As one of the most irregular phenomena in nature, lightning is very disturbing. Scientists have lately made an AI system that forecasts lightning up to 30 minutes before it strikes.
Lightning regularly kills animals and people, initiates fires, destroys power lines and keeps aircraft stranded. Till now, it has been almost out of the question to predict lightning, with no simple technology for predicting where and when it will strike the earth.
Engineers at the Ecole Polytechnique Federale de Lausanne’s (EPFL) School of Engineering built a simple and cheap system to forecast when lightning will strike. Farhad Rachidi led the research, which resulted in a technique of predicting lightning between 10 and 30 minutes before it hits, inside a 30km radius.
Using a combination of meteorological data and Artificial Intelligence, researchers are now intending to use this equipment in the European Laser Lightning Rod project, a venture designed to draw lightning away from areas that are vulnerable to lightning damage.
“Current systems are slow and complicated, and they require costly external data picked up by radar or satellite,” explains Amirhossein Mostajabi, the PhD student who came up with the method. “Our technique uses data that can be acquired from any weather station. That means we can cover distant regions that are out of satellite and radar range and where communication networks are inaccessible.”
Due to the capability to obtain the data in real-time, the method allows meteorologists to speedily predict lightning before a storm develops and notify those who could be affected.
The technique created by EPFL researchers uses a machine learning algorithm that has been trained to identify the conditions that lead to lightning. Researchers deliberated on four parameters when creating their method; air temperature, atmospheric pressure, relative humidity and wind speed. These parameters are interconnected to recordings from location systems and lightning detection.
After the method has been trained, researchers believe the system to be 80% accurate when predicting the site of a lightning strike.