Machine Learning, News

Data Labeling Contest – Cloud Native Geospatial Sprint

Standards

Welcoming New Collaborators to the Cloud Native Geospatial Ecosystem

I wanted to share some background and more details about the Cloud Native Geospatial Outreach Day and Sprint (1 week away! September 8th — signup here), which has grown out of the SpatioTemporal Asset Catalog (STAC) community sprints. One of our goals for STAC has been to make it a truly collaborative community, and one that is welcoming as possible. We believe that the best standards are forged from diverse use cases and perspectives coming together and collaborating. We started with a gathering of 25 people from 14 organizations and have always sought to bring more people into the fold.

Machine Learning, News

Radiant Earth Foundation Awarded Cooperative Agreement from NASA

News

Radiant Earth Foundation Leadership Transition

Radiant Earth Foundation today announces the transition of executive leadership effective September 1, 2020. Anne Hale Miglarese, the founder and CEO, will exit the organization as a full-time employee and remain as a member of the Board of Directors. Hamed Alemohammad, Radiant Earth’s Chief Data Scientist, will also assume the duties of Executive Director of the organization and join the Board of Directors. Board member Jerry Johnston will become the Chairman of the Board of Directors.

Standards

Join the ‘Cloud Native Geospatial’ Outreach Day and Sprint

On September 8th we will be continuing SpatioTemporal Asset Catalog (STAC) Sprint #6, but we decided to expand its scope to include more of the ‘Cloud Native Geospatial’ ecosystem. The core idea of Cloud Native Geospatial is articulated in this ‘blog series’, with the first post positing the question: ‘what would the geospatial world look like if we built everything from the ground up on the cloud?’. The second post introduced the Cloud Optimized GeoTIFF (COG), and it has since emerged as a default format for anyone doing geospatial on the cloud.

Standards

Join us for STAC Sprint #6 — our first fully remote event

With the SpatioTemporal Asset Catalog (STAC) spec recently reaching 1.0.0-beta, we figured it’s time for one final sprint before we push out 1.0.0 final. The goal with STAC has always been to ensure that the specification meets real-world needs, by always iterating its improvements in conjunction with actual implementations. One early goal was to reach 1 billion records in STAC before we go to 1.0.0, but we achieved that much earlier than expected. But the various catalogs have not necessarily upgraded to the latest STAC version right when it comes out. So our main goal for the sprint is going to be to upgrade all the STAC software and catalogs to the latest 1.0.0 beta specification and ideally add several new catalogs and data types. The goal will be to ensure that STAC is flexible enough to handle anything, so when we reach 1.0.0 the core will not need to change.

Machine Learning, News

Radiant Earth Foundation Releases the Benchmark Training Data “LandCoverNet” for Africa

LandCoverNet is an open-access global land cover classification training dataset with satellite image pixels labeled for seven land cover classes.

Radiant Earth Foundation is proud to announce the release of “LandCoverNet,” a human-labeled global land cover classification training dataset. Available for download on Radiant MLHub, the open geospatial library, LandCoverNet will enable accurate and regular land cover mapping allowing for timely insights into natural and anthropogenic impacts on the Earth. This release contains data across Africa, which accounts for ~1/5 of the global dataset.

Machine Learning, News

Radiant MLHub Hosts STAC-Compliant SpaceNet’s Datasets

Founded in 2016 to accelerate open source geospatial machine learning, SpaceNet is a nonprofit organization that runs data challenges and releases the training datasets, baseline algorithms, winning algorithms, and detailed evaluations under an open source license. They have organized six data challenges to date, each focusing on a different problem that applies machine learning to satellite imagery to solve complex mapping problems.

Machine Learning

Open Earth Observation Data in the Age of Machine Learning

The More Things Change, the More They Stay the Same.

Not so long ago, there was just one viable source for Earth imaging data: Landsat, a joint program of NASA and the U.S. Geological Survey whose mission dates back to 1973. Back then, civilian remote sensing was still in its infancy and commercial satellite operators were unheard of. And yet, the nascent professional remote sensing community was galvanized by the promise of what could be. Decades later, civil society has a wealth of commercial and government Earth observation data to analyze, and more is on the way thanks to a dramatic period of innovation whose day is almost here. Innovation fueled by the confluence of available Earth observation data, machine learning methods, cloud computing and an expanding data science workforce that is eager to create new products and solutions, will change everything. And in some respects, nothing.

Machine Learning

Enhancing Earth Observation Solutions in Agriculture with Machine Learning

Machine learning (ML) and Earth observation (EO) are complementary technologies. While EO helps us understand natural and anthropogenic changes on the Earth, ML empowers us to analyze vast amounts of imagery and build new models for EO data that would have been very difficult if not impossible using traditional physical models a few short years ago.

The promise ML and EO hold for agriculture are immense. EO satellites capture data at a global scale, and ML techniques can use these data to map croplands at local, regional, and continental levels, which provide input for farmers and policymakers alike. In particular, the ability to estimate crop yield or detect pest/disease damage during the growing season will be game-changing in addressing food insecurity problems.