iiinova — where your digital self keeps evolving

Frederik Kratzert @kratzert.bsky.social · 12/06/2026

"Now let me look at..." "Now I have a thorough understanding of.." "Now I have all the context I need..." "Now I have a comprehensive understanding of..." These sentences... 😅

000

Reposted by Frederik Kratzert

Daniel Munro @dkmunro.bsky.social · 01/04/2026

If the Moon were only 1 pixel - A tediously accurate scale model of the solar system. One of the best sites ever. Click. Scroll. Enjoy! joshworth.com/dev/pixelspa...

IF THE
MOON
WERE ONLY
1 PIXEL
0 km-
A TEDIOUSLY ACCURATE SCALE MODEL OF THE SOLAR SYSTEM

073

Frederik Kratzert @kratzert.bsky.social · 23/03/2026

Just be aware that the events are extracted from news sources in over 80 different languages.

000

Frederik Kratzert @kratzert.bsky.social · 23/03/2026

At this moment, we can't include the URLs but we are currently looking if we can make this information available in a future release. Be assured that the process to extract events targeted only publicly available news sources, which you should be able to find via Google search.

100

Frederik Kratzert @kratzert.bsky.social · 21/03/2026

If only a learning from the current situation would be to force push towards electrifying the grit and expanding renewables...something we could have learned already from the Russian invasion into Ukraine. But not in this country...

010

Reposted by Frederik Kratzert

hochreitersepp.bsky.social @hochreitersepp.bsky.social · 17/03/2026

xLSTM Distillation: arxiv.org/abs/2603.15590 Near-lossless distillation of quadratic Transformer LLMs into linear-time xLSTM architectures enables cost- and energy-efficient alternatives without sacrificing performance. Efficient xLSTM variants of instruction-tuned Llama, Qwen, and Olmo models.

057

Frederik Kratzert @kratzert.bsky.social · 14/03/2026

As always, thank you @kinarnicholas.bsky.social for sharing our work with your network. 🙇

000

Frederik Kratzert @kratzert.bsky.social · 13/03/2026

Seems like a pretty good fit actually.

010

Frederik Kratzert @kratzert.bsky.social · 13/03/2026

People definitely prefer my dataset publication posts over anything else I post on this homepage^^

061

Frederik Kratzert @kratzert.bsky.social · 12/03/2026

Obiously, there are tons of caveats to consider and remember, when working with news data (e.g. spatial bias, recency bias, and many more). We go on detail about this in the paper. Nevertheless, I'm convinced that you can surface event information from news articles that would otherwise not exist.

010

Frederik Kratzert @kratzert.bsky.social · 12/03/2026

Flash floods model Preprint: doi.org/10.31223/X51... Blog: research.google/blog/introdu... Operational predictions at g.co/floodhub

doi.org

AI expands high-quality urban flash flood forecasts globally

150

Frederik Kratzert @kratzert.bsky.social · 12/03/2026

Groundsource Preprint: doi.org/10.31223/X5R... Dataset: doi.org/10.5281/zeno... Blog: research.google/blog/introdu...

doi.org

Groundsource: A Dataset of Flood Events from News

231

Frederik Kratzert @kratzert.bsky.social · 12/03/2026

It was a huge team effort from any people that aren’t on BlueSky. But big shout-outs to Oleg Zyldenko, Rotem Mayo and Deborah Cohen. 🙏

110

Frederik Kratzert @kratzert.bsky.social · 12/03/2026

This however is just the beginning. The methodology can easily be extended. We're looking at extracting data beyond just verified news outlets, and expanding to other natural hazards that lack good datasets. 4/n

110

Frederik Kratzert @kratzert.bsky.social · 12/03/2026

But We aren't just releasing data. We also shared details about our new flash flood forecasting model that was trained flood events data from Groundsource. This allows us to better predict flash floods up to 24 hours in advance. 3/n

110

Frederik Kratzert @kratzert.bsky.social · 12/03/2026

We used Gemini to extract locations & times of past floods from unstructured global news reports in 80 langauges. The locations were further georeferenced. The result? 2.6 MILLION historical events across 150+ countries. 🌎 2/n

120

Frederik Kratzert @kratzert.bsky.social · 12/03/2026

Excited to announce Groundsource - an open-source dataset of historic flood events! This has easily been one of the coolest projects I've worked on recently! Thread 🧵 for details and all relevant links. 1/n

A worldmap of the spatial distribution of extracted flood events in the Groundsource dataset. The map displays the total number of flood events extracted by the LLM-based pipeline aggregated per grid cell. The data are visualized using a Robinson projection, with event counts represented by a logarithmic color scale. Red points indicate the spatial centroids of reference flood events from the GDACS database.

27339

Reposted by Frederik Kratzert

Joel Boerckel @jboerckel.bsky.social · 05/02/2026

I present the most interesting graph ever made. HUMAN ON BICYCLE beats every other living thing. www.scientificamerican.com/article/a-hu...

1822577

Frederik Kratzert @kratzert.bsky.social · 23/01/2026

Interesting read and something I have been thinking about recently. How fit is our education system for the new era and what does this mean for _learning_ (especially learning to learn), if students/pupils over rely on LLMs. What does this mean for my kids (2nd grade and kindergarten)...?

010

Frederik Kratzert @kratzert.bsky.social · 18/01/2026

What are your thoughts on this article. It also has been a while since I came across Tim's name, but I remember from my early days of ML how he was already publishing hardware benchmarks for ML setups and that I read them carefully whenever I upgrade my home setup.

110

Frederik Kratzert @kratzert.bsky.social · 14/01/2026

Some updates on NeuralHydrology and I'll also use this opportunity to give a shout-out to @gauchm.bsky.social for his continuous support and maintenance of NH

011

Reposted by Frederik Kratzert

Thiago Nascimento @thiagovnascimento.bsky.social · 22/10/2025

Are you working in large-sample hydrology? If so, we invite you to submit an abstract to our session for EGU 2026: HS2.4.2 "Large-Sample Hydrology: Advancing dataset developments, enhancing process understanding, and unifying insights through catchment modeling"

084

Frederik Kratzert @kratzert.bsky.social · 05/01/2026

Or, if your model outputs uncertainty bounds, at least you learn/model the uncertainty of the task that you care about.

110

Reposted by Frederik Kratzert

Daniel Klotz @danklotz.bsky.social · 01/01/2026

For those of you who are still undecided.

031

Frederik Kratzert @kratzert.bsky.social · 01/01/2026

We (wife, 7 y/o, myself) spent New Years Eve playing "Stuffed Fables" boardgamegeek.com/boardgame/23... My wife's first roleplay game and also the most complex game we played so far with our oldest. Time was flying and we only made it to the start of the second chapter 😅

boardgamegeek.com

Stuffed Fables

Live the story of a child's stuffed toys, saving her from monsters under the bed.

050

Frederik Kratzert @kratzert.bsky.social · 31/12/2025

No, I was not thinking about FM models in this context. One easy example: if you want a model that forecasts flood warnings, why train the model to predict streamflow? Under ideal conditions, you could simply train the model to forecast "send alert/ no alert"

120

Reposted by Frederik Kratzert

KinarNicholas.bsky.social @kinarnicholas.bsky.social · 30/12/2025

Hydrology Paper of the Day @kratzert.bsky.social on integrating water quality observations into the Caravan dataset: the need for proper metadata and processing of observations; a new river network with water quality stations; catchment delineation; and validation and flagging of suspect data.

0112

Frederik Kratzert @kratzert.bsky.social · 30/12/2025

Interesting point. I've been thinking about this as well in the past and I think, especially with ML, we have the opportunity to optimize for what we really want to know from the model, instead of training it on some proxy task

120

Reposted by Frederik Kratzert

Matt Stark @mattstark256.bsky.social · 31/08/2024

since everyone in Brazil's lost Twitter, I'm gonna try to make sure anything I post there is posted here too 🥲 here's a free building game I shared there a few weeks ago! mattstark.itch.io/tramstertram

game screenshot showing an amsterdam-like city with the title "tramstertram" above it

03114

Frederik Kratzert @kratzert.bsky.social · 26/12/2025

Very cool. Congratulations and surely deserved 💐

110

Reposted by Frederik Kratzert

dame @dame.is · 26/12/2025

the success of the user-created For You feed while the official Discover feed flops is actually a pretty major win for Bluesky — it literally is the embodiment of their goal to decentralize feed generation and give users more control/autonomy

933558

Frederik Kratzert @kratzert.bsky.social · 23/12/2025

Kid #2 got sick in time for Christmas and it seems I caught whatever he has, too. For the last three years we had at least one kid sick at Christmas. Happy Holidays 🎄

010

Reposted by Frederik Kratzert

Frederik Kratzert @kratzert.bsky.social · 18/12/2025

Excited to unveil Caravan-Qual! 🌊 We've expanded the Caravan framework to bridge the gap between water quantity and quality. This new open dataset features: 🔹 ~70M observations 🔹137k stations 🔹 100 constituents 🔹 Linked streamflow, forcing & attributes Links in 🧵

A world map with red and blue dots. Each dot denotes a water quality measurement station that is included in Caravan-Qual. Red dots are stations with additional streamflow observations. Blue dots are stations without streamflow observations.

22612

Frederik Kratzert @kratzert.bsky.social · 19/12/2025

All credits for data collection and standardizing go to Ed. He did all of the hard work!

010

Reposted by Frederik Kratzert

John Hammond @hydrohammond.bsky.social · 18/12/2025

@rarakihydro.bsky.social leads an exiting new preprint that maps dominant hydrologic processes across >14k US watersheds using streamflow signatures + ML. It’s been such fun following Ryoko and Hilary’s leadership alongside Admin, Anne and Gemma. egusphere.copernicus.org/preprints/20...

1156

Frederik Kratzert @kratzert.bsky.social · 18/12/2025

It is so wild how all academics seem to have decided that LinkedIn is the new platform. Essentially the same announcement receives 100x the engagement.. On a job market platform. In the good old days of Twitter, this was different and it's kinda sad that not more researchers decided to join BlueSky

060

Frederik Kratzert @kratzert.bsky.social · 18/12/2025

22612

Frederik Kratzert @kratzert.bsky.social · 14/12/2025

First time in years that I won't attend #AGU Inspiring week for everyone who attends and I hope you all stay safe.

030

Frederik Kratzert @kratzert.bsky.social · 04/12/2025

This looks amazing 😲 Deserved first bookmark on bluesky

130

Reposted by Frederik Kratzert

Martin Gauch @gauchm.bsky.social · 03/12/2025

Back by popular demand: At #EGU26 we'll organize another BUGS session: Blunders, Unexpected Glitches, and Surprises! Submit abstracts on ideas that seemed great but didn't work, errors and bugs that led to new insights (or funny stories), or any other unexpected results. www.egu26.eu/session/56997

1138

Frederik Kratzert @kratzert.bsky.social · 03/12/2025

Quick shout-out for an #EGU26 session that I'm not involved in but think is worth sharing: EOS4.4 BUGS: Blunders, Unexpected Glitches, and Surprises For a detailed session description, see www.egu26.eu/session/56997

egu26.eu

Session EOS4.4

010

Frederik Kratzert @kratzert.bsky.social · 22/11/2025

Wow, so cool. Congratulations to her achievement

010

Frederik Kratzert @kratzert.bsky.social · 20/11/2025

What do people do when their taxi driver is a) speeding like crazy and b) interacting with his phone all the time while driving. Not sure if I'm unlucky but this happens 4/5 times to me when taking the airport taxi back home...

000

Frederik Kratzert @kratzert.bsky.social · 15/11/2025

It has been a while since the last news from Caravan but I'm happy to announce that a new extension has just been published. Caravan-CZ, a dataset curated by CHMI itself in cooperation with Grey Nearing. For details check: github.com/kratzert/Car... All extensions: github.com/kratzert/Car...

github.com

[DATA CONTRIBUTION] CAMELS-CZ]: Catchment Attributes and Meteorology for Large-Sample Studies -- Czechia · Issue #49 · kratzert/Caravan

Basin prefix camelscz Zenodo DOI https://zenodo.org/records/17593968 Number of catchments 249 Location of catchments Czechia For which periods are streamflow records available in your dataset? 1950...

070

Frederik Kratzert @kratzert.bsky.social · 15/10/2025

jax.config.update("jax_debug_nans", True) saved my day.

020