Peter Düben is ECMWF’s coordinator for artificial intelligence and machine learning activities.
The use of machine learning in numerical weather prediction is on the rise. In a lecture on 10 December 2019, ECMWF scientist Peter Düben set out the main use cases and charted the way ahead.
In his talk, delivered during the 95th session of the Centre’s Council, he described how quality control, bias correction in data assimilation, emulating model components, quantifying uncertainty and many other aspects of numerical weather prediction can benefit from machine learning techniques.
“There is no doubt that this is an exciting area of research, especially since much of today’s high-performance computing research is geared towards artificial intelligence applications,” Peter says.
“In my lecture, I set out what machine learning in the field of weather and climate might look like ten years from now, but only the future can tell just how far it can be taken in the context of numerical weather prediction over the decades to come.”