@mdsumner Thanks! This is basically just me trying to understand the current landscape before I dive deeper into the cutting edge stuff from @kylebarron, @paleolimbot and @bdon. Wearing #rstats #rspatial goggles while learning some javascript on the ride. I haven't really looked into raster stuff so far, but if all goes well, I will soon enough, though coming from a climate/atmospheric modelling perspective.
Well this looks interesting!
https://cidree.github.io/duckspatial/
A little light reading for later...
Roger Bivand's presentation on Spatial economics and machine learning:
rsbivand.github.io/nem24_talk/b...
#rspatial #spatial
rsbivand.github.io/nem24_talk/biv...
New package on CRAN: {valh}, an interface between R and the Valhalla API
https://github.com/riatelab/valh
Valhalla is a routing service based on OpenStreetMap data.
https://valhalla.github.io/valhalla
Co-authored by @mthv
Felt the need to provide students with a visual summary of spatial regression models. Effective? Correct?
#rspatial
Grateful for the great resources: https://r-spatial.org/book/17-Econometrics.html and https://ruettenauer.github.io/Geodata_Spatial_Regression/05_regression-theory.html
Interestingly I had to use sf and st_intersection before I could make a "CMY set" type plot and color its different pieces...
https://github.com/geocaruso/MAGEO1642/blob/503746252822ab9cf9d04e96e91c0b4f9d4e840c/R/cmyk.R
New preprint! "Spatial Data Science Languages: Commonalities and Needs" 
Exploring challenges & insights from #Rstats #Python & #JuliaLang for spatial data handling—geodetic coords, data cubes, and more!
Read here: https://arxiv.org/html/2503.16686v1
Recently, I taught a session on landscape metrics in R—covering how to quantify spatial patterns in landscapes. 
Slides + exercises here:
https://jakubnowosad.com/rgis2025/output/landscape_metrics.html
𝘲𝘶𝘢𝘥𝘬𝘦𝘺𝘳 is now on CRAN!
Convert QuadKeys to 𝘴𝘧 dfs
Transform 𝘴𝘧 dfs to rasters
Process Fb/Meta human mobility QuadKey files → rasters
http://doi.org/10.21105/joss.06500
Thanks to #ForeSITE for the feedback 
#rstats #CRAN #rspatial
{vrtility} gets its first vignette - how to make HLS composites. I think this example really starts to show how awesome the VRT format can be and how much we can do with it! #rstats #rspatial #gdal
https://permian-global-research.github.io/vrtility/articles/HLS.html
"Spatial Data Science Languages: commonalities and needs" - that a preprint 11(!) of us wrote together as one of many outcomes of two workshops held in Münster (2023) and in Prague (2024). It summarised where we are, what we share between R, Python and Julia, what are the common challenges, lessons and recommendations - https://arxiv.org/abs/2503.16686
Big thanks belongs especially to @edzer who kickstarted the whole initiative! And to all the others who participated!
The bayesEO package provides a Bayesian approach to post-processing ML-generated images. It refines class probabilities, removes outliers, and improves labeling for more accurate classification.
Anyone know a good source for city-based polygons that's more reliable than OSM (and free)? #rspatial
WIP pkgdown site now up for {vrtility} https://permian-global-research.github.io/vrtility/
Managed to iron out a good few bugs and a bit more parallel stuff so it's starting to come together 
#rstats #rspatial #gdal
@rshean.bsky.social You can avoid running the query on buildings if you check that the city_border is actually a polygon (or more precisely not a POINT): 𝚒𝚏(!𝚜𝚝_𝚐𝚎𝚘𝚖𝚎𝚝𝚛𝚢_𝚝𝚢𝚙𝚎(𝚌𝚒𝚝𝚢_𝚋𝚘𝚛𝚍𝚎𝚛) == "𝙿𝙾𝙸𝙽𝚃"){ 𝚙𝚛𝚒𝚗𝚝("𝚌𝚘𝚘𝚕") } 𝚎𝚕𝚜𝚎 { 𝚙𝚛𝚒𝚗𝚝(𝚜𝚝_𝚐𝚎𝚘𝚖𝚎𝚝𝚛𝚢_𝚝𝚢𝚙𝚎(𝚌𝚒𝚝𝚢_𝚋𝚘𝚛𝚍𝚎𝚛)) } #rspatial
Our poster, "An Inventory of Spatial Machine Learning Packages in R" was presented at #FOSSGIS2025 in Münster.
It compares caret, mlr3, and tidymodels for spatial ML and highlights other relevant R packages.
Poster and related materials, including code: https://loek-rs.github.io/FOSSGIS2025-examples/
#rstats #rspatial #machinelearning @FOSSGISeV
Feel free to follow @random-city-bot.bsky.social for your weekly fix of "where on earth is that!?" #rstats #rspatial #geospatial
