The growth and expansion of metropolitan areas has been evident over the past decade. Buildings are getting taller, and urban areas are getting larger. What if there was a way to predict this growth and expansion?
A new study by Spanish researchers from the University of A Coruna has discovered that the increase of skyscrapers in a city reflects the pattern “of certain self-organized biological systems,” as reported by ScienceDaily. The study uses "genetic evolutionary algorithms" to predict urban growth, looking specifically at Tokyo's Minato Ward. Architect Ivan Pazos, the lead author of the new study, explained the science behind the algorithm: "We operate within evolutionary computation, a branch of artificial intelligence and machine learning that uses the basic rules of genetics and Darwin’s natural selection logic to make predictions."
Read on for more about the study and what it could mean for the possibility of estimating vertical urban development.
Adapted from various genetic algorithms, the study combines genetic tendencies with historical construction data to "learn the growth patterns of urban districts," explains ScienceDaily. The algorithm not only predicts the number of skyscrapers in a specific area, but it can also predict the most likely placement of the buildings within specific urban districts.
The study focused on one of the neighborhoods with the highest vertical growth in the world in recent years: the Minato Ward in Tokyo. The authors used the data and algorithm to generate 3D maps of the Minato Ward in 2015, and have since compared the evolutionary model results with ongoing high-rise developments.
"The predictions of the algorithm have been very accurate with respect to the actual evolution of the Minato skyline in 2016 and 2017," says Pazos. "Now, we are evaluating their accuracy for 2018 and 2019 and it seems, according to the observations, that they will be 80 percent correct."
The authors of the study predict the findings may provide an accurate estimate of a city's vertical expansion using "genetic evolutionary computation."