Advancing subseasonal forecasting with machine learning
The open-source method corrects systematic model bias and improved flood prediction skill by 76% to 92%, researchers said.
9 Articles
9 Articles
Microsoft AI Tool Can Predict Weather Up to 6 Weeks Ahead | 📲 LatestLY
Microsoft Research, in collaboration with MIT, has unveiled the Probabilistic Bias Correction (PBC) AI tool, detailed in a Nature paper published today, October 14, 2026. This open-source and cost-effective machine learning framework dramatically extends reliable weather forecast accuracy from two weeks to an unprecedented six weeks, offering substantial. 📲 Microsoft AI Tool Can Predict Weather Up to 6 Weeks Ahead.
Microsoft 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. Researchers with the company say they've found a new, cost-effective way to make more accurate weather forecasts two to six weeks in advance - allowing farmers and emergency responders […]
For meteorologists, trying to predict whether it will rain or if there will be a cold wave within a month is very similar to going to a casino and throwing the dice. Weather predictions rarely go beyond 10 days, hopefully reach 15, and rarely come this far in advance. Find out what time it will take with a margin of between two weeks and a month and a half is to fully enter the so-called “desert of predictability”: there are too many possibiliti…
Advancing subseasonal forecasting with machine learning
Decision-makers rely on weather forecasts to plant crops, manage wildfires, allocate water and energy and prepare for weather extremes1–3. Today, such forecasts enjoy unprecedented accuracy as far as 2 weeks thanks to steady advances in physics-based dynamical models and data-driven artificial intelligence models4–10. However, model skill drops precipitously at subseasonal timescales (2–6 weeks ahead) due to compounding errors, systemic model bi…
Coverage Details
Bias Distribution
- 34% of the sources lean Left, 33% of the sources are Center, 33% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
