Nissim Lebovits guest hosts with Oliver Wing, Chief Science and Product Officer at Fathom, about building global flood risk data as a business. They cover why elevation data is the most important part of a flood model, serving insurers, banks, and governments from one product stack, why an ensemble of models is not a probability distribution, tailoring uncertainty to the end user, and how Fathom is using free access and the Oasis Loss Modelling Framework to push the industry toward interoperability.
Nissim Lebovits guest hosts with Elizabeth Wesley of World Resources Institute about the global extreme land surface temperature composite they published on Source Cooperative. They cover the different ways to measure heat, why land surface temperature is an imperfect but available signal for cities that otherwise have nothing, the processing choices behind a five-year 95th-percentile Landsat composite, and why documentation and distribution are part of the data product.
Jed talks with Jen Marcus and Isaac Corley of Taylor Geospatial about Fields of the World — an open, global map of agricultural field boundaries derived from satellite imagery with AI. They cover the origin story, why a shared schema (Fiboa) came first, what’s actually in the global data release, the economics of sustaining open data products, and a new push to fix how geospatial AI models get benchmarked.
Jed talks with Christopher Dick, founder of Demographic Analytics Advisors and former Census Bureau population estimates researcher, about counting people at scale, the legal and technical constraints on census data, and what it looks like to build demographic data products that actually serve their users.
Jed talks with Kwin Keuter and Brad Andrick from Earth Genome about transforming NOAA’s Storm Events Database – 70+ years of severe weather records—into an accessible data product with multiple modes of access for emergency managers, researchers, planners, and the public.
Jed talks with Denice Ross about the critical role of federal data in American life, what happens when government data tools disappear, and why building a healthier ecosystem requires both stable federal data and external innovation.
Jed talks with Matt Hanson about the SpatioTemporal Asset Catalog (STAC) specification, why adoption is the only metric that matters for standards, and what the ‘guerrilla standards’ approach teaches us about building data ecosystems.
Jed talks with Jack Cushman from the Harvard Law School Library Innovation Lab about their project to archive and preserve more than 311,000 datasets from Data.gov. We explore how they use BagIt for long-term preservation, built a serverless search interface that makes 17.9 TB of data discoverable in the browser, and what this means for the future of online archives.
Jed talks with Brandon Liu about Protomaps, PMTiles, and why a compelling base map as a data product matters. We cover open-source, customizable alternatives to Google Maps, how PMTiles enables single-file, static hosting, and practical ergonomics that help developers put maps on the web.
Jed Sundwall and Drew Breunig explore why LLM progress is getting harder by examining the foundational data products that powered AI breakthroughs. They discuss how we’ve consumed the “low-hanging fruit” of internet data and graphics innovations, and what this means for the future of AI development.
