Artificial intelligence (AI) has been heavily criticized for its resource requirements. They consume huge amounts of energy and water and are on the rise at an alarming rate.
But scientists at the University of Helsinki are developing an AI process to slow climate change by informing smarter urban design. To improve quality of life while reducing emissions, sustainability science professor Laura Luotsalainen and her research group are developing machine learning methods to simulate traffic flows and other municipal characteristics.
sim city
Simulations are often used by engineers to explore social solutions without relying on real-world evidence, which can take years to collect. Urban planners can therefore recreate different scenarios on an exponentially faster timeline before a single brick is laid.
Researchers in Helsinki are therefore using AI to improve transportation infrastructure, streamline smooth commutes, reduce emissions, and improve air quality.
But how do you do that at a fundamental level? Through reinforcement learning. For perspective, imagine an AI entity driving through a virtual city. If you try different routes and meet set goals, you will receive digital enhancements, and if you fail to do so, you will be penalized.
AI agents can now do this at greater scale and speed than ever before to assess efficiency across cities. “Urban environments involve a huge number of interacting effects. AI can help address these complex problems and the combined effects of multiple factors, a task that cannot be done without human assistance.”
Optimizing critical citizen services
AI can also help build safer structures by enabling engineers to study the effects of natural disasters. By modeling digital twins, or virtual versions of cityscapes, researchers can study the effects of floods and other catastrophes, provide better response tactics, and save lives.
Other services are equally important. “For example, San Francisco has introduced a smart waste management system that uses sensors and internet-connected devices to optimize waste collection and disposal.”
However, many challenges still remain. Researchers must quantify, collect, and integrate vast amounts of data in a variety of incompatible formats.
Addressing these challenges is worth the effort. Approximately 60% of the world’s population currently lives in cities, and that number is expected to increase to 70% by 2050. Technological tools that improve citizen satisfaction and help slow climate change are therefore invaluable for both the population and the planet.
