Agenda

Networking with breakfast and coffee provided.

State of the Space Sector

State of the Data

State of Earth AI

State of Application

Since SatSummit last convened in 2022, we’ve seen large shifts and exciting new capabilities emerge. Constellations have emerged, and others have matured, notably in weather, SAR, hyperspectral, and GHG monitoring. Numerous Large Earth Models have been deployed, drawing on advances in Generative AI. The commercial space industry continues to work through its post-ZIRP (Zero interest-rate policy) hangover. As we witness an acceleration in climate change, our community is responding by setting new benchmarks in extreme weather monitoring and response capabilities. We are still determining how to gather the data to support new enforcement regimes designed to combat climate change.

We will hear from individuals at the center of these movements. They will brief us on the current state of play and prospects for the future across the satellite sector, data, AI, and the application of EO data to social and climate issues.

Our decisions in the next decade will crucially influence future climate scenarios, offering us the chance to define sustainable pathways for our civilization. What is this community doing to provide the data to shape those decisions?

Discussants will provide a vision for the decade ahead. They will frame the opportunity ahead and share their insights into how we can collectively rise to meet the challenge.

Networking break with beverages and snacks.

A direct dialogue between satellite industry leaders and global development and humanitarian response experts. Panelists will share how their organizations are working to accelerate earth-informed action. Panelists will reflect on the past decade, the progress that we’ve made, and the areas where progress has been elusive. They will discuss how to work across the community in our common interest.

Lunch is provided and we hope you are able to catch up with colleagues and meet new people.

Browsers and apps are the last mile for the billions of daily decisions that deserve better earth data. This rapidly developing area is benefiting from investments in gaming, AR/VR, and spatial computing. User devices can process and visualize massive geospatial data in immersive ways, unlocking entirely new use cases. Shifts to cloud computing have also put the humble browser at the forefront of scientific research. This session will explore the future of geospatial in the browser.

20th-century institutions were not built to create, manage, or share the data needed to cooperate on the global challenges we face in the 21st century. Both public and commercial institutions face limits in consolidating and harmonizing data at a global scale in a manner that is actionable, trustworthy, technically proficient, and durable. This panel will explore what institutions are needed to produce and maintain global data products and whether a new sort of institution is needed.

Our need to understand biodiversity pushes the boundaries of what’s possible with remote sensing. The UN Convention on Biological Diversity has set ambitious targets for every country to meet by 2030, but 75% of the indicators don’t have data to monitor them. Companies are being asked to disclose biodiversity impacts but don’t know where to start, and the reality of conservation on the ground is always more complicated. Join us for a lively discussion on the state of the art, and the need for better mapping of biodiversity, ecosystem conditions, and nature’s value to people.

As the world grapples with the escalating climate crisis, the imperative for open, accessible, and accurate geospatial data for nature and climate has never been more urgent. This panel will unpack open access data's critical role in democratizing data, enhancing transparency, fostering global collaboration, and accelerating innovation. The discussion will center on the significance of satellite data in enhancing public services, fostering sustainable practices, and ensuring equitable access to critical information for decision-making across various sectors. Key themes will include data accuracy, privacy considerations, and collaborative frameworks to advance the development of comprehensive digital infrastructure for public benefit. We aim to discuss the practical downstream data products that can be created with satellite data and how we can accelerate their development.

Networking break with beverages and snacks.

Overview: The cloud native geospatial paradigm has the potential to make Earth observation analysis accessible to more people, more easily. In the simplest terms, instead of downloading data before performing an analysis, it’s now possible to stream data directly from the cloud.

This workshop will explore this new capability using hands-on practical exercises, introducing participants to the incredible global datasets available online and an opinionated suite of tools that can be used to access them. At the end of the workshop, participants will have gained insight into how this cloud-native geospatial paradigm can simplify working with Earth observation data, along with practical examples to assist in implementing learnings going forward. The workshop will include a real-world use case documenting land productivity metrics, which are used as part of monitoring for the UN sustainable Development Goal indicators for 15.3.1. We’ll explore this metric using NASA’s Harmonized Landsat and Sentinel data accessed through Earthdata.

The workshop will be run as part of SatSummit in Washington, D.C. on the 16th and 17th of May, 2024. If you’re already attending SatSummit, please let us know you’re interested in attending the workshop by completing this form. If you'd like to attend the workshop independently of the broader event, you can purchase a Cloud Native EO Training Only ticket.

Requirements: This is an introductory workshop, but some experience with programming languages like Python will be helpful. If you have significant experience working with large volumes of Earth observation data, but haven’t worked with cloud native technologies like Cloud Optimised GeoTIFFs indexed in a Spatio-Temporal Asset Catalog, there are likely some techniques that will be covered that are useful.

We’ll provide a small hosted development environment, and an Internet connection, so you only need to bring a laptop along. If you have a way of working with Jupyter Notebooks that you like, you can run the workshop in your environment. Key Python libraries we’ll be using include Xarray, Geopandas, PySTAC Client, ODC STAC and ODC Geo.

Hear from innovators at the cutting edge of using Earth science for humanitarian benefits in this fast-paced session that features live pitches from teams that are primed to scale their innovations. Eleven finalist teams will share results from their pilot projects and a positive vision to scale the impact of their work, fielding questions and comments from panelists representing NASA, AWS, The World Bank, PVBLIC Foundation, The Gates Foundation, and Mercy Corps Ventures.

Earth Observation Foundation Models are a potential game-changer for climate and sustainable development. Distilling and synthesizing vast amounts of earth observation (EO) data is a powerful way to provide useful inputs for numerous downstream applications such as forest carbon measurement, disaster detection, or crop monitoring at a lower cost.

This hands-on workshop will introduce participants to applying Earth Observation (EO) foundation models in their own work. Participants will practice finetuning existing EO foundation models for specific sustainability applications, such as land cover, crop harvests, or flooding. The workshop will cover foundation models such as 1) Clay, 2) IBM and NASA's watsonx.ai geospatial foundation model, and 3) potentially a model from the European Space Agency’s FAST-EO project. With support from Amazon Web Services, participants will use SageMaker notebooks to do this exploration at no cost.

The workshop will be run as part of SatSummit in Washington, D.C. on the 16th and 17th of May, 2024. If you’re already attending SatSummit, please let us know you’re interested in attending the workshop by completing this form. If you'd like to attend the workshop independently of the broader event, you can purchase a AI Finetuning Training Only ticket.

Facilitated by: Clay

Trillions of dollars are required to decarbonize energy infrastructure, build climate-adapted infrastructure, and preserve critical ecosystems. Up to 2/3 of this cost will fall on under-resourced local governments. Donors and private investors will be needed to meet our climate commitments, and these investors will require assurance that their investments are well spent.

This panel aims to discuss this practical, medium-term, detail-oriented needs and brainstorm ways that EO data and services may help stakeholders put money into the right place and share success stories with stakeholders.

Numerous efforts have been made to map people and structures. These include “traditional” efforts from US and EU research and government institutions and crowdsourced efforts like OpenStreetMap. Recently, we’ve seen the addition of massive AI-derived open building datasets from Meta and Google and the launch of the Overture Foundation. How do these efforts compare? How can they build off each other? How should we get them into use by National Statistics Offices and government decision-makers?