Jakub Nowosad
LightNews LightNews
banner
jakubnowosad.com
Jakub Nowosad
@jakubnowosad.com
4.9K followers 45 following 170 posts
Computational geographer. Associate Professor at AMU, Poznan, Poland. Co-author of http://r.geocompx.org, http://py.geocompx.org, and http://tmap.geocompx.org books. #rstats #rspatial #geocompx

https://jakubnowosad.com/
Posts Replies Media Videos
jakubnowosad.com
The spcosa package provides an R framework for spatial coverage sampling.

Explore examples at git.wur.nl/Walvo001/spc...

#Rstats #RSpatial #GIS #SpatialStatistics
December 22, 2025 at 2:03 PM
jakubnowosad.com
✨What’s new in geocomputation this year?

The #geocompx 2025 update covers project milestones, current work, and future plans.

URL: geocompx.org/post/2025/up...

#rstats #rspatial #geopython
December 21, 2025 at 2:00 PM
Reposted by Jakub Nowosad
kylewalker.bsky.social
Introducing {geosam}: an R toolkit for Meta's Segment Anything Model 3

- Detect objects in satellite imagery with text prompts
- Interactive Shiny tools with draw & click-to-identify
- Works with Mapbox, Esri, MapTiler
- Use regular images too!

walker-data.com/geosam/
December 17, 2025 at 5:23 PM
jakubnowosad.com
🚀 Exploring COGs (Cloud‑Optimized GeoTIFFs) in R with the terra package (e.g., visualizing the internal tile structure).

See: guide.cloudnativegeo.org/cloud-optimi...

#RStats #RSpatial #Geospatial #CloudNativeGeo #GISchat
December 17, 2025 at 2:02 PM
Reposted by Jakub Nowosad
drxeo.eu
🚨 New #DataViz post!

I explore smart alternatives to a broken chart and highlight why avoiding bad practices matters.

👉 Which alternative do you prefer? Let us know in the comments!

#rstats

dominicroye.github.io/blog/2025-12...
Broken Chart: discover 9 visualization alternatives
Researcher in climate science at MBG-CSIC
dominicroye.github.io
December 15, 2025 at 9:02 AM
jakubnowosad.com
🌍 Recently I gave a brief intro talk on three connected deep learning concepts: GNNs, embeddings, and foundation models.

URL: jakubnowosad.com/agforum2025

The slides include reproducible R examples showing how each concept works in practice.

#geoAI #RSpatial #gischat
December 15, 2025 at 2:02 PM
jakubnowosad.com
A growing list of 2026 geospatial conferences is live 🌍

URL: github.com/Nowosad/conf...

If you know of additional GIS or remote-sensing events, please contribute. PRs and suggestions are welcome.

#GISchat #Geospatial #SpatialData #Conferences2026
December 14, 2025 at 2:01 PM
Reposted by Jakub Nowosad
dariia.bsky.social
❗️Our next workshop will be on Jan 8 , 6 pm CET titled Inference for non-probability samples with nonprobsvy package in R by
@mberesewicz.bsky.social

Register or sponsor a student by donating to support Ukraine!
Details: bit.ly/3wBeY4S
Please share!
#AcademicSky #EconSky #RStats
December 12, 2025 at 9:01 AM
Reposted by Jakub Nowosad
kylewalker.bsky.social
It had to be done.

Geospatial tools for @Meta's Segment Anything Model 3 are coming to R.

Shown: @TCU's football stadium as an sf polygon.

Extracted with SAM3 from the second image with the prompt "football stadium".

Keep an eye out here for updates and a package release.
December 9, 2025 at 11:11 PM
jakubnowosad.com
David O’Sullivan explores population quadtrees in R: iteratively bisecting New Zealand’s population into equal population rectangular areas.

URL: dosull.github.io/posts/2025-0...

#RStats #RSpatial #GISchat
December 10, 2025 at 2:04 PM
jakubnowosad.com
Call for papers: Coding Earth — Open Source Solutions in Physical Geography for Progress in Physical Geography ⚡

Show how open-source tools, coding workflows, and open science are reshaping physical geography.

journals.sagepub.com/pb-assets/PD...

Deadline: 1 March 2026.

#GISchat
December 9, 2025 at 2:02 PM
jakubnowosad.com
🌱 Want to calculate growing degree days (GDD) in R?

The pollen package supports three different GDD methods, letting you explore heat accumulation for plant & animal development.

Examples: jakubnowosad.com/pollen/artic...

#rstats #Ecology #Phenology
December 7, 2025 at 2:01 PM
jakubnowosad.com
New in gdalraster 2.2.0 🎉

You can now run GDAL CLI algorithms (e.g., gdal raster calc) directly from R -- thanks to the new GDAL 3.11 unified CLI.

Docs: usdaforestservice.github.io/gdalraster/a...

#RStats #RSpatial #GDAL #OSGeo
December 3, 2025 at 2:02 PM
Reposted by Jakub Nowosad
kurtschwehr.bsky.social
2025 GDAL User Survey is now active for the entire month of December! Visit gdal.org/survey/ & tell the project how you use it, where you get help, what it should do in the future, & how/if it should use LLMs going forward. (optionally) give us your email, we'll even enter you to win a GDAL t-shirt!
2025 GDAL User Survey
In 2024, the GDAL User Survey solicited feedback to help focus GDAL Sponsorship Program activities. Your contribution mattered. Last years' results triggered the project to embark on the GDAL CLI Mode...
gdal.org
December 1, 2025 at 3:32 PM
jakubnowosad.com
🌍 How trustworthy are your spatial predictions?

In my talk for the Rome R Users Group, I showed practical ways to evaluate where spatial predictions are trustworthy, and where they aren't.

Slides: jakubnowosad.com/rome2025
Video: youtu.be/uZe7thh80MI

#RSpatial #RStats #GISchat #SpatialModelling
Cover slide
December 1, 2025 at 2:00 PM
Reposted by Jakub Nowosad
robinlovelace.bsky.social
Happy to see new newest member of the #geocompx family up on the geocompx.org website: Spatial Data Visualization with tmap is an awesome book that is still in progress 🏗️ Well worth a read to launch your reproducible map making journey 🚀
November 28, 2025 at 3:24 PM
jakubnowosad.com
🚀 Tomorrow’s the day! (Thu, Nov 27 (6 PM CET))

We’ll explore practical workflows for geospatial predictive mapping in R: covering interpolation, machine learning, and strategies to make spatial predictions more reliable.

Details: www.meetup.com/rome-r-users...

#RStats #GISchat #RSpatial
R for geospatial predictive mapping, Thu, Nov 27, 2025, 6:00 PM | Meetup
**R for geospatial predictive mapping: practical workflows for reliable spatial predictions** This talk introduces practical workflows for building reliable spatial predic
www.meetup.com
November 26, 2025 at 5:05 PM
jakubnowosad.com
🔍 David O’Sullivan explores how to generate random points on the globe in R -- from uniform random to Halton sequences and blue-noise sampling.

Read more: dosull.github.io/posts/2025-0...

#RStats #RSpatial #GISchat
November 25, 2025 at 2:04 PM
Reposted by Jakub Nowosad
robinlovelace.bsky.social
Is it possible to teach an Introduction to Data Science course in 3 hours? I will find out soon!

You can too if you attend the course this Friday as part of the MSc at the Institute for Transport Studies (ITS) in Leeds. You can also attend remotely, watch this space for #openaccess materials 🚀
November 25, 2025 at 10:31 AM
Reposted by Jakub Nowosad
rfortherestofus.com
This week on What's New in R, we're featuring:
✅ A dive into {ggplot2}’s geoms and stats by @mattansb.msbstats.info
✅ New book on spatial data viz. by @jakubnowosad.com & Martijn Tennekes
✅ Demo of AI features in Positron by @ryjohnson09.bsky.social

Read the issue: buff.ly/bA4ar3v

#rstats
November 24, 2025 at 3:04 PM
Reposted by Jakub Nowosad
fubits.dev
I‘m super happy with working in @marimo.io. The reactivity + UI components make spatial work fun as well and can be combined with most of your bullet points. bsky.app/profile/fubi...
fubits.dev Ilja @fubits.dev · Aug 13
For real, @marimo.io feels like Svelte but for Python. Surreal DX (even on mobile).
Screenshot of a Marimo Notebook rendering a raster map with additional UI elements for color map and opacity)
November 23, 2025 at 2:22 PM
Reposted by Jakub Nowosad
kylewalker.bsky.social
By the way, this is all you need to create the map in the video:

library(rnaturalearth)
library(tmap)
library(tmap.mapgl)

tmap_mode("maplibre")

tm_shape(countries110) +
tm_polygons(
"INCOME_GRP",
fill_alpha = 0.7,
popup.vars = c("NAME", "GDP_MD", "INCOME_GRP")
)
November 22, 2025 at 6:18 PM
Reposted by Jakub Nowosad
kylewalker.bsky.social
For Day 22 of #30DayMapChallenge, Natural Earth, a shout-out to Martijn Tennekes and the tmap.mapgl package.

tmap.mapgl wraps mapgl, allowing you to make performant interactive maps with the same tmap syntax you know and love!

Try it out: r-tmap.github.io/tmap.mapgl/i...
November 22, 2025 at 6:18 PM
jakubnowosad.com
Chapter 8 of Geocomputation with Python is all about cartography:

🎨 Designing maps
🖼️ Static maps with .plot & rasterio.plot.show
🌐 Interactive maps with .explore

👉 py.geocompx.org/08-mapping

#GeoPython #Python #GISchat #geocompx
8  Making maps with Python – Geocomputation with Python
An introductory resource for working with geographic data in Python
py.geocompx.org
November 23, 2025 at 2:01 PM
Reposted by Jakub Nowosad
urbandemog.bsky.social
I would add WebGL-based visualization libraries (e.g. #deckgl and #mapgl). They are not exactly super new but they're really centraly in how spatial data science has changed over the past 10-ish years.

ps. #GeoParquet, and #DuckDB + spatial ! would also be at the top of my list!
jakubnowosad.com Jakub Nowosad @jakubnowosad.com · Nov 19
What are the most exciting trends you’re seeing in spatial data science lately?
Some of mine:

- New file formats (e.g. #GeoParquet)
- Geospatial DBs (e.g. #DuckDB + spatial)
- Global discrete grids

What would you add?

#Geospatial #GISchat #RSpatial #GeoPython
A discrete global grid (DGG) is a mosaic that covers the entire Earth’s surface. Mathematically it is a space partitioning.
November 19, 2025 at 9:57 PM