#30DayMapChallenge Day 23: Process 🔧 Geospatial embedding datasets allow us to quickly do fairly sophisticated analyses quickly and at a large scale. To make this map, I used the AlphaEarth embeddings dataset in #GoogleEarthEngine to detect changes. Blog post in replies ⬇️

#30DayMapChallenge Day 6: Dimensions ⛰️ The Vredefort Dome is what is left of one of the largest asteroids to have hit earth, approximately 2 Billion years ago. I was inspired by @725hemeed.bsky.social and @hellovizart.bsky.social's beautiful 3D maps, and I used Blender and QGIS to create this.

#30DayMapChallenge Day 4: My Data 🏃 My coping mechanism with the lockdown was running, and here I visualise all my runs between 2020 and 2021, culminating in me running the Berlin Marathon. I downloaded my running data using the garminconnect Python package, QGIS for layout.

It's only AI if it's from the AI region in France, otherwise it's just sparkling Machine Learning.

Physics students are told their degree is a ticket to anything but during their time at university, it's rarely elaborated on. So Toni Feder has gone out and interviewed physicists with varied careers away from the field (Posts the physicist whose job title is digital experience director...)

Can multi-sensor foundation models be more than the sum of their parts? Blog post here: fnands.com/blog/2025/mu...

A quick look at GPU programming in Mojo: fnands.com/blog/2025/fi...