AI predicts lightning strikes. One climate model predicts a coming 50% increase lightning incidence, not good, considering that lightning strikes are the lead starter of wildfires. In 2014, researchers at the University of California-Berkeley came up with a formula to predict and model lightning strikes. Lightning flash rate per area is equal to precipitation times the area’s potential electrical energy. That potential electrical energy in the US and around the globe will increase in the 21st century an average increase of 11.2 percent per degree Celsius of atmospheric warming. With even better prediction of strikes, warnings for areas could be issued. At EPFL’s School of Engineering, researchers in the Electromagnetic Compatibility Laboratory, led by Farhad Rachidi, created a simple and inexpensive system that can predict when lightning will strike to the nearest 10 to 30 minutes, within a 30-kilometer (18.64 miles) radius. Four parameters were taken into account: atmospheric pressure, air temperature, relative humidity and wind speed. Those parameters were correlated with recordings from lightning detection and location systems. Using that method, the algorithm was able to learn the conditions under which lightning occurs. Once trained, the artificial intelligence system made predictions that proved correct almost 80% of the time. The Ecole polytechnique fédérale de Lausanne (EPFL) is a research institute and university in Lausanne, Switzerland, that specializes in natural sciences and engineering.
Cool idea. Could a human looking at thunder clouds also make an 80% correct guess with a 20-mile radius to within 30 minutes? Perhaps, but who would want such a job? Check out the free (for iPhone) app, “My Lightning Tracker.” It partners with several commercial lightning data providers who each operate their own network of lightning detection equipment and it will alert you to lightning strikes in your area. You can even zoom in on each strike on a map, to the point of seeing which tree was hit … but the placement of dots on the map may not be as accurate as it appears.
#lightningmap #lightningprediction #oddnews #strangenews #ai #weathernews