"Although Google DeepMind's Weather Lab only started releasing cyclone track forecasts in June, the company's AI forecasting service performed exceptionally well. By contrast, the Global Forecast System model, operated by the US National Weather Service and is based on traditional physics and runs on powerful supercomputers, performed abysmally. The official data comparing forecast model performance will not be published by the National Hurricane Center for a few months."
"A little help in reading the graphic is in order. This chart sums up the track forecast accuracy for all 13 named storms in the Atlantic Basin this season, measuring the mean position error at various hours in the forecast, from 0 to 120 hours (five days). On this chart, the lower a line is, the better a model has performed."
"Meanwhile, at the bottom of the chart, in maroon, is the Google DeepMind model (GDMI), performing the best at nearly all forecast hours. The difference in errors between the US GFS model and Google's DeepMind is remarkable. At five days, the Google forecast had an error of 165 nautical miles compared to 360 nautical miles for the GFS model, more than twice as bad. This is the kind of error that causes forecasters to completely disregard one model in favor of another."
Preliminary analysis of Atlantic hurricane season track forecasts across 13 named storms shows Google DeepMind's Weather Lab produced the most accurate tracks while the US Global Forecast System (GFS) performed worst. Forecast accuracy was measured as mean position error from 0 to 120 hours. At five days, DeepMind's error was 165 nautical miles versus 360 nautical miles for the GFS. Brian McNoldy performed preliminary comparisons before official National Hurricane Center data release. Google's forecasts began in June. Large GFS errors prompted forecasters to disregard that model in favor of better-performing alternatives.
Read at Ars Technica
Unable to calculate read time
Collection
[
|
...
]