News, Standards

Cloud Native Geospatial Ecosystem Community Releases STAC Specification version 1.0.0 to Connect Remote Sensing Data into a Network of Information about the Earth

The SpatioTemporal Asset Catalog (STAC) specification provides a common language to describe a range of geospatial information, so it can more easily be indexed and discovered.

WASHINGTON, June 10, 2021 (GLOBE NEWSWIRE) — The Cloud Native Geospatial Ecosystem Community announces the release of the SpatioTemporal Asset Catalog (STAC) specification version 1.0.0. The STAC specification is an open metadata standard that systemically describes remotely sensed data of the Earth. The specification supports emerging cloud-based geoprocessing engines by allowing spatial data to be indexed and discovered more efficiently. This feature is fundamental when building artificial intelligence applications using Earth imagery.


STAC 1.0.0: Spec and Community Updates

While we just announced STAC 1.0.0, the initial post did not contain any of the typical information we normally include in a STAC release announcement. So in this post, we’ll dive into the details of what changed in the specification, including extensions, as well as some of the community highlights. And this will just be one of several posts diving deeper into STAC topics, including the wider ecosystem of tools.


STAC Specification 1.0.0 Released!

The SpatioTemporal Asset Catalog (STAC) community is pleased to announce the release of version 1.0.0. It’s safe to say we’re all quite proud of the release, as it’s been a large community effort for over three years. For those who haven’t heard of STAC, it provides a common language to describe a range of geospatial information, so it can more easily be indexed and discovered. You can learn more at the website, which we aim to update in the coming months to be an even better learning resource.
A Stable Foundation –I’m not going to go into all the details of the release for this post, but I’m aiming to do a series of blog posts to highlight all that has happened, share what’s next, and highlight all the amazing tools in the community. The one thing I do want to share is what a 1.0.0 release means for us. Our goal for the core STAC specification is to provide a foundational layer for the emerging ‘Cloud Native Geospatial’ ecosystem. We believe that the future of geospatial information is fully online and in the cloud, and STAC aims to help connect diverse data into a network of information about our planet (and even other planets).

Machine Learning

Publish your training data on Radiant MLHub for NeurIPS 2021

Submissions to the new Datasets and Benchmarks track require data documentation and availability on an open repository.

Organizers of the NeurIPS 2021 conference recently announced a new track for Datasets and Benchmarks. This is a significant development for a major machine learning (ML) conference to highlight the importance of data in developing algorithms for real-world problems. We at Radiant Earth Foundation welcome this initiative and applaud the organizers for establishing this new track.

In recent years, there have been many discussions and arguments to incentive ML researchers to work on real-world problems. One of those incentive mechanisms is the opportunity to publish a paper in a peer-reviewed conference, and getting recognition for working on these problems. The new track at NeurIPS is a necessary step to realize these incentives.


Machine Learning

Socially Responsible Data Labeling

Generating a global training dataset while supporting social initiatives and sustainable practices.

Labeling satellite imagery is the process of applying tags to scenes to provide context or confirm information. These labeled training datasets form the basis for machine learning (ML) algorithms. The labeling undertaking (in many cases) requires humans to meticulously and manually assign captions to the data, allowing the model to learn patterns and estimate them for other observations.

For a wide range of Earth observation applications, training data labels can be generated by annotating satellite imagery. Images can be classified to identify the entire image as a class (e.g., water body) or for specific objects within the satellite image. However, annotation tasks can only identify features observable in the imagery. For example, with Sentinel-2 imagery at the 10-meter spatial resolution, one cannot detect the more detailed features of interest, such as crop types but would be able to distinguish large croplands from other land cover classes.

Community Voices, Machine Learning

Igor Ivanov: Harnessing Machine Learning Skills to Reduce Damages from Tropical Storms

A conversation with the First Place winner of the Radiant Earth Tropical Cyclone Wind Estimation Data Competition

We recently announced the Radiant Earth Tropical Cyclone Wind Estimation Data Competition winners, a contest designed to build a machine learning (ML) model to improve NASA IMPACT’s Deep Learning-based Hurricane Intensity Estimator. Seven hundred thirty-three participants leveraged NOAA’s Geostationary Operational Environmental Satellites (GOES) imagery to estimate the wind speeds of storms at different points in time using satellite images captured throughout a storm’s life cycle. In this Q&A, we sat down with Igor Ivanov from Ukraine, winner of the first place Development Seed Award, to talk about his journey to become a data scientist and winning the contest.

Community Voices

Ashiraf Nsibambi Kyabainze: Technology and Social Entrepreneurship in Uganda

A conversation about using technology for a smart value chain to boldly impact food insecurity in Uganda

Meet Ashiraf Nsibambi Kyabainze, the founder of At HAUSE Limited, is a Ugandan entrepreneur working on African technology. The recipient of several awards, including Africa’s Top Young Entrepreneurs Award (RUFORUM) in 2018 and the Mandela Washington Fellowship for Young African Leaders Initiative Network agribusiness champion in 2019, Ashiraf founded At HAUSE to support agricultural and agribusiness workers by improving their packaging with insect-resistant solutions. At HAUSE’s business model reduces crop waste all while ensuring better financial returns for farmers.

Machine Learning

Radiant MLHub Python Client — Beta Release

Using the Python client to discover and download training datasets without managing API requests.

Community Voices, Machine Learning

Celebrating Women Leading the ML4EO Community

Meet the rising stars of women around the world at the forefront of machine learning for Earth observation.

Happy International Women’s Day!

Today, we celebrate the women who break barriers and expand the frontiers of machine learning for Earth observation. This essential field can help us understand the planet’s ecosystem, its different elements, interactions, and changes.

These 15 leading women were selected from 56 outstanding nominations from the ML4EO community. The Radiant Earth Foundation selection committee created a set of criteria to rank the nominees.


SpatioTemporal Asset Catalog (STAC) 1.0.0-rc.1 Released