Machine Learning Model Product

Data product name

DpdMerMachineLearningModel

Data product custodian

MER

Data model tag

9.0.2

Name of the Schema file

euc-test-mer-MachineLearningModel.xsd

Schema documentation tag

Documentation for data product element DpdMerMachineLearningModel:

MER machine learning model. This product is an input to the MER processing function. It contains a trained machine learning model used in one of the MER processing steps.

Data product elements

Header of type: sys:genericHeader

Data of type: mer:merDqcMachineLearningModel

QualityFlags of type: dqc:sqfPlaceHolder

Parameters of type: ppr:genericKeyValueParameters

Processing Element(s) creating/using the data product

Creators:

• None. This is an input product that is generated manually or using some dedicated scripts.

Consumers:

• This product is not used at the moment in the MER pipeline.

Processing function using the data product

MER

Detailed description of the data product

This product is an input to the MER Pipeline. It contains a machine learning model trained by the MER team and that will be used by one or several of the MER processing steps (e.g. deblending, morphology).

The main elements inside this product are:

• TileIndex (optional): The MER tile index to which the machine learning model should be associated.

• PatchId (optional): The sky patch id to which the machine learning model should be associated.

• ProcessingMode (optional): The MER pipeline processing mode (WIDE or DEEP) to which the machine learning model should be associated.

• Model: The machine learning model type (e.g. Deblending, Morphology, SpuriousSources).

• DataStorage: Element that links to a file containing the machine learning model data set.