An island, Nishinoshima, rises out of the Pacific Ocean off the coast of Japan in this December 31, 2013 image captured by WorldView 2. Photo: DigitalGlobe.

DigitalGlobe, now a business unit of Maxar Technologies, has migrated its entire 100-petabyte imagery library to Amazon Web Services (AWS), which will give its customers instant access to its vast library of geospatial images, eliminating the need to wait for tapes and disks to be retrieved for content, the company stated. DigitalGlobe, its sister division Radiant Solutions, and its partner ecosystem also leverage AWS’ frameworks and tools to build machine learning applications that allow their customers to incorporate valuable geospatial information extracted from commercial satellite imagery into their work flows.

DigitalGlobe is using AWS’ suite of machine learning capabilities, including the newly released Amazon SageMaker, to build, train, and deploy machine learning applications. By using Amazon SageMaker’s machine learning algorithms, DigitalGlobe states it can predict what images customers will request next based on their usage patterns. As a result, it can intelligently tier its image library to keep relevant imagery readily accessible in Amazon Simple Storage Service (Amazon S3) and the remainder of its library in AWS’ lower-priced archival service, Amazon Glacier.

In addition to optimizing storage costs, DigitalGlobe’s customers gain faster access to the right images needed to extract actionable intelligence. To enable this, DigitalGlobe built its Geospatial Big Data platform (GBDX) on AWS to provide data curation, analysis, and delivery. DigitalGlobe’s new product, GBDX Notebooks, will integrate Amazon SageMaker to make it easier for customers to build and deploy machine learning models that extract data from DigitalGlobe’s satellite imagery library for detailed business insights.

“Few companies work with the sheer volume of data that DigitalGlobe does. When working at this volume, it’s nearly impossible to scale and rapidly innovate without the cloud,” said Teresa Carlson, vice president of worldwide public sector sales at AWS. “DigitalGlobe was the first customer to use AWS Snowmobile — AWS’ exabyte-scale data transfer service that uses a 45-foot long ruggedized shipping container pulled by a semi-trailer truck — to move their massive image library to AWS. Ever since, they have been pushing the boundaries of what’s possible with large data sets.”