Community standards are specifications that are created through informal organization and are then widely adopted by a larger group. The STAC specification and Cloud-Optimized GeoTIFFs are examples of community specifications that have become de facto standards for geospatial interoperability. This talk will examine how the process of developing community standards differs from traditional standards development and how to drive adoption. Numerous examples of successful community standards will be presented.

In addition, we will provide a case study of a current effort - that of STAPI - a specification for satellite tasking, or more specifically, an API for how users can order data from the future from satellite platforms. We have been spearheading an effort to develop such a specification and after two sprints we presented at the last FOSS4G in Kosovo. This prompted a third sprint in Europe, bringing together an even larger community. Working with government groups, commercial satellite operators, and data integrators, these sprints have worked toward developing a specification as well as implementations for several commercial providers, as well as ordering APIs for public datasets.

This talk will dive into what worked for STAC and other community standards and how we are taking those lessons to develop a standardized way for collecting future geospatial data.

Over the past few years, the STAC community has witnessed an huge increase in adoption and implementation across various sectors. With its focus on interoperability and extensibility, STAC has successfully addressed the long-standing challenge of data fragmentation in the geospatial domain. By providing a unified framework for describing and accessing geospatial assets, STAC has empowered users to effortlessly discover and analyze vast amounts of Earth observation data.

Moreover, the emergence of an open-source ecosystem around STAC has been instrumental in its widespread adoption. A myriad of tools and libraries have been developed, enabling seamless integration of STAC into existing geospatial workflows. These tools encompass data providers, data processors, visualization platforms, and more, fostering a vibrant community-driven approach to solving complex geospatial challenges.

This presentation will provide insights into the current state of the STAC specification, including changes in 1.1 and the current set of STAC extensions with guidance on the use of extensions based on their maturity. In addition, we will provide an overview of the current STAC ecosystem, with a focus on the Python projects available in the stac-utils GitHub organization.

Every geospatial project begins with a quest for answers. Large Language Models (LLMs) are revolutionizing how we can directly understand user needs through techniques like natural language to data structure conversion. Over the couple years, we have been exploring how AI could be used for working with geospatial data. What started as figuring out how to use natural language to make STAC queries to find public data has led to much more, including natural language geocoding to contextual image searching of public data such as NAIP and Sentinel-2.

In this talk we will explore how AI can be used to help automate some of geospatial’s most tedious tasks using open data, and how open vision models can be combined to create powerful tools for search & discovery of earth imagery.

This talk will include an overview of AI for use in geospatial analysis, with a focus on using open data and open models. We will show some live demos to create accurate AOIs with natural language, as well as for advanced searching of landscape features in public datasets. Additionally we will give an overview of techniques like Retrieval Augmented Generation and LLM Agents and the potential for how these may be used to transform geospatial data science.