What if communities could map their own worlds using low-cost drones and open AI models instead of waiting for expensive satellite imagery?

In this episode with Leen from HOT (Humanitarian OpenStreetMap Team), we explore how they're putting open mapping tools directly into communities' hands—from $500 drones that fly in parallel to create high-resolution imagery across massive areas, to predictive models that speed up feature extraction without replacing human judgment.

Key topics:

• Why local knowledge beats perfect accuracy
• The drone tasking system: how multiple pilots map 80+ square kilometers simultaneously
• AI-assisted mapping with humans in the loop at every step
• Localizing AI models so they actually understand what buildings in Chad or Papua New Guinea look like
• The platform approach: plugging in models for trees, roads, rooftop material, waste detection, whatever communities need
• The tension between speed and OpenStreetMap's principles
• Why mapping is ultimately a power game—and who decides what's on the map

This conversation with Jed Sundwall, Executive Director of Radiant Earth, starts with a simple but crucial distinction: the difference between data and data products. And that distinction matters more than you might think.

We dig into why so many open data portals feel like someone just threw up a bunch of files and called it a day. Sure, the data's technically "open," but is it actually useful? Jed argues we need to be way more precise with our language and intentional about what we're building.

A data product has documentation, clear licensing, consistent formatting, customer support, and most importantly - it'll actually be there tomorrow.

From there, we explore Source Cooperative, which Jed describes as "object storage for people who should never log into a cloud console." It's designed to be invisible infrastructure - the kind you take for granted because it just works. We talk about cloud native concepts, why object storage matters, and what it really means to think like a product manager when publishing data.

The conversation also touches on sustainability - both the financial kind (how do you keep data products alive for 50 years?) and the cultural kind (why do we need organizations designed for the 21st century, not the 20th?). Jed introduces this idea of "gazelles" - smaller, lighter-weight institutions that can move together and actually get things done.

We wrap up talking about why shared understanding matters more than ever, and why making data easier to access and use might be one of the most important things we can do right now.

Reflections from the FOSS4G 2025 conference

The high volume of talks on extracting meaning from geospatial data—including Python workflows, data pipelines, and automation at scale—reinforced the idea that FOSS4G represents critical infrastructure.

• AI Dominance: AI took up a lot of space at the conference. I was particularly interested in practical, near-term impact talks like AI assisted coding and how AI large language models can enhance geospatial workflows in QGIS. Typically, AI discussions focus on big data and earth observation, but these topics touch a larger audience. I sometimes wonder if adding "AI" to a title is now like adding a health warning: "Caution, a machine did this".
• Python Still Rules (But Rust is Chatting): Python remains the pervasive, default geospatial language. However, there was chatter about Rust. One person suggested rewriting QGIS in Rust might make it easier to attract new developers.

When geospatial people meet, data infrastructure—the "plumbing" of how data is stored, organized, and accessed—always dominates.

• Cloud Native Won: Cloud native architecture captured all the attention. When thinking about formats, we are moving away from files on disk toward objects in storage and streaming subsets of data.
• Key cloud-native formats covered included COGs (Cloud Optimized GeoTIFFs), Zarr, GeoParquet, and PMTiles. A key takeaway was the need to choose a format that best suits the use case, defined by who will read the file and what they will use the data for, rather than focusing solely on writing it.
• The Spatial Temporal Asset Catalog (STAC) "stole the show" as data infrastructure, and DuckDB was frequently mentioned.
• Visualization is moving beyond interactive maps and toward "interactive experiences". There were also several presentations on Discrete Global Grid Systems (DGGS).

• Standards Matter: Standards are often "really boring," but they are incredibly important for interoperability and reaping the benefits of network effects. The focus was largely on OGC APIs replacing legacy APIs like WMS and WFS (making it hard not to mention PyGeoAPI).
• Community Empowerment: Many stories focused on community-led projects solving real-world problems. This represents a shift away from expert-driven projects toward community action supported by experts. Many used OSM (OpenStreetMap) as critical data infrastructure, highlighting the need for locals to fill in large empty chunks of the map.

If I had to offer quick guidance based on the conference, it would be:

1. Learn Python.
2. AI coding is constantly improving and worth thinking about.
3. Start thinking about maps as experiences.
4. Embrace the Cloud and understand cloud-native formats.
5. Standards matter.
6. AI is production-ready and will be an increasingly useful interface to analysis.

The conference was brilliant, but a few areas felt underrepresented:

• Sustainable Funding Models: I missed a focus on how organizations can rethink their business models to maintain FOSS4G as critical infrastructure without maintainers feeling their time is an arbitrage opportunity.
• Niche Products: I would have liked more stories about side hustles and niche SAS products people were building, although I was glad to see the "Build the Thing" product workshop on the schedule.
• Natural Language Interface: Given the impact natural language is having on how we interact with maps and geo-data, I was surprised there wasn't more dedicated discussion around it. I believe it will be a dominant way we interact with the digital world.
• Art and Creativity: Beyond cartography and design talks, I was surprised how few talks focused on creative passion projects built purely for the joy of creation, not necessarily tied to making a part of something bigger.

Karl returns to the Mapscaping podcast to discuss his latest venture, Tyche Insights - a platform aimed at building a global community of geospatial storytellers working with open data.

In this conversation, we explore the evolution from his previous company, Building Footprint USA (acquired by Lightbox), to this new mission of democratizing public data storytelling.

Karl walks us through the challenges and opportunities of open data, the importance of unbiased storytelling, and how geospatial professionals can apply their skills to analyze and share insights about their own communities. Karl shares his vision for creating something akin to Wikipedia, but for civic data stories - complete with style guides, editorial processes, and community collaboration.

Tyche Insights:

• Main website: https://tycheinsights.com
• Wiki platform: https://wiki.tycheinsights.com
• Example project: https://albanydatastories.com

Mentioned in Episode:

• USAFacts: https://usafacts.org
• QField Partner Program: https://qfield.org/partner
• Open Data Watch: (monitoring global open data policies)

Jonathan Wagner, CEO of Scribble Maps, is back on the podcast, and this time we're talking about Scribble—an AI agent he's built into his platform. Not a chatbot, an agent. There's a difference, and we get into that.

https://mapscaping.com/podcast/the-business-of-web-maps/

So far, Scribble has access to 140 tools. It can view your map, select tools, build plugins, fetch data, and handle onboarding and customer education.

But here's the thing—should you care?

I think you should, because we're going to see more and more of these things. And whether you like it or not, for a lot of people, this is going to be the way they interact with geospatial data. I don't think we can put the genie back in the bottle. I personally, I'm not entirely sure I would if I could.

Yeah, sure, there's a lot of uncertainty around what these things can do and how they're going to impact us. I get that. I feel it too. But we can't afford to stick our heads in the sand and pretend like it's not happening.

In this conversation, Jonathan walks through why he built Scribble (spoiler: his wife was expecting and he needed to solve an onboarding problem), the real risks of adding AI to your product, and the technical decisions behind using Gemini over OpenAI. We also talk about privacy concerns, the Model Context Protocol (MCP), and what this all means for the future of GIS.

We touch on the QGIS MCP server, the democratization of mapping tools, and when maps aren't actually the answer. It's an honest look at where we are with AI agents in geospatial, from someone who's actually building one.

https://en.wikipedia.org/wiki/Lojban

https://github.com/jjsantos01/qgis_mcp

How's that?