With dozens of satellites in orbit and many more scheduled over the coming year, the size and complexity of geospatial imagery continues to grow. It has become increasingly difficult to manage this data deluge and use it to gain valuable insights.
After the successfully launch of 88 Dove satellites — the largest satellite constellation ever to reach orbit, Planet Labs reached its Mission 1: the ability to image all of Earth’s landmass every day. Fully realizing the ‘Mission 1’ means preparing for 7 to 10 TBs of data per day!
The resources required to handle all of this satellite data are mammoth. That’s where Google Cloud Platform (GCP) steps in.
Planet Labs announced that after a year of evaluating several options and factors — of which reliability and scale were at the top of the list — finally Google Cloud Platform (GCP) powers its critical infrastructure. Planet Labs is now processing all of its satellite imagery on GCP. The migration process which has been completed was actually initiated in December, 2016. And Google Cloud now hosts Planet Lab’s growing imagery archive and the data pipeline processing.
GCP will provide the core storage and compute services needed to manage the pipeline and make it scale-able. According to Planet Labs, “Google’s focus on multi-region services aligns with our processing model. We find the GCP pricing model easy to understand and very predictable with their Custom Machine Types and Preemptible VMs, which we use heavily. We are already using new capabilities like Cross-Project Networking (XPN), and Internal Load Balancing (ILB). We are confident GCP will allow us to scale up usage as more satellites (88 to be exact!) come online in the coming months.”
This is not for the first time Google Cloud has provided a way out. Earlier, in October, 2016 Google Cloud brought two of the most important collections of public, cost-free satellite imagery to its platform: Landsat and Sentinel-2.
The Landsat mission, as we all know was developed under a joint program of the USGS and NASA is the longest continuous space-based record of Earth’s land in existence, dating back to 1972 with the Landsat 1 satellite. Landsat data has proven invaluable to agriculture, geology, forestry, regional planning, education, mapping, global change and disaster response. This collection includes the complete USGS archive of the Landsat 4, 5, 7 and 8 satellites, and the data is updated as new data arrives from Landsat 7 and 8. The collection is updated daily and contains a total of 4 million scenes and 1.3 petabytes of data covering 1984 to the present — over 35 years of imagery of our Earth ready for immediate analysis.
Whereas Sentinel-2, part of the European Union’s ambitious Copernicus Earth observation program, raised the bar for Earth observation data, with a Multi-Spectral Instrument (MSI) that produces images of the Earth with a resolution of up to 10 meters per pixel, far sharper than that of Landsat. Sentinel-2 data is especially useful for agriculture, forestry and other land management applications. The collection currently contains 970,000 images and over 430 terabytes of data, updated daily.
Google has years of experience working with the Landsat and Sentinel-2 satellite imagery collections. Its Google Earth Engine, a Cloud-based platform for doing petapixel-scale analysis of geospatial data, was created to help make analyzing these datasets quick and easy. Earth Engine’s vast catalogue of data, with petabytes of public data, combined with an easy to use scripting interface and the power of Google infrastructure, has helped to revolutionize Earth observation. By bringing the two most important datasets from Earth Engine into Google Cloud, it has also enabled customer workflows using Google Compute Engine, Google Cloud Machine Learning and any other Google Cloud services.
One of its customers that have taken advantage of the powerful combination of Google Cloud and these datasets is Descartes Labs (Read our exclusive story). Descartes Labs is focused on combining machine learning and geospatial data to forecast global crop production. Spaceknow is another company using Google Cloud to mine Landsat data for unique insights. Spaceknow brings transparency to the global economy by tracking global economic trends from space. Spaceknow’s Urban Growth Index analyzes massive amounts of multispectral imagery in China and elsewhere. Using a TensorFlow-based deep learning framework capable of predicting semantic labels for multi-channel satellite imagery, Spaceknow determines the percentage of land categorized as urban-type for a specified geographic region.
Planet Labs will now efficiently deliver data through its API and Web tools to its users and customers across the globe. “Philosophically, we are aligned with Google’s focus on services leveraging open source projects like Kubernetes and TensorFlow. As our data and compute infrastructure grows, we are excited to work with Google Cloud to deliver next-generation geospatial services to users,” said Planet Labs.