We are a home for Earth science data and computing professionals. Our sessions bring together the community for hands-on, interdisciplinary deep dives as we explore "Bridging Divides: Data, Technology, Community" this year. Learn more about this theme on the ESIP Meetings page.
Session and plenary recordings will be published on the ESIP YouTube Channel.
Explore how Earth science careers can thrive in an AI-enabled future by connecting human skills, values, and professional growth.
Gather community insights on what builds trust, transparency, and effective human-AI collaboration in Earth science applications.
Participants can share open job and proposal opportunities
Outcomes: For Research paper insights that inform best practices for AI application development and recruiting.
Define what makes AI trustworthy, transparent, and useful in Earth science.
Recognize the human capabilities that will help professionals thrive alongside AI.
Identify personal strengths, values, and actions that support career growth during times of technological change.
Audience Early-career and mid-career professionals balancing family and work; participants from all levels of experience across public sector, private sector, and program management
Open unconference session — topics and format to be determined collaboratively by attendees on the day. All five rooms are available. Participants self-organize into groups around topics of shared interest and report back to the broader group.
When an AI client talks to a map, a STAC catalog, or an analysis runtime, something has to define the contract between them — what state looks like, how geometry travels, how results come back interpretable. Right now every team is inventing this contract independently. This session is a working comparison across groups actively building in the space: what patterns are emerging, where they diverge, and which design choices are hardening into defaults. Through demos and short pattern talks, the session surfaces tradeoffs (reliability vs capability, declarative vs imperative, transparent vs magical) and opens the floor for community questions that don't have answers yet. Laptops welcome. Partly a public design review of the ESIP Lab MCP Mapping work and EO-GPT.
Audience EO data stewards and tool builders thinking about how their systems will be consumed by AI clients; practitioners building LLM-driven geospatial workflows; ESIP Machine Learning Cluster, IT&I, and Semantic Harmonization Cluster members; non-developer analysts and educators
