AWS re:Invent 2020 Geospatial Talks
Talks, sessions and workshops that may be of interest to those working with geospatial data. PRs accepted!
As the world population expands and food insecurity reaches record levels, the collective need for agriculture to produce more output with fewer resources is critical. Using Earth observation data brings insights to agriculture and helps inform improved practices and outcomes in farms from Africa to Brazil and beyond. In this session, hear how you can find publicly available Earth observation data relevant for agriculture on AWS, and learn how customers like OneSoil, Sinergise, and Digital Earth Africa are using the cloud to build tools that enable renewable practices.
Satellites revolving around the earth collect petabytes of data every day and send them back for ingestion, categorization, processing, and dissemination. While more organizations dedicate resources to environmental monitoring and predictive analytics, it is essential to not just give them the platform to implement their technologies but also share the responsibility in solving the problem. In this session, learn how to use AWS Ground Station, Amazon SageMaker, and data lakes to automate, scale extreme weather event detection, and help build disaster resilience. You also hear how Fireball International delivers early wildfire detection services through multi-sensor rapid wildfire intelligence.
Aerospace and intelligence companies are going all in on AWS to automate and scale space operations. Take a deep dive into how Maxar Technologies is using AWS to advance the future of space in the cloud using AWS Ground Station, AWS storage solutions, machine learning, and high-performance computing to predict where clouds and storms will be in order to deliver actionable earth intelligence to the world. Learn how Maxar uses the AWS Cloud and how they design space infrastructure to accelerate space exploration to the moon, Mars, and beyond.
In response to COVID-19, city planners more than ever need situational awareness of what is happening in their cities. This session brings together cross-domain skills in IoT, connectivity, and data analytics. Learn how to integrate IoT networks (such as LoRaWAN) with AWS Lake Formation data lakes and present geospatial analytics using Amazon QuickSight. Additionally, you learn how this reference architecture can be extended with AWS Marketplace solutions. Finally, the session includes a demonstration incorporating simulated city data.
Fueled by heat and wind, wildfires are burning throughout states on the West Coast of the United States. As part of its continued efforts to reduce the risk of wildfire, San Diego Gas & Electric (SDG&E) is building machine learning models using AWS services to automatically identify asset damage on drone imagery and vegetation risks on satellite imagery. Also, to improve customer awareness ahead of public safety power shutoff events, the company has expanded its communication channels to smart assistants that enable convenient access to important information.
We can use the power of drones, machine learning, and Internet of Things on the edge and the cloud to make turbine maintenance safer and more cost-effective. In this scenario, drones take pictures of turbines, while the solution analyzes the photos to detect damage or issues on the structure, achieving safer, quicker, and more accurate inspections. The inspection outputs are then used in business intelligence for issue monitoring, analytics, and forecasting for better decision-making processes. The project also showcases how the capabilities of digital twin technology can be leveraged for remote monitoring of wind farms.
After disasters and in rural areas, connectivity is limited, intermittent, or not available. As drone usage increases for disasters and humanitarian use cases, the ability to process imagery in no- or low-connectivity environments gives organizations information critical to planning and response. Take a deep dive to learn how the AWS Disaster Response program collaborated with NGOs like Help.NGO to prepare, provision, and operate a drone imagery pipeline at the edge using AWS Snowball devices. The faster that drone imagery can be processed, the faster it can get to decision makers.
Capella Space is leveraging Amazon SageMaker to build complex machine learning (ML) models on Synthetic Aperture Radar (SAR) satellite imagery. By applying ML to SAR imagery, Capella can begin automatically detecting global events in near-real time without being hindered by weather or time of day. Join this session to learn which approaches can be applied to geospatial use cases and learn architectures for labeling, training, and deploying geospatial ML models on AWS.
Managing compute instances to view, run, or share a notebook is tedious. Amazon SageMaker offers several choices to use Jupyter notebooks, including Amazon SageMaker Studio. SageMaker Studio notebooks are one-click Jupyter notebooks that you can spin up quickly. The underlying compute resources are fully elastic, so you can easily dial up or down the available resources, and the changes take place automatically in the background without interrupting your work. You can also easily share notebooks with others, making collaboration easy and scalable. In this session, see a demo of SageMaker Studio and other ways to use Jupyter notebooks for building machine learning models.
Desbloqueando dados do espaço para resolver desafios do planeta Terra (Unlocking space data to solve challenges on planet Earth)
Os dados do espaço habilitam formas sem precedentes para monitorar, compreender e navegar nos dados em nosso planeta em constante mudança. Nesta sessão, apresentaremos toda a jornada do cliente. Demonstrando o pipeline de dados, incluindo a captura e o processamento de imagens geoespaciais usando AWS Ground Station, Sagemaker e Step Functions com base nas experiências de clientes na América Latina. A primeira parte desta apresentação será dedicada à AWS Ground Station, que permite que organizações públicas e privadas façam a ingestão de dados de satélites na AWS, permitindo acesso de baixa latência. A segunda parte da apresentação explorará os recursos de machine learning nas imagens de satélite extraindo insights de negócios endereçando desafios globais.