news-details

Machine learning could improve extreme weather warnings

Because small changes in atmospheric and surface conditions can have large, difficult-to-predict effects on future weather, traditional weather forecasts are released only about 10 days in advance. A longer lead time could help communities better prepare for what's to come, especially extreme events such as the record-breaking June 2021 U.S. Pacific Northwest heat wave, which melted train power lines, destroyed crops, and caused hundreds of deaths.

Meteorologists commonly use adjoint models to determine how sensitive a forecast is to inaccuracies in initial conditions. These models help determine how small changes in temperature or atmospheric water vapor, for example, can affect the accuracy of conditions forecast for a few days later.

However, running adjoint models requires significant financial and computing resources, and the models can measure these sensitivities only up to five days in advance. Researchers tested whether a deep learning approach could provide an easier and more accurate way to determine the optimal set of initial conditions for a 10-day forecast.

The findings are published in the journal Geophysical Research Letters.

Related Posts
Advertisements
Market Overview
Top US Stocks
Cryptocurrency Market