Could 12 inches of rain hit New York City? AI maps plausible rare storms
Can a city's seawall stand up to a blockbuster storm? Will a region's power grid hold against record-breaking heat? And can a town's firefighting resources contain a major wildfire?
MIT engineers have created a tool to generate likely extreme weather scenarios and map their characteristics, such as duration, intensity, and area of impact. This machine-learning algorithm does not rely on historical extreme events to create plausible future extreme events. Instead, it learns from a dataset, such as a region's daily weather records and maps.
The algorithm employs a statistical approach to exclude implausible weather scenarios and then generates plausible extreme events with a certain frequency, like once every 100 years. The researchers aim to quantify the intensity and extent of such events to assist city planners in preparing for potential worst-case scenarios. While traditionally, extreme events are assessed by examining past occurrences, this new method allows for the prediction of unprecedented events that are yet to be recorded.
By applying this method to various fields, such as robotic navigation and financial markets, the team hopes to help planners and policymakers better prepare for and respond to extreme events.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
