Community and city renewal demonstration 15 minutes. A- Renewal of society. We imitate the roads, residential buildings and parks of a real community and leave other areas as vacant land for regeneration. The agent places different types of facilities to maximize service accessibility for residents in the community. B, a 15-minute city, meaning five basic housing needs can be met within a 15-minute walk or bike ride. C, facility needs. We diversify needs into five different facilities (school, hospital, business, office and leisure) that correspond to the five core services (education, medical care, shopping, work and leisure). We investigate low needs (2 accounts per facility), medium needs (4 accounts per facility), high needs (8 accounts per facility), and mixed needs (10, 5, 4, 8 and 3 accounts for the five facilities, respectively). D,Service accessibility performance under different needs. We show a 15-minute circle indicator of the five core services of a community plan created around different facility needs. The root value means the proportion of residential blocks that can access the corresponding service within 15 minutes. credit: Computational natural sciences (2023). doi: 10.1038/s43588-023-00503-5
A team of urban planners and information scientists at Tsinghua University in China discovered that an AI-based urban planning system was able to outperform human experts in creating urban planning designs. In their study, reported in the journal Computational natural sciencesThe group describes the factors that were used to describe the ideal urban plan and how well the AI performed when tested. Paolo Santi, of the MIT Senseable City Lab, published a News & Views article in the same issue of the journal outlining the work the team did on this new effort.
For most of history, cities were left to grow organically, as immediate needs were identified and urban planners and engineers attempted to meet those needs. In many cases, this haphazard approach to urban growth has led to less than optimal results. Recently, city officials and other planners have tried to take a more common-sense approach to the problem by creating designs for areas to be developed that take into account things like livability and pollution control.
This has led to the development of urban planning as a science and the emergence of professional urban development experts. This science can be very complex due to the increasing number of variables that must be taken into account as the volume of new development increases. In this new effort, the research team found a way to apply artificial intelligence to the problem to reduce the burden.
In developing their AI system, the team chose to use the 15-minute concept, where residents of a planned community should be able to get from their homes to essential services within 15 minutes. Under this system, the quality of life improves due to reduced travel time and reduced air pollution generated. The researchers trained the system through advance plans made by humans along with factors believed to be good design features such as the inclusion of parks, public green spaces, bike paths and entertainment venues.
Once the system was built, the research group used it to design a small community in a 3×3 grid city block. This allowed them to modify the system, resulting in improvements. Then they gradually increased the amount of development required and studied its results.
The researchers found that the plans developed by the system were as good or better than those created by humans. They also found a significant reduction in time, from hours to seconds. The team concludes that their system is not intended to replace human urban planners, but to free them from the mundane parts of urban planning, allowing them to focus on comprehensive concepts.
Yu Cheng et al., Spatial Planning of Urban Communities through Deep Reinforcement Learning, Computational natural sciences (2023). doi: 10.1038/s43588-023-00503-5
Paolo Santi, Artificial Intelligence improves the design of urban communities, Computational natural sciences (2023). doi: 10.1038/s43588-023-00515-1
© 2023 Web of Science
the quote: AI system found to outperform humans in creating urban planning designs (2023, September 18) Retrieved September 18, 2023 from https://techxplore.com/news/2023-09-ai-outperform-humans-urban.html
This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.