Create an Amazon SageMaker Studio Classic notebook using the geospatial image - Amazon SageMaker

Create an Amazon SageMaker Studio Classic notebook using the geospatial image

Important

As of November 30, 2023, the previous Amazon SageMaker Studio experience is now named Amazon SageMaker Studio Classic. The following section is specific to using the Studio Classic application. For information about using the updated Studio experience, see Amazon SageMaker Studio.

Before you start the following procedure, create a domain in Amazon SageMaker Domain by following the steps in Onboard to Amazon SageMaker Domain. After creating a domain, you can access the capabilities that Amazon SageMaker geospatial provides.

Note

Currently, SageMaker geospatial is only supported in the US West (Oregon) Region.

If you don't see SageMaker geospatial available in your current domain or notebook instance, make sure that you're currently in the US West (Oregon) Region.

After November 30, 2023, how you access SageMaker geospatial changed. SageMaker geospatial is only available via Studio Classic.

To create a Studio Classic notebook with the SageMaker geospatial image

  1. Launch Amazon SageMaker Studio

  2. Under Applications, choose Studio Classic.

  3. On the JupyterServer page, use the table to find the name of your existing Studio Classic space if you created one prior to November 30, 2023. To launch it, choose Open. If no previous environment exists, choose Create Studio Classic space.

    1. Give your Studio Classic space a Name.

    2. Then, choose Create space. When the space is ready for use the Status changes to Running.

  4. Choose Home in the menu bar.

  5. Under Quick actions, choose Open Launcher.

  6. When the Launcher dialog box opens. Choose Change environment under Notebooks and compute resources.

  7. When, the Change environment dialog box opens. Choose the Image dropdown and choose or type Geospatial 1.0.

    A dialogue boxing showing the correct geospatial image and instance type selected.

  8. Next, choose an Instance type from the dropdown.

    SageMaker geospatial supports two types of notebook instances: CPU and GPU. The supported CPU instance is called ml.geospatial.interactive. Any of the G5-family of GPU instances can be used with the Geospatial 1.0 image.

    Note

    If you receive a ResourceLimitExceeded error when attempting to start a GPU based instance, you need to request a quota increase. To get started on a Service Quotas quota increase request, see Requesting a quota increase in the Service Quotas User Guide

  9. Choose Select.

  10. Choose Create notebook.

After creating a notebook, to learn more about SageMaker geospatial, try the SageMaker geospatial tutorial. It shows you how to process Sentinel-2 image data and perform land segmentation on it using the earth observation jobs API.