscapes looked like hundreds of years ago. But what would we see if we looked at these older maps with a modern lens?
Henrique Andrade is a student at Escola Politécnica da Universidade de Pernambuco, Recife who has been examining maps of his hometown Recife, in Brazil, for several years now.“I gathered all these digital copies of maps, & I wound up discovering things about my hometown that are not so widely known,” he says. “I feel that in Recife people were denied access to their own past, which makes it hard for them to understand who they are, and thus what they can do about their own future.”
Andrade approached a professor at his university, Bruno Fernandes, with an idea: to develop a machine learning algorithm that could transform ancient maps into Google satellite images. Such an approach, he accepts, could inform people of how land use has changed over time, including the social and economic impacts of urbanization.
To see the project realized, they used an existing AI tool called Pix2pix, which depends on 2 neural networks. The 1st one creates images based on the input set, while the second network chooses if the generated image is fake or not. The networks are then prepared to fool each other, and eventually create realistic-looking images based on the historical data provided.
In this study, they took a map of Recife from 1808 and generated modern-day images of the area.
“When you look at the images, you get a better grasp of how the city has changed in 200 years,” explains Andrade. “The city’s geography has drastically changed—landfills have reduced the water bodies and green areas were all removed by human activity.”
He says an advantage of this AI approach is that it requires relatively little input volume; however, the input requires some historical context, and the resolution of the generated images is lower than what the researchers would like.
“Moving forward, we are working on improving the resolution of the images, and experimenting on different inputs,” says Andrade. He sees this approach to generate modern images of the past as widely applicable, noting that it could be applied to various locations and could be used by urban planners, anthropologists, and historians.