Cloud computing offers immense potential for processing and analyzing geospatial data at scale, enabling faster and more efficient workflows with large amounts of satellite imagery, vector data, and other spatial datasets. Amazon Web Services (AWS) provides a suite of services that are particularly well-suited for geospatial workflows. This training is designed to introduce participants to the key AWS services used in geospatial workflows, such as EC2 for scalable computing, S3 for data storage, SageMaker for building and training machine learning models, and the AWS Open Data Registry for accessing geospatial datasets. Through practical examples and hands-on sessions, participants will learn how to design, implement, and optimize geospatial workflows using AWS while understanding the underlying architecture and best practices for managing cloud-based resources, including pricing.
This workshop organized by the Center of Expertise in Big Geodata Science (CRIB) in collaboration with AWS Netherlands, will cover the following aspects:
A. High-level introduction, including:
- Overview of AWS services relevant to geospatial workflows, such as EC2, S3, SageMaker, and Open Data Registry.
- Understanding AWS's operating model and cost management.
- Case study: selecting the appropriate AWS services and configurations for geospatial data processing.
B. Practical hands-on sessions, including:
- Setting up a SageMaker environment for geospatial analysis.
- Accessing Earth Observation (EO) data on AWS using STAC.
- Performing EO imagery analysis using xarray.
- Managing outputs by storing intermediate and final data by using AWS services.
For more information and training programme, please visit the training page.
