In this episode of the Spatial Stack, Matt sits down with Kyle Walker, Professor of Geography at TCU and the creator of popular R packages like tigris and tidycensus.

Kyle dives into why he views US Census data as critical infrastructure and how open data is fundamentally transforming decision-making across industries like real estate and energy. He shares the origin story of his open-source work, explaining why he champions the R programming language for full-stack geospatial analysis. The conversation also covers the evolution of web mapping, from the laborious process of rendering dot-density maps to the blazing-fast performance of modern tools like PMTiles.

Finally, Kyle reveals how generative AI specifically Claude Code and the Zed editor is serving as his ultimate coding assistant, allowing him to rapidly build complex projects like the mapgl package and turn his ideas into reality faster than ever.

Connect with Kyle:

X/Twitter: https://x.com/kyle_e_walker
LinkedIn: https://www.linkedin.com/in/walkerke/
Bluesky: https://bsky.app/profile/kylewalker.bsky.social

00:01:00 – Welcome and Kyle Walker’s Background at TCU
00:06:18 – Why US Open Data is Critical Infrastructure
00:09:20 – Demystifying Census Data with tigris and tidycensus
00:15:48 – Applied Spatial Data: Real Estate and Forecasting Models
00:18:28 – The Evolution of High-Resolution Dot Density Maps
00:23:48 – The Human Element: How People React to Seeing Data Maps
00:29:14 – R vs. Python: Why R is a Geospatial Powerhouse
00:37:44 – Accelerating Development: Using Claude and AI for Coding
00:43:40 – The Future of Mapping: PMTiles, Segment Anything, and LLMs
00:48:18 – Where to Find Kyle’s Book, Tools, and Workshops

---

🚀 Join The Spatial Lab:
Stop guessing at your career path. Get direct mentorship, advanced training, and a roadmap to these high-value roles inside The Spatial Lab.
👉 https://forrest.nyc/spatial-lab/

📰 Daily modern GIS insights: https://forrest.nyc

CONNECT WITH ME
📸 Instagram: https://www.instagram.com/matt_forrest/
💼 LinkedIn: https://www.linkedin.com/in/mbforr/
📧 Newsletter: https://forrest.nyc
🌐 Website: https://forrest.nyc

We have never had more data about our planet: petabytes of satellite imagery, aerial photos, and sensor readings collected daily. Yet, turning that massive volume of "noise" into a clear signal remains the fundamental challenge of the geospatial industry.

In this episode of the Spatial Stack, I sit down with the engineering and product minds from Wherobots: Ryan, Phil, and Len - to tear down the architecture required to handle Earth Observation data at a planetary scale. We move beyond the buzzwords to discuss the engineering "war stories" of building resilient inference pipelines.

We dive deep into why the industry is moving away from simple computer vision toward "Large Earth Models" that function like LLMs for the physical world. We also get into the weeds of the tech stack: the battle between Dask and Ray for distributed compute, why Cloud-Optimized GeoTIFFs (COGs) aren't always the answer for inference, and how formats like Zarr are unlocking multidimensional analysis.

In this episode, we cover:

The Data Bottleneck: Why "garbage in, garbage out" is still the biggest hurdle in monitoring a changing planet.

Infrastructure Realities: The specific limitations of Google Earth Engine and why we needed a cloud-agnostic approach.

Engineering Pivot: Why Wherobots migrated from Dask to Ray to solve "crashing cluster" syndromes and memory management issues.

The Future of GeoAI: How embeddings and foundation models are compressing petabytes of data into searchable, semantic insights.

✅ Sign Up for Wherobots: https://wherobots.com/
✅ Learn more about Apache Sedona: https://wherobots.com/apache-sedona/
✅ Learn more about RasterFlow: https://wherobots.com/blog/rasterflow-earth-observation-inference-engine/
✅ Sign Up for the RasterFlow Private Preview: https://wherobots.com/rasterflow-preview/

00:00 – Teaser: The "Garbage In, Garbage Out" problem in GeoAI
00:01:51 – Introductions & Icebreakers (The controversial ice cream opinions)
00:03:08 – The Challenge: Monitoring a changing Earth at scale
00:10:30 – Data Engineering: The hidden complexity of NAIP, clouds, and tiling artifacts
00:14:19 – Modeling Reality: Why Computer Vision models fail on geospatial data
00:21:51 – The Google Earth Engine Debate: Walled gardens vs. bringing compute to the data
00:27:53 – Introducing Rasterflow: A new architecture for scalable inference
00:36:51 – The Engineering Story: Why we switched from Dask to Ray
00:43:40 – File Formats: Why Zarr is superior to COGs for multidimensional inference
00:47:40 – Workflow Walkthrough: Running the "Fields of the World" model
00:51:40 – Embeddings, Foundation Models, and Large Earth Models
00:57:40 – How to get started with Rasterflow

📰 Modern GIS insights: https://forrest.nyc

CONNECT WITH ME
📸 Instagram: https://www.instagram.com/matt_forrest/
💼 LinkedIn: https://www.linkedin.com/in/mbforr/

🌐 Website: https://forrest.nyc

There are trillions of dollars invested in the physical world every da: infrastructure, supply chains, and our planet.

Yet many of these massive decisions are made without the data to back them up. For too long, geospatial analytics has been gated behind specialized teams and siloed technology, treated as "spatial is special" rather than just another data type.

In this episode, we sit down with Damian Wiley from Wherobots to break down how cloud architecture is finally closing this gap. With a heavy-hitting background from AWS EC2 and Databricks, Damian explains the shift from transactional databases to the Lakehouse architecture and why "Zero ETL" is the holy grail for data engineering.

We dive deep into why spatial data shouldn't be gated, how open table formats like Iceberg are changing the game, and why the future involves AI agents that can directly query the physical world.

If you are a data engineer, developer, or leader looking to unlock location intelligence without the headache of complex infrastructure, this conversation is for you.

✅ Sign Up for Wherobots: https://wherobots.com/
✅ Learn more about Apache Sedona: https://wherobots.com/apache-sedona/
✅ What is Apache Sedona: https://wherobots.com/blog/what-is-apache-sedona/
✅ Test out SedonaDB: https://sedona.apache.org/sedonadb/latest/
✅ Connect with Jia on LinkedIn: https://www.linkedin.com/in/wyliedamian/

00:00 - The Trillion Dollar Data Gap: Investing in the physical world without intelligence
02:15 - From AWS EC2 to Geospatial: Damian’s journey from cloud infrastructure to spatial data
06:40 - "Spatial is Special" No More: Breaking down silos and making spatial data "just data"
09:00 - The Lakehouse Advantage: Decoupling storage and compute for economic agility
12:15 - Fragmented History: Why geospatial tech became so compartmentalized
17:30 - Real-World Impact: Optimizing supply chains and climate response with frequent data
22:45 - The Economics of Analytics: Lowering the Total Cost of Ownership (TCO) for pipelines
28:30 - AI Agents & The Physical World: Connecting LLMs to ground-truth reality
37:00 - Compute Strategy: When to use OLAP vs. OLTP for spatial workloads
46:00 - Zero ETL & The Future: How Iceberg and open standards enable interoperability
51:20 - Getting Started with SedonaDB: Vibe coding and the future of spatial queries

📰 Daily modern GIS insights: https://forrest.nyc

CONNECT WITH ME
📸 Instagram: https://www.instagram.com/matt_forrest/
💼 LinkedIn: https://www.linkedin.com/in/mbforr/
📧 Newsletter: https://forrest.nyc
🌐 Website: https://forrest.nyc

We have an incredible amount of public geospatial data—high-resolution elevation, weather forecasts, floodplain maps, real-time sensors—yet most people still can’t easily answer a simple question:

“What’s my flood risk right here, right now?”

In this episode, I’m joined by Kevin Bullock, an aerospace engineer and remote sensing expert at Development Seed, to talk about how he turned years of geospatial expertise into Hydra Atlas, a mobile app designed to make flood risk understandable and accessible for everyday users.

We explore why so much critical data remains difficult to use, how Kevin pulled together datasets from FEMA, NOAA, and USGS, and why mobile—not web—was the right platform for this problem. Kevin also shares what it was like building a geospatial app with Swift, testing real-world use cases, and designing an interface that prioritizes clarity over complexity.

This conversation goes beyond flooding. It’s about modern GIS, product thinking, open data, and what happens when geospatial professionals stop building tools for other experts and start building tools for people.

If you’re interested in geospatial product development, public data, mobile mapping, or turning complex systems into usable software, this episode is for you.

Download HydraAtlas: https://apps.apple.com/us/app/hydraatlas/id6749492232
Follow Kevin on LinkedIn: https://www.linkedin.com/in/kevbullock/

---

Whenever you’re ready, here are 3 ways I can help you:

🎓 Modern GIS Accelerator: The step-by-step roadmap to master Python, Spatial SQL & Cloud workflows. Stop just "making maps" and start building spatial solutions. 👉 https://forrest.nyc/accelerator/

🧪 The Spatial Lab: Join the top 5% of geospatial professionals in our private community. Get access to exclusive courses, mentorship, and the network you need to level up. 👉 https://forrest.nyc/spatial-lab/

🧭 Career Compass: Not sure where to start? Get the fast, practical steps to land the GIS role you actually want. 👉 https://forrest.nyc/career-compass/

📰 Daily modern GIS insights: https://forrest.nyc

CONNECT WITH ME
📸 Instagram: https://www.instagram.com/matt_forrest/
💼 LinkedIn: https://www.linkedin.com/in/mbforr/
📧 Newsletter: https://forrest.nyc
🌐 Website: https://forrest.nyc

If there’s one word to describe the past year in geospatial, it’s change.

In this solo episode, I take you behind the scenes of what I’ve been seeing, hearing, and working on across geospatial, cloud, and AI over the past year, and how those shifts are shaping what actually matters heading into 2026 .

I talk about:

- Where AI is real vs overhyped in geospatial workflows
- Why cloud-native geospatial has quietly crossed into real production systems
- How formats like GeoParquet, Iceberg, and modern compute engines are changing where spatial data lives
- Why architecture and systems thinking are becoming the most valuable skills in the industry
- The rise of power skills (not “soft skills”) across roles like data engineering, product, architecture, and leadership
- What roles are emerging, and how they actually work together in modern spatial teams

This isn’t a predictions episode built on hype. It’s a grounded look at what changed, what didn’t, and what skills and mindsets will matter most as geospatial continues to integrate with the broader data and AI ecosystem.

If you’re a GIS professional, data engineer, architect, product manager, or leader trying to understand how spatial fits into modern systems, this episode will help you frame what’s next, and how to prepare for it.

---

🚀 Ready to move beyond desktop GIS?
Step into the Spatial Lab: a global community for ambitious geospatial professionals who want to break out of outdated workflows and join the top 5% of the field.
👉 Join Spatial Lab: https://forrest.nyc/spatial-lab/

🎓 Want structured, career-changing learning?

🚀 Modern GIS Accelerator: https://forrest.nyc/accelerator/
— master Python, Spatial SQL & cloud workflows in 2 weeks

🧭 Career Compass: https://forrest.nyc/career-compass/
— fast, practical steps to land the GIS role you want

🪄 AI Copilot for GIS: https://forrest.nyc/ai-copilot-for-gis/
— learn to integrate AI into your geospatial workflows & boost your productivity

📰 Weekly modern GIS insights: https://forrest.nyc

⚡️ Spots for the next live cohort and mentorship cycle are closing soon, join now to lock in your place and momentum.

CONNECT WITH ME
📸 Instagram: https://www.instagram.com/matt_forrest/
💼 LinkedIn: https://www.linkedin.com/in/mbforr/
📧 Newsletter: https://forrest.nyc
🌐 Website: https://forrest.nyc

GeoPandas is one of the most important tools in modern GIS, but many people still aren’t sure when to use it, why it matters, or where it fits alongside tools like PostGIS, DuckDB, Apache Sedona, and cloud-native data formats.

In this video, I break down GeoPandas from the ground up: what it is, how it works under the hood, its strengths and limitations, and when to choose something else. If you’ve ever worked in ArcGIS or QGIS and wondered how to bring those same workflows into Python, this is the perfect place to start.

What we cover in this video:

- What GeoPandas actually does (How it extends Pandas, adds geometry types, reads vector formats, and integrates tools like Shapely, Fiona, PyProj, GeoArrow, and GeoParquet)
- Why GeoPandas matters in modern GIS
- When GeoPandas is the right tool
- When NOT to use GeoPandas
- How GeoPandas fits into the modern stack (How it pairs with DuckDB, SedonaDB, PostGIS, Apache Sedona (Spark), data lakes, Iceberg, and cloud-native geospatial)
- How to actually get started

This video is for you if you are a:

• GIS professionals moving into Python
• Data scientists adding spatial capabilities
• Engineers exploring geospatial data stacks
• Anyone who wants a modern alternative to desktop GIS workflows

Resources from the video

- My GeoPandas Course: https://www.youtube.com/watch?v=0mWgVVH_dos
- GeoPandas Documentation: https://geopandas.org/en/stable/getting_started/introduction.html
- Dr. Qiusheng Wu's New Book on Geospatial Python: https://www.amazon.com/dp/B0FFW34LL3

---

🚀 Ready to move beyond desktop GIS?
Step into the Spatial Lab: a global community for ambitious geospatial professionals who want to break out of outdated workflows and join the top 5% of the field.
👉 Join Spatial Lab: https://forrest.nyc/spatial-lab/

🎓 Want structured, career-changing learning?

🚀 Modern GIS Accelerator: https://forrest.nyc/accelerator/
— master Python, Spatial SQL & cloud workflows in 2 weeks

🧭 Career Compass: https://forrest.nyc/career-compass/
— fast, practical steps to land the GIS role you want

🪄 AI Copilot for GIS: https://forrest.nyc/ai-copilot-for-gis/
— learn to integrate AI into your geospatial workflows & boost your productivity

📰 Weekly modern GIS insights: https://forrest.nyc

⚡️ Spots for the next live cohort and mentorship cycle are closing soon, join now to lock in your place and momentum.

0:00 Intro to GeoPandas
0:35 What is GeoPandas
2:54 Why should you care about GeoPandas?
5:12 Do you need to use GeoPandas?
8:22 How do you use GeoPandas?
10:59 Pitfalls of GeoPandas
13:06 When NOT to use GeoPandas?
14:50 Where to learn about GeoPandas?

CONNECT WITH ME
📸 Instagram: https://www.instagram.com/matt_forrest/
💼 LinkedIn: https://www.linkedin.com/in/mbforr/
📧 Newsletter: https://forrest.nyc
🌐 Website: https://forrest.nyc

ArcGIS Pro has been the center of GIS workflows for decades but how does it hold up in a world moving toward open, cloud-native, and AI-powered geospatial tools? In this video, I break down what ArcGIS Pro actually is, where it shines, where it struggles, and how it fits into the modern GIS ecosystem.

Whether you’re doing personal GIS projects, running a small team, or architecting enterprise-scale systems, this deep dive will help you understand when ArcGIS Pro is the right choice and when alternatives like QGIS, GeoPandas, DuckDB, PostGIS, Sedona, or cloud-native stacks might serve you better.

What You’ll Learn

- What ArcGIS Pro is and how it fits into Esri’s ecosystem
- Its strengths in cartography, desktop analysis, 3D tools, enterprise integration, and data management
- Newer support for modern formats like GeoParquet, COGs, STAC, and DuckDB
- Where ArcGIS Pro begins to struggle (big data, cloud workflows, Python lock-in, cost/licensing)
- How it compares to open tools like QGIS, GeoPandas, and modern geospatial data platforms
- My honest assessment of whether YOU should be using ArcGIS Pro across personal, team, and enterprise use cases

---

🚀 Ready to move beyond desktop GIS?
Step into the Spatial Lab: a global community for ambitious geospatial professionals who want to break out of outdated workflows and join the top 5% of the field.
👉 Join Spatial Lab: https://forrest.nyc/spatial-lab/

🎓 Want structured, career-changing learning?

🚀 Modern GIS Accelerator: https://forrest.nyc/accelerator/
— master Python, Spatial SQL & cloud workflows in 2 weeks

🧭 Career Compass: https://forrest.nyc/career-compass/
— fast, practical steps to land the GIS role you want

🪄 AI Copilot for GIS: https://forrest.nyc/ai-copilot-for-gis/
— learn to integrate AI into your geospatial workflows & boost your productivity

📰 Weekly modern GIS insights: https://forrest.nyc

⚡️ Spots for the next live cohort and mentorship cycle are closing soon, join now to lock in your place and momentum.

0:00 Intro to ArcGIS Pro
0:31 My background with Esri
1:16 What is ArcGIS
4:02 Why does ArcGIS Pro matter?
7:11 Do you need to use ArcGIS Pro?
12:54 How do you use ArcGIS Pro?
14:50 Pitfalls of ArcGIS Pro
17:47 When to use ArcGIS Pro?
20:15 Where to learn about ArcGIS Pro?

CONNECT WITH ME
📸 Instagram: https://www.instagram.com/matt_forrest/
💼 LinkedIn: https://www.linkedin.com/in/mbforr/
📧 Newsletter: https://forrest.nyc
🌐 Website: https://forrest.nyc

What does it really take to teach AI to understand our planet?

In this episode, Matt sits down with Isaac Corley, Senior Machine Learning Engineer at Wherobots and maintainer of TorchGeo, and Christopher Ren, Data Scientist and writer behind some of the most thought-provoking essays on Earth observation and AI.

They dive deep into the state of Geospatial AI from embeddings and foundation models to how these tools are reshaping Earth observation and remote sensing. You’ll hear real-world perspectives on what’s working, what’s not, and where the hype outpaces reality.

Key topics covered:

What "embeddings" actually mean for geospatial and remote sensing
How foundation models like AlphaEarth and Tessera are trained
The challenges of applying ML at global scale
The future of Earth observation data pipelines
Why geospatial AI is still the "wild west"

If you’ve ever wondered how AI models are built to map, monitor, and understand the Earth, this conversation breaks it down without the buzzwords.

LINKS:

ISAAC CORLEY

Website: https://isaacc.dev/
LinkedIn: linkedin.com/in/isaaccorley
X: @isaaccorley_
GitHub: @isaaccorley
I’m active in TorchGeo slack: free to join https://join.slack.com/t/torchgeo/shared_invite/zt-22rse667m-eqtCeNW0yI000Tl4B~2PIw

CHRISTOPHER REN

Blog: https://christopherren.substack.com/
Podcast: Spotify | Apple | Youtube
LinkedIn: https://www.linkedin.com/in/christopherren/
Geovibes/Github: https://github.com/cr458/geovibes

🚀 Ready to move beyond desktop GIS?
Step into the Spatial Lab: a global community for ambitious geospatial professionals who want to break out of outdated workflows and join the top 5% of the field.
👉 Join Spatial Lab: https://forrest.nyc/spatial-lab/

🎓 Want structured, career-changing learning?

🚀 Modern GIS Accelerator: https://forrest.nyc/accelerator/
— master Python, Spatial SQL & cloud workflows in 2 weeks

🧭 Career Compass: https://forrest.nyc/career-compass/
— fast, practical steps to land the GIS role you want

🪄 AI Copilot for GIS: https://forrest.nyc/ai-copilot-for-gis/
— learn to integrate AI into your geospatial workflows & boost your productivity

📰 Weekly modern GIS insights: https://forrest.nyc

⚡️ Spots for the next live cohort and mentorship cycle are closing soon, join now to lock in your place and momentum.

CONNECT WITH ME
📸 Instagram: https://www.instagram.com/matt_forrest/
💼 LinkedIn: https://www.linkedin.com/in/mbforr/
📧 Newsletter: https://forrest.nyc
🌐 Website: https://forrest.nyc