Machine learning can now forecast lightning sooner than other methods

University of Washington researchers have created a new machine-learning algorithm to predict lightning strikes sooner than ever.

1 minute & 10 seconds read time

In a new study led by the University of Washington, researchers have demonstrated artificial intelligence's ability to improve lightning forecasts.

Machine learning can now forecast lightning sooner than other methods 01

Lightning strikes led to the devastating California Lightning Complex fires of 2020, but the strikes are still relatively hard to predict. With more accurate forecasts, firefighters could potentially mitigate wildfires by getting the chance to stop smaller fires caused by strikes before they grow out of control, as well as helping to forecast severe weather systems like thunderstorms.

"The best subjects for machine learning are things that we don't fully understand. And what is something in the atmospheric sciences field that remains poorly understood? Lightning. To our knowledge, our work is the first to demonstrate that machine learning algorithms can work for lightning," said Daehyun Kim, an associate professor of atmospheric sciences at the University of Washington.

Researchers trained the machine learning system with lightning data from the World Wide Lightning Location Network (WWLLN), spanning 2010 to 2016. The system could discover the relationships between weather variables and lightning strokes using the data. They then made predictions for strikes spanning 2017 to 2019 using the machine learning model and an existing physics-based method, both of which were compared against the actual observations.

Machine learning can now forecast lightning sooner than other methods 02

The new machine learning method, paired with weather forecasting, can predict lightning two days earlier than the current leading technique. Researchers hope to improve the system with more data sources, weather variables, and new, more sophisticated techniques.

"In atmospheric sciences, as in other sciences, some people are still skeptical about the use of machine learning algorithms-because as scientists, we don't trust something we don't understand. I was one of the skeptics, but after seeing the results in this and other studies, I am convinced," said Kim.


Adam grew up watching his dad play Turok 2 and Age of Empires on a PC in his computer room, and learned a love for video games through him. Adam was always working with computers, which helped build his natural affinity for working with them, leading to him building his own at 14, after taking apart and tinkering with other old computers and tech lying around. Adam has always been very interested in STEM subjects, and is always trying to learn more about the world and the way it works.

Newsletter Subscription

Related Tags