Thought Leadership

Democratizing Open Machine Learning Technologies for Earth Observation

I had the privilege of speaking at the closing plenary at the Pecora conference last month. The session’s theme was “The Next 50 Years: Synergy and Collaboration.” It gave me a chance to reflect on my experiences within the Earth science community and our plans for the future of Radiant Earth Foundation.

Inspired by the wonderful presentations Paul Ramsey has given over the years, this post attempts to create a readable version of my presentation at Pecora. It is the first in an ongoing series on our approach to create a more sustainable ecosystem of open machine learning and Earth science community.

Machine Learning, News, Thought Leadership

The Many Meanings of ‘Open’

Open Data, Open Source, and Open Standards
Over the past decade, much has been said about open data, open source software, and open standards. So much, in fact, that many people have begun to use the terms interchangeably. But open data, open source, and open standards are not synonymous and should not be conflated.

The confusion poses a challenge for many organizations, in particular, those which lack technological expertise but nevertheless work on global issues that seek out “open” digital solutions. In this article, we define the parameters of open data, open source, and open standards, and identify the key differences between them.

Thought Leadership

Geo-Diverse Open Training Data as a Global Public Good

As part of the Amazon Sustainability Data Initiative, Hamed Alemohammad, Chief Data Scientist at Radiant Earth was invited to share how the organization is using open data and the Amazon Web Services (AWS) Cloud to support the global development community.

Machine learning in support of the SDGs
To effectively leverage open EO data and analytics in support of the SDGs, we turn raw EO data into insights that can guide the decisions required to create a sustainable future. Machine learning is an important part of that process but has one major drawback – the lack of geo-diverse training datasets. Radiant Earth is actively working to fill that gap.

Thought Leadership

Commercial Entrants are Driving Innovation in Earth Observation — and That is All Good!

In the last installment of this blog series on the value of Earth observation (EO) data, we focused on government supplied satellite data and its use in progressing global development solutions. Government EO data are predominately characterized by high to low spatial resolution, a consistent revisit rate, constant imaging that allows for routine monitoring, and, a deep archive of data to be built up and relied upon (United Nations, 2017, p. 42 and Green et al., 2017, p. 51). In the case of the Landsat and Sentinel programs, the data are open and free to use and hosted on multiple sites globally. These satellites tend to be large, very expensive to build and launch, and can take a decade to go from design to launch and then to operations.

Thought Leadership

Government Satellite Data and Its Role in Advancing Global Development

Understanding our world and the interconnectedness of the natural and built environment is a great challenge to global development professionals as well as scientists and technologists. The role that Earth observation (EO) plays in this understanding is difficult to put in terms of economic value. However, to capture the greatest use from EO, our community is continually challenged to make this information much more accessible and ready for analysis, enabling data-driven development.