!["[It] doesn't require the high cost involved in running a supercomputer — you can even run it out of a good quality desktop."](https://www.thecooldown.com/wp-content/uploads/2024/03/8HN9tJg3jPdn.jpg?w=1920&h=800)
Gone are the days of complaining that the meteorologist on the news doesn't know what they are talking about.
As extreme weather events become more frequent, intense, and unpredictable, we need technology that is up to the task of warning us when they are about to hit. Weather agencies across the globe are focused on artificial intelligence to help provide those warnings.
The India Meteorological Department is using AI to generate public alerts for heat waves and disease outbreaks, such as malaria. Crucially, the AI model doesn't break the bank.
"An AI model doesn't require the high cost involved in running a supercomputer — you can even run it out of a good quality desktop," said Saurabh Rathore, an assistant professor at Delhi's Indian Institute of Technology, according to Reuters.
Other weather agencies are also relying on AI. In England, researchers from the Alan Turing Institute and the Met Office are working together to develop AI models that have "the potential to revolutionize weather forecasting," according to the Met Office.
"This project aims to tackle the big hold-out problem in weather prediction — fast and accurate prediction of impactful weather events, which sadly are capable of bringing devastating consequences to communities," said Dr. Jean Innes, CEO of the Alan Turing Institute. "This is an enormously ambitious project. … We aim to save lives, protect infrastructure and push the boundaries of scientific understanding for the benefit of communities here in the UK and internationally."
Elsewhere, an AI weather prediction model funded by Google was found to have outperformed conventional methods of predicting the weather.
"The numerical models used to predict weather are large, complex, and computationally demanding and do not learn from past weather patterns," a summary of the study, published in the journal Science, read. Using "a machine learning-based method that has been trained directly from reanalysis data of past atmospheric conditions [researchers] were able to quickly predict hundreds of weather variables globally up to 10 days in advance and at high resolution."
Join our free newsletter for weekly updates on the coolest innovations improving our lives and saving our planet.
Cool Picks
