Home › Hard problems › Science and maths

Science and maths

Weather beyond two weeks

Solo: possibleOne person can test a narrow slice of it.

a few days: AI modelsbeat physics modelsskill fades?seasonal forecasts:still weaktodayabout 2 weeksa month and more
AI weather models win for days ahead, but every forecast spreads apart and its skill fades after about two weeks.

Why it is still open

AI weather models now beat physics models for days ahead, but skill fades after about 2 weeks, and seasonal forecasts stay weak.

An experiment one person can run in 8 weeks

Compare open AI forecasts with simple climatology at 1, 2 and 4 weeks ahead for one region.

Verdict: Solo: possible

Open data; making a real gain is hard.

The solo test behind the verdict

  1. Can it be measured? There is a number that shows you did better, such as an error rate, a catch rate or a cost per answer.
  2. Is it cheap to try? It runs on a laptop, free open models and open data, or under about ₹50,000 of rented GPU time.
  3. Is there a public yardstick? A benchmark or dataset others use, so your result can be compared and believed.
  4. Would a small win get noticed? A lab, a funder or a customer would care about a 10% improvement, not only a full solution.

Four yeses means Solo: strong. Two or three means Solo: possible. Fewer means Follow, don't build.

PreviousTurning maths into machine-checked proofsNextPredicting what a protein does or binds to

All 79 hard problems · Working on this, or know of a result we missed? basant@cleandataengineering.ai