One step closer to automation and end of human forecasting?

[Scott A. Kampas]

Weather forecasters could find themselves pushed out of a job by an artificial intelligence system designed to write clearer, less ambiguous reports.

Computer scientists at the University of Aberdeen, UK, were asked to generate an \"artificial weatherperson\" by operators of offshore oil rigs, who wanted more clarity in their forecasts. The vocabulary used by different forecasters can be vague and highly variable, says Ehud Reiter, who led the Aberdeen team.

To remove such uncertainties, the team programmed a natural language generation (NLG) software package to transform data on the forecast weather into an unambiguous written bulletin (Artificial Intelligence, vol 167, p 137).

Similar systems could be used to clarify the medical notes of hospital critical care beds to prevent the phrases used to describe a patient's condition being misinterpreted.

New Scientist, 28 September 2005

 

[Andrew Khan]

I don't like the idea..now think of all the people who would lose there jobs...oh well, if it did happen it wouldn't ben any time soon.

 

[rdale]

This is a project to convert the forecasts into a standardized text format... Nobody loses a job here, the forecast itself is still made by a human.

 

[Scott A. Kampas]

I posted it as another step closer to automation in the vein of increasing momentum towards automation with inevitable technological advancement coupled with political and funding realities. That is where things are headed, to be sure. This system/project itself will not replace anyone. It does, however, generate actual forecasts (which are preferred by end users to human forecasts) from NWP data. In practical use, given the liimtations of NWP model output, it does use human adjusted forecasts as inputs to generate a more accurate, linguistically-standardized and clear output --though it can ran by itself, too, and still performed very well. Again, it's another step; I post it as something to ponder.

Scott