
We compare the results of two machine learning models that detect clouds in Sentinel-2 satellite imagery and share pointers about models you can try for yourself.
We compare the results of two machine learning models that detect clouds in Sentinel-2 satellite imagery and share pointers about models you can try for yourself.

k6.io provides a flexible base for load testing with a convenient scripting language, and the quickstart docs will get you pretty far, but testing with a session of TMS requests had some unique challenges.

Hear from labeling competition participants on why this diverse group of people came together, from across the world, to collaborate on a hallmark training dataset compliant with the STAC standard.

2020 was awful. Who was accessible changed radically. We, and the people around us, by necessity took on different roles. Including at work.

As we wrap up 2020, we are looking forward to the 2020 American Geophysical Union (AGU) Fall Meeting, the largest meeting of geoscientists in the world. #AGU20 is scheduled from 1-17 December and in this remote format will accommodate over a thousand hours of virtual content to minimize conflicts while maximizing global engagement! The theme for…
Responsible for the data labeling for a machine learning project? Here are some insights weโve developed while managing data labeling for machine learning.

Grantmaking organizations are often asked to fund software development, but are unsure of how to evaluate the scope, budget, or potential impact of these types of projects. We created this list of the key questions to ask when evaluating a software development proposal.

In this post, we’ll be using some advanced TypeScript libraries to help us stay type-safe even in the face of unknown inputs. In order to get the most from this post, I recommend having a basic understanding of TypeScript.

Data visualization is key to making data useful. We look at the example of the USDA Forest Service Wildfire Risk dashboard to highlight best practices for nonprofit and government leaders when designing compelling data visualizations.

We joined with Radiant Earth at the Cloud Native Geospatial Sprint to run a labeling competition for non-technical folks. This resulted in over 2.3 million square kilometers mapped and lots of lessons learned.
