It's Friday and our latest quarterly newsletter is out in the world!! 📬

We share more about:
🌎 Updates to our Queryable Earth demos
🔮 The future of agentic AI & the open source ecosystem
🗓️ Our Spring conference calendar!
🤝 Open roles on our team

mailchi.mp/a0adddbe56e2...

Building Conversational Interfaces for Querying and Analyzing Geospatial Data • Element 84 We present highlights from our ongoing open-source work aimed at building conversational interfaces to query and analyze NOAA data using LLMs.

As geospatial data becomes increasingly accessible, how can we also make it trivial to query & analyze the same data using modern LLMs?

In this blog, Adeel Hassan details our ongoing open-source work to answer this question as part of a NOAA-funded study: element84.com/machine-lear...

Building and Validating LLM-Generated Captions and Embeddings for Geospatial Imagery in Queryable Earth • Element 84 We detail how we caption Queryable Earth tiles. We also share the tools we use for validating our results and comparing the generated embeddings.

In our latest blog post we kick off a technical deep-dive into Queryable Earth. 🔍 🌎 We discuss our process captioning Queryable Earth tiles, validating our results, and comparing the embeddings generated by SkyCLIP, Claude Haiku, & Claude Opus.

Check out the full blog: element84.com/machine-lear...

Antelope Valley Wildflower Forecast | Leaftime 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.

Check out Leaftime: antelope.leaftime.net

And learn more about Earthsearch here! element84.com/earth-search/

It's always the highlight of our week when we see a creative new way our work is being used in the wild!

Biologist Stephen Klosterman developed an experimental forecast of flower blooms in California's Antelope Valley using Sentinel-2 satellite imagery from Earthsearch. 🪻🌷

(Re)Making Cirrus: Three lessons learned • Element 84 Reflecting on the Cirrus story, three core lessons emerged that seem worth discussion, lessons that apply to software projects generally.

It's time for (Re)Making Cirrus: Part 2!! Jarrett Keifer is back on the blog picking up where he left off in the last installment of this retrospective discussion about Cirrus, the data orchestration framework we develop and use here at E84.

Check it out: element84.com/data-science...

Takeaways from the First Geospatial Vector Embeddings Standards Sprint 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.

Our Director of AI Applications, Jason Gilman, just returned from the 1st Geospatial Vector Embeddings Standards Sprint!

Attendees worked to define common standards, best practices, and documentation for geospatial vector embeddings.

His takeaways: www.linkedin.com/pulse/takeaw...

If AI Is Going to Task Satellites, We Need Standards • Element 84 In order for AI to task satellites and act in the physical world at scale, the community must to settle on an agreed upon standard.

"If we want AI to act in the physical world at scale, we don’t need the standard that models every possible sensor state. We need the one that everyone actually agrees to use."

@geoskeptic.bsky.social shares about the importance of satellite tasking in the age of AI: element84.com/software-eng...

(Re)Making Cirrus: Reflections on five years spent building an open-source data orchestrator • Element 84 A retrospective look at the history of Cirrus, a data orchestration framework we develop and use at E84, and where we plan to go from here.

Cirrus = the data orchestration framework we develop and use at E84, and, despite being a critical component of our infrastructure, we haven’t discussed it much publicly.

We take a retrospective look at the framework's history and look towards the future: element84.com/software-eng...

AI Coding and the Future of Open-Source Geospatial Software • Element 84 The geospatial domain offers unique perspective into the recent shift in AI coding and related impacts on the entire open-source ecosystem.

📚 What we're reading: "AI Coding and the Future of Open-Source Geospatial Software," from Matt Hanson at @element84.com.

"Open-source software is facing a new kind of pressure — not from funding or standards debates, but from tools that are now building tools, often beyond our oversight." 🤖

Queryable Earth Demo Update: Now with Change Detection!  • Element 84 We detail how we used queryable Earth and natural language geocoding to demonstrate data accessibility in an intuitive and interactive way.

Our Queryable Earth demos now include change detection! (+ a several other new and updated features) ✨ 🥳 🌎

With change detection, users are able to search a large amount of data for specific changes like new construction and changes to landscapes.

Full post: element84.com/machine-lear...

Yesterday, Dan Pilone had the opportunity to spend the day in DC at the #NASAIndustrySummit!

His biggest takeaways surrounded our community's perspective on data, and the importance of tailoring our data to users (and specific use cases) to maximize impact as geospatial professionals.

We loved listening in on this very timely conversation between @geoskeptic.bsky.social and Daniel O'Donohue on MapScaping!

Conversations like this help us to prepare for the continuing evolution of AI as it relates to the geospatial world. 🔮✨🌎

Check it out: mapscaping.com/podcast/vibe...

AI Coding and the Future of Open-Source Geospatial Software • Element 84 The geospatial domain offers unique perspective into the recent shift in AI coding and related impacts on the entire open-source ecosystem.

What is the role of subject matter expertise in today's AI-centric climate? @geoskeptic.bsky.social takes to the blog to discuss how our geospatial niche fits into the conversation, and to suggest ways we can all work to reduce fragmentation caused by AI.

element84.com/geospatial/a...

Yesterday our E84 team had the pleasure of hosting the latest Philadelphia #SustainableBusinessNetwork meeting!

It felt especially pertinent to discuss the intersection of environmental impact & AI use, and how we can find a balance while furthering sustainable innovation.

BoundarySync: Streamlining Water Utility Boundary Management Through an Intuitive, Free, and Open Source Web App  • Element 84 We collaboratively designed and developed BoundarySync, a free and open source tool that streamlines water boundary maintenance.

In small, rural, or underfunded communities, water utilities often don’t have the tooling they need to capture their water boundaries digitally.

BoundarySync, a free and open source tool, streamlines water boundary maintenance. Read more: element84.com/projects/bou...

Is Zarr the new COG? • Element 84 We discuss the actual differences between Zarr and COG and how each stores the data contained within its files to combat the assumption that there is a discrete choice between the two.

AND YOUR FAVORITE POST..... 🥁

1. Is Zarr the new COG? by Jarrett Keifer and Julia Signell !! element84.com/software-eng...

Let us know if we missed one of your favorite blogs from this year, and let us know what you'd like to hear us speak more about in the future!

Exploring AlphaEarth Embeddings • Element 84 We take a closer look at AlphaEarth embeddings and explore their usefulness for classification, similarity search, and change detection.

2. Exploring AlphaEarth Embeddings by Adeel Hassan element84.com/machine-lear...

Introducing Natural Language Geocoding v0.1.0: An LLM-Enabled Geocoding Database • Element 84 We discuss Natural Language Geocoding v0.1.0 and progress with LLM-geocoding databases more generally.

3. Introducing Natural Language Geocoding v0.1.0: An LLM-Enabled Geocoding Database by Jason Gilman element84.com/machine-lear...

Introducing Earth Search v1: New datasets now available • Element 84 We outline the latest from Earth Search: an endpoint that hosts a catalog of Sentinel-2 and Landsat data to improve data accessibility.

4. Introducing Earth Search v1: New datasets now available by Matthew Hanson element84.com/geospatial/i...

Why We’re Talking About a Centralized Vector Embeddings Catalog Now • Element 84 We discuss our detailed white paper in which we make the case for how Earth Observation (EO) data providers such as NASA can dramatically improve access to their data by creating a centralized vector ...

5. Why We’re Talking About a Centralized Vector Embeddings Catalog Now by Jason Gilman, Adeel Hassan, and Nathan Zimmerman element84.com/machine-lear...

As we head into 2026, we took a scroll back through our last year of E84 blogs to find YOUR favorite posts from 2025.

Writing, researching, & publishing blogs is always a highlight of our work, primarily because it helps us to launch important conversations.

This year's top blogs were... 🧵

We are looking forward to hosting the next Sustainable Business Network of Greater Philadelphia meeting in January!

We'll be sharing about our work on tools like Stormwater Connect and our new Vision for AI in Engineering.

Learn more and RSVP: sbngreaterphilly.app.neoncrm.com/nx/portal/ne...

Boosting Ingest and Data Streaming Capabilities using LLMs – All at a Lower Cost  • Element 84 We share our response to a data outage incident and how our response ultimately increased available data and decreased latency for our client.

It's the 2025 home stretch! and we're reflecting on all of the hard work that went into helping make a big impact for our clients this year.

In this case study we share just one snapshot of our year -- we recount an experience responding to a data outage.
element84.com/projects/boo...

We loved the opportunity to continue ongoing conversations surrounding advancements in GeoAI at our #AGU2025 reception on Tuesday. Thank you to everyone who attended, and to @awscloud.bsky.social for supporting the event!

Earth Observation Essentials: December 17, 2025 Five Themes That Defined EO in 2025

If you're not already subscribed to the TerraWatch Space newsletter, you're missing out on a free, comprehensive, Earth Observation-focused recap.

In today's edition, our Geospatial Tech Radar got a shout out, so we know they have good taste 😉

newsletter.terrawatchspace.com/earth-observ...

Yesterday we loved the opportunity to share the latest from our work on an Agentic Workflow for Querying NOAA Climate Archives, Natural Language Geocoding, and ChatGSFC at #AGU2025

Reach out to us directly to continue the conversation!

Beyond the Hype: Element 84's Pragmatic Vision for AI in Engineering • Element 84 We discuss our approach to integrating AI in engineering at Element 84, and outline our guidelines for incorporating AI into our work.

Trying to figure out how it looks to integrate AI into your work in an intentional way? Us too.

In our latest blog, our Chief of Engineering Staff, Lauren Frederick, outlines our guiding principles for AI integration in engineering.

element84.com/company/beyo...

Exploring AlphaEarth Embeddings • Element 84 We take a closer look at AlphaEarth embeddings and explore their usefulness for classification, similarity search, and change detection.

New on the blog: Adeel continues the conversation on vector embeddings with a deep dive on AlphaEarth Embeddings.

The blog evaluates the embeddings for use in real-world scenarios including classification, similarity search, and change detection.

element84.com/machine-lear...

Cool (FREE) Event Alert!! 🚨📢

E8-er Adeel Hassan will be presenting at a virtual Geospatial Professional Network (GPN) meeting this Wednesday to discuss upcoming trends in Geospatial AI as well as some of our work in this area.

Learn more and register: www.macurisa.org/event-6459389