Best Practices For Using Machine Learning Keywords in Collection and Service Records in the Common Metadata Repository (CMR)

Overview

This best practices document describes how to use Machine Learning keywords in collection and service records in the Common Metadata Repository (CMR) to improve metadata and discoverability of machine learning data and models. 

Machine Learning Model keywords are a representation of predictive models that, when trained on a set of data containing certain features, enables a computer to identify similar features in other data. Machine Learning Training Data keywords are a representation of input data necessary for running a machine learning model.

Best Practices

Science keywords from the GCMD Keyword Management System (KMS) are important for the precise search and retrieval of data and should accurately represent the dataset being described. At a minimum, one science keyword hierarchy must be provided, and this hierarchy must go down to the 'Term' level of detail.

• The Earth Science keywords should be picked from the GCMD KMS.
  • The list of valid keywords can be found at https://gcmd.earthdata.nasa.gov/KeywordViewer/scheme/Earth Science
• The Machine Learning Training Data keywords should be picked from the GCMD KMS.
  • The list of valid keywords can be found at https://gcmd.earthdata.nasa.gov/KeywordViewer/scheme/Earth%20Science%20Services/676bb4aa-1452-4527-aa05-83233ad5d01d
• The Machine Learning Model keywords should be picked from the GCMD Keyword Management System.
  • The list of keywords can be found at https://gcmd.earthdata.nasa.gov/KeywordViewer/scheme/Earth%20Science%20Services/fe4392b0-13a9-43ff-bacc-f44a65aed4fa

Machine Learning Training Data (Model Training Data):

1. Describe your machine learning training data as a UMM Collections (UMM-C) compliant collection record in CMR. 
2. Add relevant Machine Learning Training Data keywords describing the input data necessary for running a machine learning model.  
3. Add relevant Earth Science keywords describing what is being measured as part of the training data set. 
4. Ingest your UMM-C record into the CMR.   
5. Add the 'machine.learning' CMR tag. (Note: Tag permission is granted through the provider via the INGEST_MANAGMENT_ACL. Users can add tags if they are granted the appropriate permission.)
1. To add a tag to a collection record, see the Search API Documentation.

Machine Learning Models (Model):

1. Describe your machine learning model as a UMM Services (UMM-S) compliant record in CMR. 
2. Add relevant Machine Learning Model keywords describing the type of model that was used to train the data. 
3. Ingest your UMM-S record into the CMR.   
4. Add a collection association to relevant Machine Learning Training Data collections in the CMR. (Note: Collection association is granted through the provider via the INGEST_MANAGMENT_ACL. Users can add tags if they are granted the appropriate permission.)
   1. To associate a service with one or more collections using the Metadata Management Tool (MMT), see the MMT User Guide. 
   2. To associate a service with one or more collections using the CMR API, see the CMR Search API Documentation.