Michael Szell boosted:
2026-02-05
Winter landscape above cargo bike on Copenhagen RådhuspladsenWinter landscape above cargo bike on Copenhagen Rådhuspladsen
Michael Szell boosted:
2026-02-03

Just published in JOSS: 'GeoAI: A Python package for integrating artificial intelligence with geospatial data analysis and visualization' doi.org/10.21105/joss.09605

2026-02-03
2026-01-30

@kagihq Wow, this looks interesting. Does it work like google #scholar, listing only publications/preprints? What sources are indexed? Many researchers are looking for alternatives to google scholar..

Michael Szell boosted:
Hans van der Kwast :qgis:hansakwast@fosstodon.org
2026-01-30

I’m launching #QwastTube: a #PeerTube‑based, privacy‑friendly alternative to my YouTube channel.
If you care about digital sovereignty and open‑source GIS, this is for you.

I’m still importing videos, but it’s already live:

👉 videos.qwast-gis.com

YouTube will stay in sync for now, but I hope you’ll join me on the fediverse.

#PeerTube #Fediverse #OpenSource #GIS #QGIS #DigitalSovereignty

2026-01-27

@jankamensky Deine Videos sind super-cool, auch für die Wissenschaft! ❤️ youtu.be/yGW2TsV-LDA?si=5dEay-

Am besten hashtags folgen und dann Leuten. Zb #verkehrswende #cycling #motonormativity

Michael Szell boosted:
Jan Kamensky 𝚄𝚃𝙾𝙿𝙸𝙰𝙽jankamensky
2026-01-27

ARD-Doku „Kraftfahrzeug – Eine deutsche Liebe“ jetzt in der Mediathek:

ardmediathek.de/film/Y3JpZDovL

Ein Ausschnitt meines Interviews unten im Video.

Schönen Dank an @jantenhaven für diesen Film „zwischen PS-Träumen und Protestkultur“!

@SheDrivesMobility
@www.daserste.de @NDR

Michael Szell boosted:
2026-01-25

Use this virtual slime mold simulator to build a subway map for your city.
googlemapsmania.blogspot.com/2

Michael Szell boosted:
2026-01-22
The new unified citation dialog in Zotero 8, with buttons to switch between inserting items and inserting notes and between List and Library modes
Michael Szell boosted:
2026-01-22

We are very pleased to announce the release of pandas 3.0.0! 🚀🥳

This major release brings some exciting new features, including:
- a new default string data type
- consistent copy/view behaviour
- changed default resolution for datetime data
- initial support for pd.col() syntax
- ...
alongside many other improvements and bug fixes. But those also come with some potentially breaking changes.

See the blogpost at pandas.pydata.org/community/bl for more details

2026-01-21

@AndrzejWasowski Jeszcze Grenlandia nie zginęła..

2026-01-21

@ai6yr Be aware that such bot sign-up messages sometimes are tailored to reference the instance and its focus, see image, which can be harder to detect than a general-purpose template. #mastoadmin

Hi! I’m interested in joining datasci.social because I work in or have a strong interest in data science, machine learning, and analytics. I enjoy discussing techniques, sharing insights, learning from others’ experiences, and keeping up with trends in the field. I value respectful, well-moderated communities and plan to follow the instance rules while contributing positively.
Michael Szell boosted:
2026-01-20

Ich habe mir diese Woche den dreiteiligen #ARTE Dokumentarfilm von Cédric Tourbe über den amerikanischen Kapitalismus angesehen:

"Reichtum als Kult"

arte.tv/de/videos/103517-001-A

Wirklich sehenswert für alle, die verstehen wollen, warum der heutige Wahnsinn keine Anomalie, sondern die logische Konsequenz einer Weltsicht ist, die grundsätzlich durch Gier, Ungleichheit und Klassenkampf von oben herab getrieben wird.

Michael Szell boosted:
Martin Fleischmannmartinfleis@fosstodon.org
2026-01-19

New package: gwlearn (because I just can't help myself I guess)

It provides a framework for geographically weighted modeling by bridging scikit-learn with libpysal. You can basically wrap standard sklearn estimators (regression or classification) to make them spatially explicit using local weights. What is super cool, is that you can define your own neighbourhoods and fit models across those, breaking the Euclidean distance cage.

Docs: pysal.org/gwlearn/stable/ Repo: github.com/pysal/gwlearn

2026-01-18

@christianp Nice, just made a similar post inspired by yours. It's good if more #mastoadmin s make a collective effort at this.

2026-01-18

My posts are currently mirrored across to bluesky by brid.gy. Not sure I will continue, due to bluesky welcoming #ICE.

For people on bluesky who see this and want a place that doesn't encourage fascism: Have a look at datasci.social

2026-01-12

Mind the gap: Revealing sidewalk networks at scale
pdf: iopscience.iop.org/article/10.

Nice to see important research on the both most important and neglected mode of transport 🚶

Figure 2. Schematic pipeline of the network construction process. The deep learning stage (a-c)
begins with (a) tiling high-resolution aerial imagery (5000 × 5000 pixels) into smaller patches (512 × 512
pixels), which are fed to (b) a segmentation model (DeepLabV3). This model generates (c) binary output
masks identifying sidewalk pixels. The masks are then reassembled to reconstruct the full segmented tile. In
the network construction stage (d-f) the merged predictions undergo a (d) binary closing to fill gaps, (e)
skeletonization to reduce the sidewalk predictions to their centerlines, and (f) generation of the network (nodes
and edges). Finally, these tile-level results are integrated to produce a large network across the entire urban
area
Michael Szell boosted:

"In China, driverless delivery vans have become a total meme, they plow through crumbling roads, fresh concrete, motorcycles, anything. Nothing stops them."

Michael Szell boosted:
Anita Graser 🇪🇺🇺🇦🇬🇪underdarkGIS@fosstodon.org
2026-01-11

Finally it's here: Jupyter notebooks inside QGIS. I don't know about you but I've been hoping for someone to get around to doing this for quite a while.

HT @giswqs via @hansakwast

anitagraser.com/2026/01/10/not

Client Info

Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst