More and more businesses are pressed to find technologies that can hold and crunch massive data sets. A business specializing in geospatial data, including satellite imagery of the entire globe, will likely the feel the squeeze more than most. What lessons can they share with the rest of the business world on meeting unprecedented data demands?

Descartes Labs Inc. offers geospatial data services to industries from energy to agriculture. “What we’ve seen is there’s not just the magic data set that gives you the pure answer,” said the company’s co-founder Tim Kelton (pictured). “It’s fusing of a lot of these data sets together to tell you what’s happening and then building models to predict how those changes affect our customers, their businesses, their supply chain, all those types of things.”

Inspired by the potential of machine learning to recognize images and suss out patterns, Descartes Labs opened for business in 2014. The company knew it would need technology that could bite off and chew petabytes of data in brief cycles — even a petabyte a day, according to Kelton.

“One of our big questions early on was actually could the cloud actually even handle that type of scale?” he said. The company opted for the Google Cloud Platform in part due to the vast Google LLC network and reliance on open-source software. 

Kelton spoke with John Furrier (@furrier) and Dave Vellante (@dvellante), co-hosts of theCUBE, SiliconANGLE Media’s mobile livestreaming studio, during the Google Cloud Next event in San Francisco. They discussed the challenge of processing geospatial data as well as various successful use cases. (* Disclosure below.)

A pound of data yields an ounce of prediction

Descartes culls data from satellites, sensors overhead and on the ground and other sources to render geospatial information. Its data might be used to predict crop yield, prevent famine and gain insight on natural disasters such as hurricanes.

“Often it’s the temporal cadence that’s almost the key indicator on seeing how things are actually changing over time. And people are coming to us and saying, ‘Can you quantify that?'” Kelton said.

In order to do so, Descartes must ingest floods of data daily through its cloud-native platform. The scalability of Google’s network helps, as do its open-source components — like the Kubernetes orchestration platform for containers (a virtualized method for running distributed software applications).

“We read the Kubernetes source code; we’ve committed changes,” Kelton said. “When you get in really hard problems, you kind of need to understand that code sometimes at that level.”

Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of the Google Cloud Next event. (* Disclosure: Google Cloud sponsored this segment of theCUBE. Neither Google nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE