Planetary-scale answers, unlocked.
A Hands-On Guide for Working with Large-Scale Spatial Data. Learn more.
Welcome to This Month In Wherobots the monthly developer newsletter for the Wherobots & Apache Sedona community! This month we have news about Wherobots and the Overture Maps Foundation, a deep dive on new Wherobots Cloud features like raster inference, generating vector tiles, and the Spatial SQL API, plus a look at retail cannibalization analysis for the commercial real estate industry.
Wherobots has officially joined Overture Maps Foundation to support the next generation of planetary-scale open map data. Wherobots has supported the development of Overture datasets through Overture Maps Foundation’s use of the open-source Apache Sedona project to develop and distribute global data, enabling Overture to embrace modern cloud-native geospatial technologies like GeoParquet. By joining Overture as Contributing Members Wherobots will continue to support the ongoing development, distribution, and evolution of this critical open dataset that enables developers and data practitioners to make sense of the world around us.
Read the announcement blog post
This month’s featured community members is Ilya Marchenko from YuzuData where he focuses on AI and location intelligence for the commercial real estate industry. Ilya recently wrote a blog post showing how to use Wherobots for a retail cannibalization study. Thanks Sean and Ilya for being a part of the community and sharing how you’re building geospatial products using Wherobots!
Understanding the impact of opening a new retail location on existing locations is an important analysis in the commercial real estate industry. In this code-heavy blog post the YuzuData team detail a retail cannibalization analysis using WherobotsDB, Overture Maps point of interest data, drive-time isochrones using the Valhalla API, and visualization with SedonaKepler. Sean also presented this analysis earlier this week in a live webinar.
Read the blog post or watch the video recording
One of the most exciting features in Wherobots’ latest release is WherobotsAI Raster Inference which enables running machine learning models on satellite imagery for object detection, segmentation, and classification. This post gives a detailed look at the types of models supported by WherobotsAI and an overview of the SQL and Python APIs for raster inference with an example of identifying solar farms for the purpose of mapping electricity infrastructure.
Read the blog post to learn more about WherobotsAI Raster Inference
WherobotsDB VTiles is a highly scalable vector tile generator capable of generating vector tiles from small to planetary scale datasets quickly and cost-efficiently and supports the PMTiles format. In this post we see how to generate vector tiles of the entire planet using three Overture layers. Using Wherobots Cloud to generate PMTiles of the Overture buildings layer takes 26 minutes. The post includes all code necessary to recreate these tile generation operations and a discussion of performance considerations.
Read the blog post to learn more about WherobotsDB VTiles
The Wherobots Spatial SQL API enables integration with Wherobots Cloud via Python and Java client drivers. In addition to enabling integrations with your favorite data applications via the client drivers, Wherobots has released an Apache Airflow provider for orchestrating data pipelines and an integration with Harlequin, a popular SQL IDE.
Read the blog post to learn more about the Wherobots Spatial SQL API
William Lyon from Wherobots was recently a guest on The Geospatial Index podcast. In this episode he discusses the origins of Apache Sedona, the open-source technology behind Wherobots, how users are building spatial data products at massive scale with Wherobots, how Wherobots is improving the developer experience around geospatial analytics, and much more.
Watch the video recording
Want to receive this monthly update in your inbox? Sign up for the The Spatial Intelligence Newsletter:
Key takeaways
Overture membership, a taco-chain cannibalization study, Raster Inference, VTiles/PMTiles, the Spatial SQL API, a Geospatial Index podcast episode with William Lyon, and upcoming events.
Yes. This issue announces Wherobots as a Contributing Member, continuing support for Overture datasets that are produced with Apache Sedona and published as GeoParquet.
The recap says generating PMTiles of the Overture buildings layer on Wherobots Cloud takes 26 minutes.
Python and Java client drivers, an Apache Airflow provider for pipeline orchestration, and an integration with the Harlequin SQL IDE.
RasterFlow is now available in Public Preview
RasterFlow makes planetary-scale earth intelligence workflows easy and costs predictable. We are excited to announce that RasterFlow is now in Public Preview, opening up the power of planetary scale Earth Intelligence to all Wherobots Professional Edition customers! RasterFlow let’s you solve complex monitoring challenges with vision-language models or tailored models for specific use cases, without […]
Wherobots for QGIS: Cloud-Scale Spatial Data, from Wherobots Labs
Wherobots for QGIS is a new plugin that connects QGIS to Wherobots Cloud. From a panel inside QGIS, an analyst can run spatial SQL against WherobotsDB, load the results as a map layer, push a local layer up to a Wherobots Iceberg table, and pull raster data into the canvas. Why Wherobots for QGIS: Eliminating […]
How Wherobots builds with NVIDIA to let AI see the physical world
The world and what happens in it is digitized by petabytes of raw and derivative spatial datasets of various data types and scales, and the potential for applying AI to it is immense. But the AI models and agents we use every day need connectivity to tools that turn this data into usable insights and relationships. Wherobots gives AI the ability operate on and understand raw physical-world data, and NVIDIA GPUs are core to it. Architecturally here’s how this works at a high level.
El Niño 2026, atmospheric rivers, and California’s burn scars: one SQL engine, two data models
7,713 mapped building footprints sit inside or within 500 m (1,640 ft) of the 42 Eaton basins USGS rates high hazard for debris flows, and 388 km (241 mi) of mapped road and path cross the low ground below the scar. WherobotsDB finds both in SQL: a join to the USGS basins for the buildings, and a raster vector join over elevation for the roads.
share this article
Awesome that you’d like to share our articles. Where would you like to share it to:
