Amazon SageMaker now supports geospatial Processing jobs

Amazon SageMaker now supports geospatial Processing jobs, making it easier for data scientists and ML engineers to run planetary-scale ML workloads. To run such large-scale workloads, customers need a flexible compute cluster that can scale from tens of instances to process a city block, to thousands of instances for planetary-scale processing. Manually managing a DIY compute cluster is slow and expensive. Additionally, building and maintaining a standardized environment to access, process, and visualize geospatial data is complex, time consuming, and expensive. With this launch, customers can now use SageMaker’s purpose-built geospatial container with Processing jobs for a simplified, managed experience to create and run a cluster. SageMaker’s standardized, purpose-built geospatial container enables you to access a geospatial data catalog, process the data with open-source algorithms or pre-trained ML models, and visualize predictions on a map and collaborate with other team members. With just a few lines of code, you can scale out your geospatial workloads with SageMaker Processing jobs. You simply specify a script that defines your workload, the location of your geospatial data on Amazon Simple Storage Service (Amazon S3), and the geospatial container. SageMaker Processing provisions cluster resources for you to run city, country, or continent-scale geospatial ML workloads. Support for the geospatial image within SageMaker processing jobs is now Generally Available in US West (Oregon) [Region](https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/). To learn more about geospatial ML capabilities, visit the [webpage](https://aws.amazon.com/sagemaker/geospatial/), or view our [documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/geospatial.html).