Back to Bigger Picture

BIGGER PICTURE Disaster preparedness

Forecasting a downpour without blurring it away

A generative weather model tackles an awkward problem: averaging several possible storms can produce a smooth forecast of a storm that never happens.

AI-generated illustration: Conceptual rain cloud with translucent possible future positions over a valley.
Rain cloud with translucent possible future positions over a valley.AI-generated illustration of the idea, not a photograph of the actual people, equipment or event.
Lead time
5–90 minutes
Expert evaluation
More than 50 Met Office forecasters
Approach
Several plausible radar futures

How the idea works

  1. Read recent radar

    Radar sequences show how rain has moved and changed.

  2. Generate possible continuations

    The model produces coherent future rain patterns.

  3. Compare and interpret

    Forecasters assess location, intensity and uncertainty.

A blurred storm can hide the dangerous bit

A weather forecaster needs to know where intense rain may fall in the next hour, not just whether the wider region will be damp. Some machine-learning forecasts become blurry as they look further ahead. Averaging possible storm positions can soften the very peaks that matter for decisions about heavy rain, transport and local flood risk.

Sources: [1][3]

Generate plausible weather, then test it

DeepMind and the Met Office developed DGMR to generate multiple realistic continuations of recent radar observations. Rather than presenting one smoothed answer, the system represents several possible ways rain could evolve. Its predictions cover lead times from five to ninety minutes. The research checks both numerical skill and whether the resulting structures make sense to professional forecasters.

Sources: [1][3][4]

The people using the forecast got a vote

More than fifty Met Office meteorologists compared the model with two alternatives in a systematic evaluation. They strongly preferred the generative forecasts for accuracy and usefulness; the final publication’s accompanying account reports first preference in 89% of cases. That percentage describes expert preference in a comparison, not the probability that any future forecast will be correct.

Sources: [3][4]

Useful uncertainty beats false precision

The Met Office describes the work as a demonstration evaluated against standard methods. It is evidence of a useful forecasting approach, not proof that this particular 2021 model now issues public warnings or has prevented a quantified loss. Its transferable contribution is showing uncertainty in a form experts can interpret without erasing the physical intensity of possible events.

Sources: [4][1]

The original sources

  1. Ravuri et al., arXiv; published in NatureSkillful Precipitation Nowcasting using Deep Generative Models of Radar
  2. NatureSkilful precipitation nowcasting using deep generative models of radar
  3. Google DeepMindNowcasting the next hour of rain
  4. Met OfficeA framework for data science in the Met Office 2022–2027

What to explore next

Which storm on the screen is about to become dangerous?A chip’s floor plan can be learned
Explore all 99 applications