Really good piece from @[email protected] about #ElNino on #TheClimateBrink. We have been thinking a lot about this in the @[email protected] #PISCO project - there are important ENSO related effects on #Antarctic ice sheet.

Combined dynamical-deep learni...
Combined dynamical-deep learning ENSO forecasts - Nature Communications

This study proposes two schemes for integrating DL and dynamical models for ENSO prediction, which outperform individual models and improve the prediction skill across a range of lead times.

Nature

Really good piece from @hausfath on #TheClimateBrink about #ElNino - we have been thinking a lot about this in the @esaclimate #PISCO project - there are important ENSO related effects on #Antarctic ice sheet.

Interestingly I think all the models here are classic numerical models, a Chinese deep learning model also shows a strong El Nino (https://www.nature.com/articles/s41467-025-59173-8).
2025 seems to offer a good test bed for the different forecasts.

#AI #DeepLearning

https://open.substack.com/pub/theclimatebrink/p/the-el-nino-cometh

Combined dynamical-deep learning ENSO forecasts - Nature Communications

This study proposes two schemes for integrating DL and dynamical models for ENSO prediction, which outperform individual models and improve the prediction skill across a range of lead times.

Nature

I realise on the fediverse this is maybe asking for a flaming, but yesterday out of sheer curiosity I tried Claude for a simpleish coding task that I'd been putting off (largely inspired by @hausfath 's latest on #theclimatebrink). The performance of Claude was seriously impressive. I am convinced the AI cycle is more than hype (and have been for a while), the chatbots have been a huge attention hogger, misleadingly so, while the serious work has been done elsewhere. (We are developing ML tools to supplement parts of our climate model workflows).

Now I'm wondering if there is any serious EU competition to Anthropic? - Mistral's codestral perhaps?
Because this kind of performance changes everything and we can't afford to lag behind...
#AIcoding #ML

Edit: here is the climate brink post I mentioned

https://www.theclimatebrink.com/p/the-ai-augmented-scientist

The AI-Augmented Scientist

The promise and pitfalls of using AI tools to boost my capabilities as a scientist

The Climate Brink

#FYI #ZekeHausfather #TheClimateBrink

"Global temperatures were in record territory for the first three weeks of the year in the Copernicus/ECMWF ERA5 dataset, only falling out of record territory over the past few days."

https://www.theclimatebrink.com/p/january-sets-an-unexpected-temperature

#climate #ClimateScience #climatechange #ClimateEmergency #ClimateCrisis #ClimateBreakdown #climatecatastrophe #globalWarming #globalHeating #ExtremeWeather

January sets an unexpected temperature record

Despite long-faded El NiƱo conditions, 2025 saw the warmest January on record

The Climate Brink

It's an interesting symmetry with @andrewdessler's latest on the LA fires, insurance is where we'll start to feel #ClimateChange in the wallet first. (Though admittedly Danish floods are generally less destructive and deadly than California's fires).
#TheClimateBrink

https://www.theclimatebrink.com/p/some-thoughts-on-the-la-fires
From: @Ruth_Mottram
https://fediscience.org/@Ruth_Mottram/113822898817115241

Los Angeles burns: What you need to know

This is terrible. This is climate change.

The Climate Brink

Were they the hottest days in 120,000 years*? How do we know and does it matter?

Brilliant overview on the newest world record as ever by @andrewdessler on #TheClimateBrink

*Global mean temperature that is - they definitely weren't the hottest days ever in #Scandinavia...

https://open.substack.com/pub/theclimatebrink/p/the-hottest-days-in-125000-years

The hottest days in 120,000 years

Last week we set a record: we experienced the hottest day in the observational record.

The Climate Brink

Some years ago the Danish meteorological society (full disclosure, I sit on the board) held an evening debate on cloud seeding, based on a film from the middle east and with a scientist from Israel who had been assessing experiments for many years. He was extremely sceptical it worked. I think I reached very similar conclusions to this excellent piece in #theclimatebrink. Cloud seeding can work under very specific conditions, but it's mostly a scam.

https://open.substack.com/pub/theclimatebrink/p/a-primer-on-cloud-seeding

A primer on cloud seeding

no, it did not cause the flooding in Dubai

The Climate Brink