Machine Learning

Announcing the Updated Machine Learning for Earth Observation Market Map

Meet the 150+ organizations that focus on machine learning applications with satellite data. 

The updated Machine Learning for Earth Observation Market Map is finally here!

The ML4EO market map is a curated list of organizations focused on different machine learning aspects with a satellite data pipeline. This release includes an additional list of 50 organizations, which we missed in the first version published in September 2020.


SpatioTemporal Asset Catalogs and the Open Geospatial Consortium

Community Voices

Data Labeling Contest: Crowdsourcing a scalable solution to generate labels for satellite imagery

A conversation with the First Place winners of the Data Labeling Contest – In September 2020, we announced the Data Labeling Contest winners. The contest was part of the Cloud Native Geospatial Outreach Day sponsored by Planet, Microsoft, Azavea, and Radiant Earth Foundation. Participants were invited to contribute to open-access training data catalogs by identifying cloudy pixels in Sentinel-2 scenes. Two hundred thirty-one labelers joined the contest, representing a wide range of educational backgrounds, institutions, and geographies. While several awards were given to the top 83 contributions in six categories, in this Q&A, we sat down with Solomon Kica from Uganda and Jhomira Vanessa Loja Zumaeta from Peru, who won the Top Labeler first prize awards. Both winners were selected for the top prize because their scores were incredibly close, a 3.6% difference, and both scores stood out from the rest of the participants.

Machine Learning

Can you guess if this place is real?

Generating synthetic training data that can improve the accuracy of machine learning models – You have probably read about fake images and videos being generated by machine learning (ML) models. While this application might sound more like a fun exercise or, in some cases, malicious activity, synthetic (aka fake) data can help improve the accuracy of ML models. For example, research has shown that Generative Adversarial Networks (GANs) can generate synthetic data to augment real medical image training data that improves liver lesion classification and medical diagnosis.

As part of a project to tackle the scarcity of training data for agricultural monitoring applications, we are using GANs to generate synthetic Sentinel-2 satellite imagery. The results reveal that our GAN model can generate realistic imagery that can be used in classification models. Check out and see how many of the images you can correctly identify as real or synthetic.


The first STAC API 1.0 release: 1.0.0-beta.1

I’m pleased to share that we’ve just released STAC API 1.0.0-beta.1. This is our first release of the API since we split the specification, with STAC now living in its own repository. You can see the latest specification in the stac-api-spec repository, and we link to browsable API representations of the major portions below.

What started out as a pretty modest release ended up snowballing into a major amount of work, but I think we’re all pretty proud of the end state. Our main goal was to have a version of the API that was released standalone, independent of the STAC Core releases. In previous versions, it was just assumed that a version number applied to both the STAC content and the API. So we wanted to enable services could be more explicit about which version of each they supported — one could upgrade the service to 1.0.0-beta.1 API, but have it still serve STAC 0.9.0 Items.

Machine Learning

Advancing AI for Earth Science: A Data Systems Perspective

Tackling data challenges and incorporating physics into machine learning models will help unlock the potential of artificial intelligence to answer Earth science questions.

The Earth sciences present uniquely challenging problems, from detecting and predicting changes in Earth’s ecosystems in response to climate change to understanding interactions among the ocean, atmosphere, and land in the climate system. Helping address these problems, however, is a wealth of data sets—containing atmospheric, environmental, oceanographic, and other information—that are mostly open and publicly available. This fortuitous combination of pressing challenges and plentiful data is leading to the increased use of data-driven approaches, including machine learning (ML) models, to solve Earth science problems.

Community Voices

Zhuangfang NaNa Yi: Building Machine Learning Applications that Empower Policymakers with Insights to Support Vulnerable Communities

A conversation about the nuances of applying machine learning algorithms to Earth observation for global development organizations.

It is our pleasure to Dr. Zhuangfang NaNa Yi, a machine learning engineer at Development Seed, supporting international development organizations like UNICEF, the World Bank, and USAID in making data-driven policy decisions. She has extensive experience in applying machine learning algorithms to geospatial and satellite data, from building applications that farmers can use to track crop types and changes to water bodies, mapping forest and measuring food security, and more.


The Tools to Make Spatial Data More Open

How the STAC tool ecosystem is growing towards supporting truly open spatial data.

The STAC specification is transforming the way data providers and consumers are thinking about how to work with open spatial data. It provides a clear, common language for spatial data that is flexible and developed by an open community. But what is a language without the tools that speak it? The open-source STAC tooling ecosystem is a critical part of making spatial data open and accessible for use. In this post, I’ll talk about why access to that tooling provides is so important, and describe two instances of collaboration I experienced in the recent STAC and Cloud Native Geospatial sprints that, to me, exemplifies the growth of STAC tooling.

Machine Learning, News

Machine Learning for Earth Observation Market Map

Meet the 100+ organizations that focus on machine learning applications with satellite data

Building geospatial machine learning applications involve many dependable moving parts, from accessing Earth observation (EO) data, labeling imagery, and generating training data to creating and developing models and running analytics. A growing list of organizations from various sectors are providing solutions and services to advance these applications. Who can help you build machine learning applications, identify patterns from your data, or run your crowdsourcing campaign? What organizations are providing software or a platform that you can utilize to develop your machine learning model?

Machine Learning

Using Generative Adversarial Networks to Address Scarcity of Geospatial Training Data

Results show models based on Generative Adversarial Networks perform better than Convolutional Neural Networks in classifying land cover classes outside of the training dataset.

In many supervised machine learning (ML) applications that use Earth observations (EO), we rely on ground reference data to generate training and validation data. These reference data are the building block of those applications and require geographical diversity if one aims to deploy the models across various geographies. Ground reference data collection, however, is an extensive process and extremely scarce in remote areas that would most benefit from the use of EO.