_The Evening Post_, 14 March 1925:
The Wireless World
…
A TIMARU EXPERIENCE
During a holiday in the South, "Grid-Bias" called on a #Timaru amateur, who demonstrated the character of reception in that town.…Static put on one of its finest performances…. In spite of the din, the party listened to 1YA, 2YK, 2YM, KGO, 2BL, and 2FC…. The strength of KGO, second only to that of 2YK, was remarkable. A curious feature of the performance was that 2BL, Sydney, was as strong as 2FC, and at times stronger. The apparatus used [technical details follow].… The owner states that in the winter he regularly receives 2YK and 4YA on a short indoor aerial. This is a ridiculous appendage to the set—about four yards of copper strip suspended across the room. The Timaru amateur takes his hobby seriously. Besides using his apparatus consistently for entertainment, he is systematically recording the weather and radio reception conditions, particularly the nature and intensity of static.… The nature of the static observed on a given date and the weather which follows may suggest similar weather after a similar outburst of atmospherics; and… may be found very useful in the work of weather experts.
https://paperspast.natlib.govt.nz/newspapers/EP19250314.2.146.3
#weatherforecasting
"What NOAA has is a truth the GOP doesn’t want anyone to see. NOAA is one of the foremost research agencies in the field of Climate Change. They collect much of the vital data, but also tell the story of anthropogenic climate change, well, and deeply, with receipts.
Here is NOAA’s mortal sin: their message is comprehensive, clear, and backed up with many, many studies. NOAA is easy to access for anyone in the world. This little slice of the federal government is telling on our crimes against nature, and the GOP doesn’t like that.
Without miraculous intervention, NOAA may be doomed in the coming weeks and months. I hope, and expect, that the people at NOAA are archiving its vast trove of potentially civilization-preserving records they’ve collected over the decades, to keep it from being destroyed by this insane GOP. I also hope companies and other governments will scoop up these people and get them back to their work — the work of preserving our comfortable Holocene civilizations on Planet Earth."
https://www.emptywheel.net/2025/03/06/noaa-the-biggest-little-agency-in-america/
Scientists at U.S. weather forecasting agency ordered to get clearance before talking to Canadian counterparts
Travelling for international meetings or even joining a call with Canadian counterparts has become impossible for some #USGovernmentScientists, under new directives since U.S. President #DonaldTrump took office.
Canadian ecologist Aaron Fisk says he recently tried to set up a virtual call to discuss plans with American colleagues, including a government scientist, around sampling fish.
"We tried to have a quick meeting with one of our collaborators … and they were denied access," Fisk said.
#ScienceMastodon #WeatherForecasting #UnitedStatesWeatherForecastingAgency #Canada #AmericanFascism #Environment #Weather
https://www.cbc.ca/news/science/trump-american-scientists-international-engagements-1.7461238
New blog post!
There's a new Python package on PyPi, it's about forecasting the weather, and I am the author!
In the blog post I am talking about my first time publishing to PyPi, how stressful is to show one's work publicly, but also to show how easy it is to be a part of PyPi.
https://stfn.pl/blog/52-published-my-first-python-package-to-pypi/
We're hiring at dmi.dk 
! If #deeplearning and high-resolution #weatherforecasting sounds exciting to you, come to DMI and work with me and the rest of the group to build the first operational graph neural-network km-scale weather model (https://candidate.hr-manager.net/ApplicationInit.aspx?cid=5001&ProjectId=182511&DepartmentId=10154&MediaId=5).
You’ll be building on https://github.com/mllam/neural-lam and https://github.com/ecmwf/anemoi-models, creating the state of the art!
Deadline 15th Sep
Details on https://candidate.hr-manager.net/ApplicationInit.aspx?cid=5001&ProjectId=182511&DepartmentId=10154&MediaId=5
Feel free to get in touch if you have any questions and please share!
@lowqualityfacts 
Finally, a legitimate use for AY -- Ayahuasca!
#Ayahuasca, #WeatherForecasting, #LowQualityFacts, #TuckersBalls
You can read about our existing efforts to develop and run a global ML #WeatherForecasting system, AIFS, here: https://www.ecmwf.int/en/about/media-centre/aifs-blog. This is part of a wider programme to expore ML in weather forecasting alongside hybrid approaches that combine ML with existing techniques as part of the forecast chain. From June we'll begin a second phase of the EU-funded Destination Earth project, which will include new additional funding for machine learning, so we're able to expand our efforts.
Yesterday the Danish Meteorological Society had a talk and discussion on #AI in #weatherforecasting. It's a big area that DMI (cc @leifdenby ) is also investigating, + in #PRECISE_NNF project we're developing a #climate + #iceSheet variant. I missed this before but @voooos piece here is an excellent primer...
https://sciencemastodon.com/@voooos/111426572785565467
voooos@sciencemastodon.com - For background, here's our Science story from earlier this week explaining the explosive growth in weather AI: https://www.science.org/content/article/ai-churns-out-lightning-fast-forecasts-good-weather-agencies
This is great news for farmers in France! Data and forecasts from Météo France weather stations will be freely accessible after the start of the New Year. You will be able to mine the data to calculate frost risks, heat accumulation and could use it to forecast disease infection periods as well as much more!
https://meteofrance.fr/actualite/presse/au-1er-janvier-2024-donnees-publiques-en-acces-libre
Science writer Kara West explains why computer models aren’t keeping pace with the changing climate. #snow #dust #climate #weatherforecasting https://eos.org/articles/dust-is-melting-snow-and-current-models-cant-keep-up
Challenges I learned about in two years of machine learning in weather forecasting
A little over two years ago, I dove into the world of machine learning in weather forecasting.
I was convinced that machine learning could revolutionize this field.
Forecasting the weather saves lives, saves money and keeps people happy, but there are SO many challenges!
Imagine this: weather forecasts that could accurately predict the path of a hurricane, provide precise details on the formation of thunderstorms, and anticipate localized events like flash floods.
These were the ambitious goals we set out to improve with machine learning.
TURNS OUT ML IN WEATHER FORECASTING IS HARD
But as we embarked on this journey, the hurdles grew taller, and the challenges more daunting.
What I discovered was that applying machine learning to w...
#MachineLearning #WeatherForecasting
Find more here: https://dramsch.net/articles/challenges-in-two-years-machine-learning-weather-forecasting/
_The Evening Post_, 14 Oct 1922:
INLAND WEATHER STATIONS
Suggestions that the Marine Department should establish more inland meteorological stations so that information of value to farmers might be secured were made in the House of Representatives by Mr. T. D. Burnett (Temuka) yesterday. Mr. Burnett mentioned the need for a station in Central Otago, another at the Mount Cook Hermitage, and a third at Lake Coleridge. The Hon. G. J. Anderson replied that the needs of the Marine Department were met by the stations on the coast, but he could quite see the value of inland stations to the farmer. He suggested that Mr. Burnett should collaborate with other members interested, and then put before him the positions at which it was thought desirable to establish stations. He would have to have an assurance, too, that there were people willing to attend to the instruments daily.
https://paperspast.natlib.govt.nz/newspapers/EP19221014.2.45.5
#OnThisDay #OTD #PapersPast #Meteorology #WeatherForecasting #Agriculture
Making weather forecasting machine learning models operational!
As a team at ECMWF we have open-sourced "ai-models" and plugins for all the major open-source data-driven NWP models:
FourCastNet v2 with spherical harmonics by NVIDIA
PanguWeather 3D transformer by Huawei
GraphCast multi-mesh graph neural network by Google DeepMind
View them on the ECMWF website with the charts you know.
Or even run them yourself! pip install ai-models-fourcastnetv2 pip install ai-models-panguweather pip install ai-models-graphcast
These are all open-source plugins that make it easy to load data from MARS if you have access, CDS, or your own grib files.
Super proud of our work so far and that we can run these alongside our physical model now as a service to the weather community.
Also, can we talk about running, ONNX, Pytorch, and Jax for this? Now just waiting for a Tensorflow model to fill my Pokedex. 
#MachineLearning #WeatherForecasting #DeepLearning #MLOps #Tech
(Pst, we're hiring btw! 
)
This is fascinating - the rise of #MachineLearning models for #WeatherForecasting.
A very exciting field right now!
The improvements in #weatherForecasting in the last 20-30 years are sometimes called "the quiet revolution" - not just improved resolution and processes but especially data assimilation of satellite and ground observations have been key..