Software Engineering
<- Return to all blogs
-
Introducing Natural Language Geocoding v0.1.0: An LLM-Enabled Geocoding Database
The landscape of geospatial AI is rapidly evolving. Many organizations are building LLM-powered solutions that tackle complex geospatial problems and answer sophisticated questions about our planet. These agentic approaches allow LLMs to autonomously select from toolsets that include geospatial tools, Earth Observation (EO) catalogs, and EO data processing capabilities. The result? Systems that can process…
-
Introducing Natural Language Geocoding v0.1.0: An LLM-Enabled Geocoding Database
The landscape of geospatial AI is rapidly evolving. Many organizations are building LLM-powered solutions that tackle complex geospatial problems and answer sophisticated questions about our planet. These agentic approaches allow LLMs to autonomously select from toolsets that include geospatial tools, Earth Observation (EO) catalogs, and EO data processing capabilities. The result? Systems that can process…
-
Chunks and Chunkability: An Origin Story
If you accept that we are living through the Tyranny of the Chunk, then you might be wondering how we got to this place. Who created the first chunks and what was their motivation? As we explore the history of different data formats we’ll see recurring patterns of thinking around how much information to consolidate…
-
Chunks and Chunkability: Tyranny of the Chunk
We discuss our attempt to understand chunks and chunking more deeply including where we are today and where we might go from here.
-
Perceived Gaps in Earth Observation
At Element 84, our team looks forward to the Spring season and the return of a busy conference schedule every year. Our time attending, presenting, and learning at conferences helps us to feel connected and plugged into trends in the geospatial industry and beyond. It also allows us to receive feedback on our team’s latest…
-
Why We’re Talking About a Centralized Vector Embeddings Catalog Now
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 embeddings catalog, in addition to the more standard data catalogs that they already maintain.
-
Is Zarr the new COG?
Just to be upfront and get it out there: no. Despite what you may have heard, Zarr is not (yet) a replacement for the Cloud-Optimized GeoTIFF (COG) format. Zarr is great for Level 3 and Level 4 n-dimensional data cubes. COG is great for Level 1, Level 2, and other non-data-cube rasters. Enthusiastic Zarr users…
-
Zarr + STAC
As part of our work writing a STAC + Zarr Report for the Cloud Optimized Geospatial Formats Guide our team is exploring the partially overlapping goals of STAC and Zarr and offering suggestions for how to use them together. This effort is particularly relevant currently due to several recent developments in the space that we…
-
STAPI Sprint #5: 0.1 Release
We recap our most recent STAPI Sprint in Lisbon. We worked toward evolving the satellite data ordering process, and released version 0.1.
-
Finding Changes on the Earth with Natural Language
We discuss our work with Natural Language Driven Geospatial Change Detection with Vector Embeddings. This technology builds on our ongoing development of generative AI and vision models that enables users to explore our world through natural language queries.
-
Updating our Geospatial Technology Radar for 2024
We introduce the second iteration of our geospatial technology radar, which is designed as a resource for the community to outline impactful technologies in the space.
