850,000 parcels in New York City. All visualized on an interactive map in 3D by estimated market value per square foot. Filtered dynamically in the browser with an interactive legend.

Our beloved Claude - even with access in this case to multiple years of conversations with me about mapping - defaults to a year-and-a-half-old release of MapLibre. A large percentage of people using AI uncritically are actually 18 months behind. Use this to your advantage.

A personal and professional goal of mine is to always be using and developing tools that Claude doesn’t know about yet by default

This is why I'm so excited about my new R/Python package, {freestiler}. I connect to a 146M row @duckdb.org database; generate vector tiles for 2.8 million jobs in CO from a query; serve the tiles and visualize on a @maplibre.org map. All in seconds! Get started: walker-data.com/freestiler

I work with AI agents daily. It is becoming more and more difficult to tell between when answers look right and are right, and when they look right and are wrong. Even more difficult: when answers look right but are suboptimal. Take the human out of the loop at your own risk.

An irony that's not lost on me: My older R packages that I wrote by hand have limited to no test coverage, in large part because of how time consuming it is to write tests, whereas; My newer, LLM-assisted R packages have comprehensive test coverage

Another update to R's spopt-r package: you can specify "required" and "candidate" facilities in max coverage / location-allocation solvers Brief demo: choosing the best new fire stations from candidate points in Fort Worth Same functionality here as ArcGIS's Network Analyst

I tend to be a CRAN-appreciator. But wow, R-Universe is such a useful project. As a developer, I can: - Experiment with new and creative approaches that would never get accepted on CRAN; - Have cross-platform binaries for my packages built within an hour (usually) of a GitHub push

New in the spopt-r #rstats package: route optimization. Solve the classic Traveling Salesman Problem for a single driver or optimize a fleet by solving the Vehicle Routing Problem. Written in Rust so they solve fast. Read the vignette which covers r5r integration: walker-data.com/spop...

If you are using AI the right way, it should make your job harder, not easier.

All 8.1 million US Census blocks. Visualized smoothly in 3D. Instant population and housing totals from a lasso selection. All running seamlessly in the browser, no traditional backend. While everyone’s talking about AI, it’s an incredible time for geospatial tech.

368,000 miles of Texas pipelines across nearly 500,000 line segments visualized in @maplibre.org as vector tiles. With {freestiler}, the tiling process took under 15 seconds. Infrastructure data meets modern geospatial tooling.

Incredible day 1 response and feedback to my new vector tile engine, freestiler. Several of you asked for an easier way to serve and map vector tiles. freestiler now has a built-in local tile server along with a new mapping vignette. Check it out: walker-data.com/free...

Announcing {freestiler}: a high-performance vector tiling engine for R and Python. Generate vector tiles for your maps directly from R/Python spatial data, @duckdb queries, and local spatial files. Check out the docs here: walker-data.com/free... Some highlights:

640,000 parcels in Dallas County Texas, visualized in 3D by appraised value per square foot. The data prep? Vector tiles generated in 15 seconds directly from a @duckdb.org database using my latest geospatial tool, {freestiler}. Package announcement coming tomorrow!

With OpenClaw, you can have on-demand location intelligence in your pocket. I taught my bot how to pull demographic data and do drive-time analytics for any address using validated pipelines; It then formats a branded PDF report and delivers to me by Telegram, ready to share.

This week on What's New in R: ✅ Tutorial on visualizing biking data w/elevation profiles ✅ {typeR} package for simulating live typing in demos ✅ @kylewalker.bsky.social's guide to creating travel-time matrices for spatial analysis Read the issue: buff.ly/T7DqdIw @fgazzelloni.bsky.social #rstats

With Claude Code as my dev partner, I'm getting close to releasing the most technically impressive geospatial package I've ever created. This one will have both R and Python bindings - I think you'll like it. It is an incredible time to be building things.

For me, Gemini is the #1 LLM for several use-cases including document extraction and image generation. But it doesn't get nearly the hype of its competitors as the Gemini CLI is a distant third for agentic coding. For us users - it pays off to know the best tool for the job.

Next step....getting {calcite} to work with {mapgl} 👆🏼 it already does, i just need to make an example :P New release coming in the next week or so! github.com/r-arcgis/cal... #rstats

spopt-r brings powerful spatial optimization algorithms for regionalization, facility location, and market analysis to R with a blazing-fast Rust backend. Use them for analyses in energy, retail, logistics, sales, real estate, and more. Get started: walker-data.com/spopt-r

We live in a magical time for #dataviz. This map is just a static html page served on GitHub pages 🤯 It uses the incredible {pmtiles} #rstats package by @kylewalker.bsky.social to quickly filter through ~21M rows of data hosted on Cloudflare vehicletrends.github.io/hhi-map/

New in R's mapgl: native support for Esri basemap styles! Build your maps and apps in R & Shiny, display your data over your favorite Esri styles that you use in ArcGIS Pro / Online. Just grab your ArcGIS API token and use `esri_style()` for dozens of choices.

How I map millions of features without breaking the bank: - Data prep: R - Data tiling: tippecanoe, PMTiles - Deployment: Cloudflare R2 / Workers - Mapping: MapLibre / R / mapgl Lightning-fast with edge caching, minimal hosting costs See it in action: personal.tcu.edu/kylewalker/m...

OpenClaw + R = custom maps and insights sent to my phone. I think there’s a huge opportunity in custom analytics bots for businesses with differentiated context and data.

I’m teaching my OpenClaw bot how to do mapping and spatial analysis. Location intelligence is now just a Telegram message away!

I joined Matt Forrest on the "Spatial Stack" podcast's latest episode. We discussed the importance of open data; why I use R for my geospatial work; why I'm enthusiastic about AI; and more. Watch / listen here:

14.3 million Texas parcels in a browser. Click anywhere, query the full database in real time. No server. No complex infrastructure. Just modern geospatial tech on a laptop.

"Software engineering is dead! People will just say what they need, and AI will make it!" Yes, because: People are famously skilled at describing what they need (ask any therapist), and; They definitely are patient enough to "fix" things if they don't work on the first try

Built a spatial SQL explorer for my GIS students this week. Drop a GeoJSON, practice writing queries, see instant results on a map + linked table. All in-browser, nothing to install. Powered by @duckdb.org WASM + @maplibre.org. Try it out: personal.tcu.edu/kylewalker/u...

Client-side #GIS tools are very effective for exploring patterns in dense datasets. Shown here: click a Texas well, create an AOI from the approximate boundary of other wells in its lease / unit. Stack: R, MapLibre/mapgl, Turf.js.

We're at a weird inflection point where LLMs are making it easier to build dashboards / data apps with code than with WYSIWYG / drag-and-drop editors The advantage to WYSIWYG was always the gentle learning curve compared to more customizable code... that advantage is evaporating

I'm a loyal Claude Opus / Claude Code user, but I have to say... They are right about Codex 5.3

My most popular map ever, Educational Attainment in America, gets a fresh look for 2026: - Updated to the 2024 ACS - MapLibre via R's mapgl with built-in interactivity - OpenFreeMap basemap, Cloudflare-hosted PMTiles (blazing fast!) Explore your city: personal.tcu.edu/kylewalker/m...

It's easy to feel overwhelmed by the current pace of change in technology. A useful counterpoint: There are STILL organizations using ArcMap for their GIS even though ArcGIS Pro has been out for over a decade. Technology moves fast; capacity for adoption, not always.

Showed my Advanced GIS students Claude Code this week. We built this map of code compliance violations in Fort Worth; heatmap giving way to points on zoom. Used the ArcGIS SDK for JavaScript. Took 10 minutes. I believe in Jevons Paradox. But we need to be teaching skills for 2026, not for 2016.

West Texas energy infrastructure identified from satellite imagery using zero-shot image segmentation. Shown: Well pads from simple text prompts; Draw a box around a wind turbine, find the others in the view; Click a solar farm, segment the area.

Half of the United States' population lives in these 144 counties. Explore: walkerke-county-popu...

In Feb 2024, I asked ChatGPT: "What do income levels by neighborhood look like in Dallas, Texas? Make me a map of the results." The result: the first nonsensical image. Today I asked Claude that question - it made an accurate MapLibre map. Wonder where we'll be in 2028...

Quality-of-life improvements to the #rstats {geosam} package: - Interactive swatches let you customize extraction color in the explorer; - The explorer sidebar is now collapsible; - The package installs the stable version of HuggingFace Transformers walker-data.com/geosam

Distributed energy is harder to map than centralized infrastructure, but cutting-edge AI tools can help. Shown: identifying rooftop solar panels in a suburban neighborhood with Mapbox imagery, Meta's SAM3. Useful for utilities, grid planners, and solar prospecting.

Mapped every pipeline in Texas: 368,000 miles of infrastructure at your fingertips. For energy operators, midstream companies, and data center site selectors, understanding pipeline proximity matters. Open data + modern GIS makes it accessible.

It's 2024 5-year American Community Survey release day! The ACS is the best resource for small-area analysis of US demographics. In R, use tidycensus and mapgl to dive into the data right now. Copy-paste the code below for an interactive income map with a legend filter:

{calcite} looking good 💅 🗺️ Esri's Calcite Design System in {shiny}? Yes, please!!! Full-stack spatial in R keeps getting better. github.com/r-arcgis/cal... #rstats

The big story coming out of yesterday's 2025 Census Population Estimates release: international migration declined in EVERY state in the past year. The plot: international migration rates since 2021 (each year covers the previous 12 months). Biggest drops: NY, NJ, CO, TX, UT

The 2025 @uscensusbureau Population Estimates were released today. Some takeaways: - Rapid growth in the Carolinas, Idaho, Texas; - 17 states + PR had more deaths than births; - Florida is #1 for international migration; - SC ranks #1 for domestic migration rate; NY ranks last

I merged a PR for mirai today (fixing an esoteric bug), that came with a performance boost that I'd never have thought existed. That means that on my laptop, the default (with dispatcher) round-trip performance now dips into sub-100 microseconds territory!! Get it now: `pak::pak("r-lib/mirai")`

Nearly 18 million California jobs in 2023, visualized by 2-digit NAICS category with block-level precision. Open data and modern geospatial technology make powerful labor market analytics possible.

Identifying possible empty lots in Fort Worth's South Main district with Meta's Segment Anything Model 3. Draw an "exemplar" prompt, find similar areas in the satellite image. Useful for urban redevelopment, real estate, and more. Try out {geosam}: walker-data.com/geosam

Social media: "if you're not using {Ralph Wiggum|Clawdbot|next week's new framework} you're ngmi" Now you're endlessly trying to optimize your workflows instead of doing the actual work you're avoiding. Agents will get better and better but they don't substitute for agency.