Microsoft open-sources PBC weather forecast correction tool
What happened
On 15 October 2026, The Verge reported that Microsoft Research has proposed probabilistic bias correction (PBC), a machine learning method that identifies and corrects systematic biases in existing weather forecast models. The related paper was published in Nature, and the tool has been open-sourced. The research shows that PBC raised the precipitation accuracy of ECMWF's physical model to 98% and its temperature target to 92%, and doubled the accuracy of its AI forecasting system. The method can run on CPU alone, and the researchers hope institutions with limited resources can use it to improve local forecasts.
Written by AI from the reports · updated 2 d ago
Timeline
Follow the reports to see the event from each side.
- The Verge · AIMicrosoft has a new machine learning tool to improve weather forecasts
Old-school physics-based weather forecasting and even new AI models typically become less reliable beyond two weeks, a problem Microsoft claims to have solved using machine learning.
Heat of this event
Current heat 3·Peak in the comparable range 9（Oct 15 05:00）·Change over 24 hours in the comparable range -51%
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.