Day 1: Wednesday, April 30

Workshop: Interfacing with Cloud-Native Overture Data and the GERS Ecosystem

1:15PM - 2:45PM | Ballroom 2 - Dana Bauer, Jennings Anderson (Sean Knight will be joining from Wherobots)

We'll be joining Overture Maps Foundation's workshop on the GERs ecosystem. Overture Maps GERS IDs are powerful, but what if your dataset doesn’t already include them? In this workshop demo, we’ll show how to use Wherobots to assign GERS IDs to non-Overture Maps data and join it with Overture Maps data. The demonstration will focus on a real-world retail and restaurant use case.

Day 2: Thursday, May 1

Talk: Introducing geospatial support in Apache Iceberg (Systems: Innovations in System Design) 

9:45AM - 11:15AM @ Magpie A | Jia Yu

This talk explores Apache Iceberg’s new native geospatial support (Iceberg Geo), tackling challenges in large-scale spatial data management. It covers Iceberg Geo’s development, design, and goals, highlighting its impact on both geospatial and Iceberg communities.

Talk: Extract insights from satellite imagery at scale with WherobotsAI (Getting Started with Cloud-Native Geospatial Workflows 1: Solutions)

1:45AM-1:15PM @ Wasatch A | Damian Wylie

Inferring objects and detecting change in satellite imagery was once reserved for companies with the talent, money, and time to build, manage, and run sophisticated, self-managed machine learning (ML) inference solutions against satellite data. Now with Wherobots, you can easily put your models into production with WherobotsAI Raster Inference. Learn about it in this session, as well as where we are taking it with our latest Meta SAM 2 model, and coming soon, the TorchGEO model ecoysystem. 

Birds of a Feather Discussion (BoF): Making ML models accessible with TorchGeo and the STAC Machine Learning Model extension

3:00PM-3:45PM @ Wasatch B |  Ryan Avery and Isaac Corley

Discovery geospatial models that are relevant for a particular use case, trained on a geography of interest, and documented enough to run it is difficult. To address this problem, the STAC Machine Learning Model (MLM) Extension standardizes descriptions of machine learning models trained on overhead imagery. The STAC MLM extension supports describing "foundational" models that generate image embeddings as well as computer vision models that produce classification, detection, or segmentation results.

TorchGeo, a framework for training deep remote sensing models, also supports these same kinds of models, allowing for an integration where TorchGeo can export models that can be easily catalogued and run in different execution environments on the correct STAC data.

In this session we will present a short overview of the STAC MLM Extension, present some use cases, and discuss how we can make it better so that it is easier to find machine learning models and run them on the correct datasets. We'll also talk about progress on integrating STAC MLM into TorchGeo, so that any model trained in TorchGeo is more portable and can be run with minimal dependencies.

This will mostly be a discussion based format, so bring any questions or feedback you have about TorchGeo or the STAC MLM extension!

Panel: Builders Panel 

4:30pm-5:15pm @ Ballroom 2-3 | Mo Sarwat, Amy Rose, Sean Gorman

Hear from some of the founders and builders of the movers and shakers in the geospatial data community as they explore the journey of their respective projects, and share what they see might be coming soon. 

Meet the Team

If you’re interested in chatting about anything related to geospatial data or have questions about how we can help with cloud-native geospatial, come say hi and connect with the team!

• Mo Sarwat - Co-Founder and CEO, Creator of Apache Sedona
• Jia Yu - Co-Founder and CTO, Creator of Apache Sedona
• Ben Pruden  - Head of Go-to-Market
• Damian Wylie - Head of Product
• Sean Knight - Senior Solutions Architect
• Ryan Avery - Senior ML Engineer
• Isaac Corley - Senior ML Engineer
• Chris McCormick - Founding Account Executive

Or feel free to leave your contact information and we'll reach out to find a time to meet!