An algorithm could predict the likelihood of lightning striking

Lightning is one of the most unpredictable phenomena in nature. It regularly kills people and animals and sets fire to homes and forests. It keeps aircraft grounded and damages power lines, wind turbines and solar-panel installations.

Little is really known about what triggers lightning, and there is no simple technology for predicting when and where lightning will strike the ground.

Researchers from the Ecole Polytechnique Fédérale de Lausanne (EPFL) have however, developed a simple and inexpensive system that can predict when lightning will strike to the nearest 10 to 30 minutes, within a 30-kilometre radius. It uses a mixture of standard meteorological data and artificial intelligence. 

The team from EPFL’s Laboratory of Electromagnetic Compatibility led by Farhad Rachidi. used data collected over a ten-year period from 12 Swiss weather stations, located in both urban and mountainous areas in order to train the system to predict the possibility of lightning occurring.

Factors that were taken into consideration in the training process included: atmospheric pressure, air temperature, relative humidity and wind speed. Once trained, the system proved to be accurate almost 80% of the time.

Amirhossein Mostajabi, the PhD student who came up with the technique said: "Our method uses data that can be obtained from any weather station. That means we can cover remote regions that are out of radar and satellite range and where communication networks are unavailable."

The system allows the data to be collected in real time, which means that forecasts can be made quickly and weather warnings can be issued well in advance of the storm developing. 

This predictive ability will have the opportunity to contribute to an ambitious European project called Laser Lightning Rod, which aims to develop systems to protect people from lightning. The project, which was launched in 2017, consists of sending short laser pulses of several terawatts into the atmosphere during a storm in order to provoke a lightning strike, guiding it to a specific location and away from vulnerable areas. 

The intention is to cushion the catastrophic effects that certain storms cause. Between 6,000 and 24,000 worldwide die as a result of lightning strikes across the world every year - with men being six times more likely than women to be struck by lightning. 

Lightning has a massive impact on the world on a daily basis. There are approximately 1,800 thunderstorms in progress around the world at any one time. This equates to around 40,000 storms a day. More than 17 million bolts of lightning hit the Earth every day, which is 200 per second. Lightning is the cause of whole towns and cities to lose power, sparks forest fires and damage to infrastructure, which amounts to millions of euros each year.

This is the first time that a system based on simple meteorological data has been able to predict lightning strikes through real-time calculations. The method offers a simple way of predicting a complex phenomenon and could ultimately save lives.