To give you a glimpse into the vast image data that #ESAEuclid is observing in its surveys, #ESA published a new set of images: a section of 2 weeks of observations, 132 deg² on the sky, that's 500x the area of the Moon, and zoom-ins.

Check out the images in our Euclid Blog, where you can also find a link to ESA's full release with high-res images and all explanations and background.

https://www.euclid-ec.org/euclids-first-large-piece-of-the-sky

#astronomy #astrodon #space #cosmology

https://www.youtube.com/watch?v=rl9FShX0mws

what? The Simpsons became reality.

We have (finally!) released @geopandas 1.0 today. While the release notes are long and full of exciting stuff, the most important from my perspective of a maintainer is a massive cleanup of internal handling of geometry engines. It was a bit pain lately.

A short reflection on that which wouldn’t fit in a toot - https://martinfleischmann.net/geopandas-1.0-is-out/

And a post I wrote when we released 1.0a1, highlighting things that have a potential to break stuff downstream - https://martinfleischmann.net/geopandas-1.0-is-coming.-what-will-change/

Please report bugs! 🐛

I've created a basic app for searching an aerial photo using text queries. That's right, you can search for "roundabout" or "school playground" on an image of a city and get pretty good results!

Have a play with it here: https://server1.rtwilson.com/aerial - it's set up with an aerial image of Southampton, UK

Under the hood this uses the SkyCLIP model and the Pinecone vector database.

#geospatial #ai #vector #ml #embedding #gis #remotesensing #aerial #python