Using AI to predict weather hazards faster and more accurately
The Wall Street Journal’s Technology section brought the AI2ES Institute and Dr. Amy McGovern’s work there to the attention of the business community on April 4, 2021 with the article “How AI Can Make Weather Forecasting Less Cloudy.”
Weather-related damage to infrastructure and property in the first quarter of 2021 alone has amounted to over $90 billion. Better predictions of impending weather impacts could allow better preparation and thus reduce damages.
Artificial intelligence (AI) and machine learning (ML) can improve the efficiency of processing millions of data each day, to deliver forecasts more accurately and faster than the traditional numerical models used for weather forecasting.
“Instead of using brute-force computation to forecast weather based on present conditions, these [neural] networks review data on weather from the past and develop their own understanding of how conditions evolve.” – T. Alcorn, WSJ
AI/ML methods are being used alongside traditional weather models for now, so that meteorologists can understand how and how well these new tools work. Applications range from regional forecasts to local “nowcasts,” or short-term forecasts, with applications for citizens and businesses.
“In addition to developing artificial-intelligence methods to improve prediction of extreme weather and coastal oceanography, they are working to ensure the tools they develop are viewed as trustworthy by the human forecasters who will ultimately use them.” – T. Alcorn, WSJ
Read the online article at How AI Can Make Weather Forecasting Less Cloudy, Ted Alcorn, The Wall Street Journal, April 4, 2021.