AWS Public Sector Summit 2018 Geospatial Talks
Talks, sessions and workshops that may be of interest to those working with geospatial data. PRs accepted!
GOES-16 is a source of critical data for monitoring smoke, flooding impacts, burn scars, volcanic ash, and weather. However, finding and using this data can require significant investment. Element 84 married video compression and streaming technology with NASA’s Cumulus data processing pipeline, plus AWS Managed Services, to make the entire GOES-16 archive interactive on an array of formats. Users can now easily identify dates of interest for events like natural disasters, and stage a subset of the archive for analysis. And all of this scales down to $0 when not in use.
For just a moment, think of the immense amount of data generated by Earth-observing systems. The sheer volume often makes it impractical for humans alone to perform the analysis, and accordingly, many groups are turning to artificial intelligence (AI) and machine learning (ML) algorithms to support their analysis. We'll hear from Development Seed and EOS about how they are using AI and ML to unlock the power of this planetary-scale data that is becoming increasingly more accessible in the cloud. From open-source libraries and human-in-the loop initial processing passes, to fully automated pipelines, we'll examine the new capacity for analysis made possible by technology.
SkyWatch is all about making Earth-observation data digestible and accessible. They believe that creating a single place to bring together the planet’s observational datasets will make new waves in geospatial analytics. In this session, we'll take a look at how companies can take advantage of cloud-native workflows to enable access and analysis across planetary-scale datasets. You’ll hear how SkyWatch leveraged AWS serverless technologies to build a company that transforms petabytes of sensor data from space into useful information. You'll also learn how Sinergise is merging a variety of data streams through products like Sentinel Hub, and creating actionable intelligence for its users.
AWS hosts a variety of public data sets that anyone can access for free. Previously, large datasets such as satellite imagery or genomic data have required hours or days to locate, download, customize, and analyze. When data is made publicly available on AWS, anyone can analyze any volume of data without needing to download or store it themselves. The AWS Open Data Team will share tips and tricks, patterns and anti-patterns and tools to help you most effectively stage your data for analysis in the cloud.
Thursday, Jun 21, 2:00 PM - 2:50 PM – Room 144 ABC
The need for public and private entities to collaborate and exchange data about transportation-related issues is becoming more and more prominent. This session will feature The World Bank describing DRIVER, a web and mobile application enabling field data collection and analysis of road safety incidents, currently being tested and piloted in several countries, primarily in Asia. Also featured is SharedStreets, a non-profit developing a global data infrastructure for streets, and creating new models for third-party data exchange.
Thursday, Jun 21, 9:00 AM - 9:50 AM – Room 144 ABC
The cloud can enable groups to support humanitarian and disaster response partners through all phases of the response cycle. We'll hear from the Humanitarian OpenStreetMap Team about how they are using AWS along with open-source tools to deploy a fully scalable system that can meet the needs of emergency activations and crisis response situations. We'll also take a look at a prototype for monitoring and starting a response chain based on the USGS Earthquake Notification Service.
Thursday, Jun 21, 11:00 AM - 11:50 AM – Room 144 ABC
During and after a disaster, the speed, timeliness, and accuracy of response and recovery efforts can be the difference that saves many lives. In this session, you will be introduced to the Amazon Web Services Disaster Response Program (AWS DRP). We will provide an overview of the program, its purpose, services, and the capabilities designed to assist customers responding to disasters and/or emergencies. This session will also provide insights into “the Art of the Possible” as it relates to how the various native AWS Services can be used to deliver the capabilities required to assist customers in accessing critical data, infrastructure, and decision making tools during disasters.
Thursday, Jun 21, 3:05 PM - 3:55 PM – Room 152 AB
NASA, Alaska Satellite Facility and the University of Washington are all going through the process of empowering groups of internal and external users to work with planetary scale datasets. This session will look at the various techniques used to power those internal revolutions and lower the cost of knowledge for all.
Thursday, Jun 21, 10:00 AM - 10:50 AM – Room 144 ABC
Real-Time Machine Learning on Satellite Imagery: How DigitalGlobe Uses Amazon SageMaker to Massively Scale-up Information Extraction from Satellite Imagery
If you have ever searched for directions, called an Uber, or looked up a trailhead, you have used DigitalGlobe’s imagery or information derived from it. DigitalGlobe went all-in on AWS to meet the growing demand for commercial geo-intelligence, migrating its entire 18-year imagery archive to the cloud. With the new WorldView Legion satellite constellation coming online, DigitalGlobe looked to leverage AWS for migrating their GBDX machine learning software to autonomously analyze incoming data at scale. GBDX leverages Amazon SageMaker to drastically speed-up both inferencing & training of machine learning models, ushering in a new era of rapid feedback & iteration: a data scientist’s dream come true.
Thursday, Jun 21, 9:00 AM - 9:50 AM – Room 150 AB
This session highlights how Earth observation data shared in the cloud is accelerating research in machine learning that can have a dramatic impact on the effectiveness of future warfighting capability. Come learn about SpaceNet, a project sponsored by CosmiQ Works, DigitalGlobe, and Nvidia that makes commercial satellite imagery available for machine learning research on AWS. In this session, you will learn how AWS machine learning services like SageMaker, hyper-scale GPU compute capacity, and datasets shared in the cloud can ultimately produce machine learning models that could have a dramatic impact on the effectiveness of future warfighting capability. As the DoD strives to bring innovation directly to the warfighter, a combination of global open data sets coupled with easily built ML models can give warfighters access to critical information when the mission needs it most.
Wednesday, Jun 20, 9:00 AM - 9:50 AM – Room 146 B