Class: Dataset

name: Dataset
description: Abstract base class for all dataset types. Contains fields common to
  both field/observational and model simulation datasets. Generally following guidelines
  & best practices as outlined in [science-on-schema.org](https://github.com/ESIPFed/science-on-schema.org/blob/main/guides/Dataset.md)
from_schema: OAEDataManagementProtocol
exact_mappings:
- schema:Dataset
- dcat:Dataset
slots:
- name
- description
- project_id
- experiment_id
slot_usage:
  name:
    name: name
    description: 'A brief descriptive sentence that summarizes the content of a dataset.
      Here is one example:

      "Dissolved inorganic carbon, total alkalinity, pH, temperature, salinity and
      other variables collected from profile and discrete sample observations using
      CTD, Niskin bottle, and other instruments from R/V Wecoma in the U.S. West Coast
      California Current System during the 2011 West Coast Ocean Acidification Cruise
      (WCOA2011) from 2011-08-12 to 2011-08-30"'
    title: Dataset Title
    range: string
    required: true
  description:
    name: description
    description: The abstract of a dataset is a brief summary that provides an overview
      of the dataset's content, purpose, and scope. It is used to provide context
      and background information to users who are interested in using the dataset.
      An abstract may include information such as the dataset's source, how the data
      was collected or generated, the variables or attributes included in the dataset,
      and any limitations or restrictions on the use of the data. It may also include
      information on how the data can be accessed or used.
    range: string
    required: true
  project_id:
    name: project_id
    required: true
  experiment_id:
    name: experiment_id
    required: true
attributes:
  dataset_type:
    name: dataset_type
    description: Selected controlled vocabularies for data types relevant to mCDR
      have been referenced from NASA's SeaBASS metadata system and are provided below,
      for additional data types of optical characteristics see the [SeaBASS controlled
      definitions list](https://seabass.gsfc.nasa.gov/wiki/metadataheaders#data_type).
      Additional data types have been included to meet the needs of mCDR field projects.
    title: Dataset Type
    from_schema: Dataset
    rank: 1000
    domain_of:
    - Dataset
    range: DatasetType
    required: true
  dataset_type_custom:
    name: dataset_type_custom
    description: Custom "data type" when an appropriate value is not found in the
      controlled vocabulary list for mCDR Data Type and the corresponding `data_type`
      field is set to "other".
    title: Dataset Type (Custom)
    from_schema: Dataset
    rank: 1000
    domain_of:
    - Dataset
    range: string
  data_submitter:
    name: data_submitter
    title: Data Submitter
    from_schema: Dataset
    rank: 1000
    domain_of:
    - Dataset
    range: Person
    required: true
  author_list_for_citation:
    name: author_list_for_citation
    description: Author list in the format of Lastname1, Firstname1 Middlename1; Lastname2,
      Firstname2 Middlename2; ...
    title: Author List (for citation)
    from_schema: Dataset
    rank: 1000
    domain_of:
    - Dataset
    range: string
  license:
    name: license
    description: Link a Dataset to its license to document legal constraints by adding
      a schema:license property. The guide recommends providing a URL that unambiguously
      identifies a specific version of the license used, but for many licenses it
      is hard to determine what that URL should be. Thus, we recommend that the license
      URL be drawn from the [SPDX license list](https://spdx.org/licenses/), which
      provides a curated list of licenses and their properties that is well maintained.
      For each SPDX entry, SPDX provides a canonical URL for the license (e.g., http://spdx.org/licenses/CC0-1.0),
      a unique licenseId (e.g., CC0-1.0), and other metadata about the license.
    title: License
    from_schema: Dataset
    rank: 1000
    slot_uri: schema:license
    domain_of:
    - Dataset
    range: uri
  fair_use_data_request:
    name: fair_use_data_request
    description: A statement from the data producer regarding how this dataset should
      be used.
    title: Fair Use Data Request
    from_schema: Dataset
    rank: 1000
    domain_of:
    - Dataset
    range: string
  filenames:
    name: filenames
    title: Filenames
    from_schema: Dataset
    rank: 1000
    domain_of:
    - Dataset
    range: string
    required: true
    multivalued: true
    minimum_cardinality: 1

name: Dataset
description: Abstract base class for all dataset types. Contains fields common to
  both field/observational and model simulation datasets. Generally following guidelines
  & best practices as outlined in [science-on-schema.org](https://github.com/ESIPFed/science-on-schema.org/blob/main/guides/Dataset.md)
from_schema: OAEDataManagementProtocol
exact_mappings:
- schema:Dataset
- dcat:Dataset
slot_usage:
  name:
    name: name
    description: 'A brief descriptive sentence that summarizes the content of a dataset.
      Here is one example:

      "Dissolved inorganic carbon, total alkalinity, pH, temperature, salinity and
      other variables collected from profile and discrete sample observations using
      CTD, Niskin bottle, and other instruments from R/V Wecoma in the U.S. West Coast
      California Current System during the 2011 West Coast Ocean Acidification Cruise
      (WCOA2011) from 2011-08-12 to 2011-08-30"'
    title: Dataset Title
    range: string
    required: true
  description:
    name: description
    description: The abstract of a dataset is a brief summary that provides an overview
      of the dataset's content, purpose, and scope. It is used to provide context
      and background information to users who are interested in using the dataset.
      An abstract may include information such as the dataset's source, how the data
      was collected or generated, the variables or attributes included in the dataset,
      and any limitations or restrictions on the use of the data. It may also include
      information on how the data can be accessed or used.
    range: string
    required: true
  project_id:
    name: project_id
    required: true
  experiment_id:
    name: experiment_id
    required: true
attributes:
  dataset_type:
    name: dataset_type
    description: Selected controlled vocabularies for data types relevant to mCDR
      have been referenced from NASA's SeaBASS metadata system and are provided below,
      for additional data types of optical characteristics see the [SeaBASS controlled
      definitions list](https://seabass.gsfc.nasa.gov/wiki/metadataheaders#data_type).
      Additional data types have been included to meet the needs of mCDR field projects.
    title: Dataset Type
    from_schema: Dataset
    rank: 1000
    alias: dataset_type
    owner: Dataset
    domain_of:
    - Dataset
    range: DatasetType
    required: true
  dataset_type_custom:
    name: dataset_type_custom
    description: Custom "data type" when an appropriate value is not found in the
      controlled vocabulary list for mCDR Data Type and the corresponding `data_type`
      field is set to "other".
    title: Dataset Type (Custom)
    from_schema: Dataset
    rank: 1000
    alias: dataset_type_custom
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  data_submitter:
    name: data_submitter
    title: Data Submitter
    from_schema: Dataset
    rank: 1000
    alias: data_submitter
    owner: Dataset
    domain_of:
    - Dataset
    range: Person
    required: true
  author_list_for_citation:
    name: author_list_for_citation
    description: Author list in the format of Lastname1, Firstname1 Middlename1; Lastname2,
      Firstname2 Middlename2; ...
    title: Author List (for citation)
    from_schema: Dataset
    rank: 1000
    alias: author_list_for_citation
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  license:
    name: license
    description: Link a Dataset to its license to document legal constraints by adding
      a schema:license property. The guide recommends providing a URL that unambiguously
      identifies a specific version of the license used, but for many licenses it
      is hard to determine what that URL should be. Thus, we recommend that the license
      URL be drawn from the [SPDX license list](https://spdx.org/licenses/), which
      provides a curated list of licenses and their properties that is well maintained.
      For each SPDX entry, SPDX provides a canonical URL for the license (e.g., http://spdx.org/licenses/CC0-1.0),
      a unique licenseId (e.g., CC0-1.0), and other metadata about the license.
    title: License
    from_schema: Dataset
    rank: 1000
    slot_uri: schema:license
    alias: license
    owner: Dataset
    domain_of:
    - Dataset
    range: uri
  fair_use_data_request:
    name: fair_use_data_request
    description: A statement from the data producer regarding how this dataset should
      be used.
    title: Fair Use Data Request
    from_schema: Dataset
    rank: 1000
    alias: fair_use_data_request
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  filenames:
    name: filenames
    title: Filenames
    from_schema: Dataset
    rank: 1000
    alias: filenames
    owner: Dataset
    domain_of:
    - Dataset
    range: string
    required: true
    multivalued: true
    minimum_cardinality: 1
  name:
    name: name
    description: 'A brief descriptive sentence that summarizes the content of a dataset.
      Here is one example:

      "Dissolved inorganic carbon, total alkalinity, pH, temperature, salinity and
      other variables collected from profile and discrete sample observations using
      CTD, Niskin bottle, and other instruments from R/V Wecoma in the U.S. West Coast
      California Current System during the 2011 West Coast Ocean Acidification Cruise
      (WCOA2011) from 2011-08-12 to 2011-08-30"'
    title: Dataset Title
    from_schema: OAEDataManagementProtocol
    rank: 1000
    slot_uri: schema:name
    alias: name
    owner: Dataset
    domain_of:
    - Organization
    - NamedLink
    - ExternalProject
    - MonetaryGrant
    - Experiment
    - Person
    - Dataset
    - Platform
    - ModelComponent
    range: string
    required: true
  description:
    name: description
    description: The abstract of a dataset is a brief summary that provides an overview
      of the dataset's content, purpose, and scope. It is used to provide context
      and background information to users who are interested in using the dataset.
      An abstract may include information such as the dataset's source, how the data
      was collected or generated, the variables or attributes included in the dataset,
      and any limitations or restrictions on the use of the data. It may also include
      information on how the data can be accessed or used.
    title: Description
    from_schema: OAEDataManagementProtocol
    rank: 1000
    slot_uri: schema:description
    alias: description
    owner: Dataset
    domain_of:
    - Project
    - ExternalProject
    - Experiment
    - VocabularyItemReference
    - Dataset
    - ModelComponent
    range: string
    required: true
  project_id:
    name: project_id
    description: 'The project to which the submitted data belong. A unique project
      identifier that can be used to link project data across data submissions, and
      link baseline data to intervention data, for example.

      If no Project ID has been assigned, one may be generated by combining: lead
      organizer surname and first initial or company, a unique date, and location.

      Any method that creates a unique ID that will link all project data is acceptable.'
    title: Project ID
    from_schema: OAEDataManagementProtocol
    rank: 1000
    alias: project_id
    owner: Dataset
    domain_of:
    - Project
    - Experiment
    - Dataset
    range: string
    required: true
  experiment_id:
    name: experiment_id
    description: 'The experiment to which the data belong. Any naming convention that
      produces a unique ID is usable. The recommended naming convention is:

      Project ID + Experiment type + Optional numerical indicator to differentiate
      between various experiments of the same type for a project. A two digit consecutive
      number beginning with 01'
    title: Experiment ID
    from_schema: OAEDataManagementProtocol
    rank: 1000
    alias: experiment_id
    owner: Dataset
    domain_of:
    - Experiment
    - Dataset
    range: string
    required: true