A CNG community gathering in New York City during NYC Climate Week.

YouTube video by AI for Good

A CNG community gathering in New York City during NYC Climate Week.

We discuss the evolution of Queryable Earth into Agentic Queryable Earth, including a more conversational experience.

We revisit the question: is Zarr the new COG? We review changes from the past year and discuss the shrinking gap between the two data formats.

In this blog we give a sneak preview into the typical conversation structure we have with new-to-us organizations through frequently asked questions that we regularly answer during introductory calls.

Discover AI for Good Summit 2026 programme, led by ITU, aims to unlock AI’s potential to serve humanity through building skills and standards, and advancing partnerships to solve global challenges.

In this blog, we sit down with Mark Reese to discuss his personal connection to his work, and how he sees E84’s work in the federal space continuing to evolve.

Element 84 builds software that helps answer big questions about our health, our infrastructure, and our changing planet. We’re excited about what we do, and

Towards an Agentic Queryable Earth UMD Workshop on GeoAI for Autonomous Spatial Analysis June 14, 2026 | @element84 Jason Gilman Director of AI Applications linkedin.com/in/jason-gilman I’m the Direct...

(function($) {window.fnames = new Array(); window.ftypes = new

For businesses operating in highly regulated industries, zero risk tolerance policies often lead to delays in AI adoption. Although there are certainly risks

Queryable Earth

Sharing our findings from the past year helping NASA build and scale a chat-based AI tool called ChatGSFC.

We present highlights from our ongoing open-source work aimed at building conversational interfaces to query and analyze NOAA data using LLMs.

We detail how we caption Queryable Earth tiles. We also share the tools we use for validating our results and comparing the generated embeddings.

See when California poppies and goldfields are blooming in the Antelope Valley. Updated every 2-3 days with satellite imagery and AI-powered bloom forecasts.

Reflecting on the Cirrus story, three core lessons emerged that seem worth discussion, lessons that apply to software projects generally.

Earlier this week, I participated in an amazing sprint to define common standards, best practices, and documentation for geospatial vector embeddings. I have some initial takeaways to share.