Last updated May 29, 2018 at 12:03 pm
Models used to describe natural selection also successfully forecast urban development, a new study reveals.
Can cities be characterised as giant, self-organising biological systems? From a computational point of view, it seems they can, with Spanish research showing that algorithms derived from genetics and the mathematical rules governing natural selection can accurately forecast the growth of urban skylines.
In a paper published in the Journal of Urban Planning and Development, a team led by Ivan Pazos, a senior architect at Japanese building company Nihon Sekkei, show that “evolutionary computation” can be used to predict future development density with remarkable geographic precision.
Pazos and some colleagues from Spain’s University of A Coruña focussed on the Minato Ward of Tokyo, one of the fastest growing localities in Japan and home to the headquarters of corporations including Mitsubishi, Honda, NEC, Toshiba and Sony.
Some years ago, the researchers began their project by compiling data arising from construction sector activity in Minato and combining it with economic information. The result was then subjected to an algorithm designed around well-known genetic and evolutionary principles.
“In this type of computing, a multitude of possible solutions to a problem are randomly combined,” explains Pazos, “and a selection system is choosing the best results. This operation is repeated again and again until the algorithms get the most accurate results.”
In 2015, the team created a set of maps for Minato, predicting vertical growth in the area between 2016 and 2019.
“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% correct.”
The team’s maps not only predicted the number of new high-rises built in the ward, but also their geographic location.
The success of the approach means that it could be a useful tool for city planners striving to identify where construction activity is likely to be focussed in years to come.
“The final conclusion of the study is that evolutionary computation seems to be able to find growth patterns that are not obvious in complex urban systems, and by means of its subsequent application, it serves the function of predicting possible scenarios for the evolution of cities,” says Pazos.