Using radar data from the USA and China, NowcastNet produces physically plausible rain forecasts with sharp detail over 2,048 km squares, up to 3 hours ahead.

The paper

The paper's details are OpenAlex's; the citation count is OpenAlex's, 15 Oct 2026. The line on the paper is machine-written, as noted under Why it matters.

Why it matters

Written by Claude (claude-sonnet-5-5) on 15 Oct 2026 from the paper's abstract (as the publisher's record at Crossref publishes it) and its OpenAlex record. Machine-written context to help a reader: it is not evidence, it moves no number, and it may be wrong. The quoted sentence is the claim; where it stands is computed from the record. If it misreads the paper, tell the stewards.

The story so far

1. 1

   What the authors did

   The authors built a nowcasting model trained and tested on radar observations from the USA and China. They also had 62 professional meteorologists from across China evaluate its forecasts against leading methods.

   Machine-written from the paper's abstract, as noted under Why it matters.

2. 2

   What they found

   • NowcastNet unifies physical-evolution schemes and conditional-learning methods in one neural-network framework with end-to-end forecast error optimisation.
   • In an evaluation by 62 professional meteorologists from across China, it ranked first in 71% of cases against leading methods.
   • It provides skilful forecasts from light to heavy rain rates, including extreme events with advective or convective processes previously considered intractable.

   Machine-written from the paper's abstract, as noted under Why it matters.

3. 3

   What has been checked on Ecdysis

   Exuvia registered the claim on 15 October 2026, with a test written from the paper. No check has been filed yet.

What would check it

How far it has been checked

1. 1
   The object itself, checked againverification · not yet

   Not yet: re-run the paper's analysis on its own data, where the authors have published it.

2. 2
   New instances of the constructionreproduction · not yet

   Not yet: the same construction run afresh.

3. 3
   The designrobustness tests and arguments · not yet

   Nothing yet: change the method or the data and see whether it holds (a robustness test), or argue that the method does not test what the claim says.

How sure is the record?

Share this finding

Ready-made posts, written from the record. You post them yourself, from your own account; nothing is ever posted for anyone.

Click a post's text to select all of it. Both posts give the claim's standing on the record, and the longer one says what the checks show and what they do not; the wording changes when the record does. The longer post quotes the paper first, then gives the machine-written headline, marked as such; edit it as you like. To cite the claim, see Cite this claim.

What would prove it wrong

Refuted if, when applied to independent radar observations covering 2,048 km × 2,048 km regions and lead times up to 3 h, the NowcastNet model fails to produce precipitation nowcasts that exhibit sharp multiscale patterns or are physically plausible according to established physical criteria (e.g., conservation of mass, consistency with known advective processes).

The test as Exuvia registered it on 15 Oct 2026, written from the paper's words.

The wider literature

Other claims from the same paper

• uncheckedIn an evaluation by 62 professional meteorologists across China, NowcastNet was ranked first in 71% of cases against leading methods.“In a systematic evaluation by 62 professional meteorologists from across China, our model ranks first in 71% of cases against the leading methods.”
• uncheckedNowcastNet provides skilful forecasts at light-to-heavy rain rates, particularly for extreme-precipitation events accompanied by advective or convective processes that were previously considered intractable.

Headlines are machine-written from the paper's abstract, or from the quote and the paper's title where no abstract is open; each claim's own words are quoted beneath its headline.