Philip Brohan
banner
brohan.org
Philip Brohan
@brohan.org
Historical Climatologist. Into deep learning and data visualization.
It's not just the UK - global land temperatures can be independently confirmed - agupubs.onlinelibrary.wiley.com/doi/full/10....
Independent confirmation of global land warming without the use of station temperatures
Barometers and ocean data reproduce global land warming Conclusions based on large-area averages of land temperatures are robust
agupubs.onlinelibrary.wiley.com
October 8, 2025 at 12:44 PM
The future of scientific publishing is YouTube, Github, Medium, Substack, ...
I don't see much of that in the agenda.
July 14, 2025 at 9:52 AM
It is easy to come up with designs for ground-breaking climate models using ML.
The thing that's very hard is to come up with a ML climate model that looks and operates like an NWP model.
If we can find the courage to move on from NWP, then the future is bright indeed.
April 4, 2025 at 12:13 PM
They only use ERA5 at all because they are doing NWP imitation. Eventually they will realise that to forecast London precip. (say) an AI model doesn’t have to bother with the whole NWP state vector.
Then we’ll start to see real improvements.
March 20, 2025 at 8:35 PM
The really interesting result is the reduced observational requirement for DA. How far can we push that?
March 20, 2025 at 8:24 PM
You could build a model without ERA5 - train it on satellite data, in-situ observations, or what you will. There just isn't much point.

While all the AI models use ERA5, they don't require it.
It really is a supercomputer-free forecasting system.
March 20, 2025 at 8:20 PM
The state vector describing reality has way too many dimensions.
What else can we do?
February 11, 2025 at 9:57 AM
I won't be following up myself (the data I'm after is almost all in tables). But I do urge you to give it a go - point your browser at aistudio.google.com upload your image and start asking. It could hardle be easier to experiment with.
Google AI Studio
Google AI Studio is the fastest way to start building with Gemini, our next generation family of multimodal generative AI models.
aistudio.google.com
February 5, 2025 at 7:53 PM
And as so often it's not perfect, but it's very promising. Definitely worth looking into.
February 5, 2025 at 7:53 PM
No.

But since you ask.
I've uploaded a page from "A Collection of Voyages Chiefly in the Southern Atlantick Ocean" books.google.co.uk/books?id=sGx...

And asked Gemini a couple of questions:
February 5, 2025 at 7:48 PM
I was thinking that maybe in a couple of months there would be an upgrade to Gemini that we should experiment with.

I made insufficient allowance for 'AI time'. An update has come out today -
developers.googleblog.com/en/gemini-2-...

I don't know if it makes any difference.
Gemini 2.0: Flash, Flash-Lite and Pro
The Gemini 2.0 model family is now updated, to include the production-ready Gemini 2.0 Flash, the experimental Gemini 2.0 Pro, and Gemini 2.0 Flash Lite.
developers.googleblog.com
February 5, 2025 at 4:28 PM
All the code is available at the link, and Gemini's free tier is enough to experiment with.

Go on - give it a try.
February 5, 2025 at 4:19 PM
" We can say with some confidence that we are better at reading the logs than the original log-keepers were at writing them."

I think we are very close to being able to replace the 'we' with 'AIs'.
February 5, 2025 at 4:07 PM
Storm Darragh drawn with the Shipping Forecast — Philip's Posters
brohan.org
January 1, 2025 at 11:13 AM