Lightning strikes may be beautiful to see, but the consequences of them can be brutal. For one, lightning kills more people each year than tornadoes or hurricanes. On top of that, lightning strikes can be detrimental to farmers as they can cause fires that can destroy millions of dollars’ worth of crops. Lightning belongs in the category of things that show nature is all-mighty, but that doesn’t mean we can’t be better prepared for when lightning will strike.

In Switzerland, a team of researchers has been working on an artificial intelligence system that can predict lightning strikes down to the nearest 10 to 30 minutes inside a 30-kilometer radius (about 18.6 miles). To do this, the team trained their machine-learning algorithm to recognize weather conditions that typically lead to lightning. Specifically, they used four variables, including air pressure at station level, air temperature, relative humidity, and wind speed. 

After the algorithm completed its learning phase, it made correct predictions about new lightning strikes about 80 percent of the time. It’s the first time a simple model, trained on meteorological data, has predicted lightning strikes with live calculations. And since it’s based on existing data, it’s pretty cheap and simple to replicate.

Pretty nifty, especially considering that the only warning system for lightning has long been storm clouds.