schema.yml

subak_dc_schema_version: 2
entity_type: dataset

fields:
  - name: title
    description: Name of the dataset
    type: short text
    required: true
    example: Global Electricity Generation and Demand by Country
    
  - name: owner_org
    description: Name of the organisation that has produced/published the dataset
    type: short text
    required: true
    example: Ember Climate

  - name: overview
    description: One or two sentences describing the purpose of the dataset
    type: long text
    required: false
    example: A global dataset for electricity generation & demand across 217 countries from 2000 to 2020. 

  - name: description
    description: A Detailed description of the dataset, including data quality and processing techniques
    type: long text or README.md markdown file
    required: true
    example: README.md

  - name: primary_taxonomy_category
    description: The primary taxonomy that your would categorise the dataset under
    type: choice
    required: false
    choices:
    - Emission Reduction > Upstream Fossil Fuel > All
    - Emission Reduction > Electricity > All
    - Emission Reduction > Electricity > Fossil Fuel > All
    - Emission Reduction > Electricity > Fossil Fuel > Coal
    - Emission Reduction > Electricity > Fossil Fuel > Oil
    - Emission Reduction > Electricity > Fossil Fuel > Gas
    - Emission Reduction > Electricity > Renewables > All
    - Emission Reduction > Electricity > Renewables > Solar
    - Emission Reduction > Electricity > Renewables > Wind
    - Emission Reduction > Electricity > Renewables > Hydro electricity
    - Emission Reduction > Electricity > Nuclear
    - Emission Reduction > Electricity > Storage
    - Emission Reduction > Buildings > All
    - Emission Reduction > Buildings > Residential 
    - Emission Reduction > Buildings > Commercial
    - Emission Reduction > Transport > All
    - Emission Reduction > Transport > Land > All
    - Emission Reduction > Transport > Land > Light Road
    - Emission Reduction > Transport > Land > Heavy Road
    - Emission Reduction > Transport > Land > Rail
    - Emission Reduction > Transport > Sea
    - Emission Reduction > Transport > Air
    - Emission Reduction > Industry > Construction & Cement
    - Emission Reduction > Industry > Metallurgy
    - Emission Reduction > Industry > Chemical & Petrochemical
    - Emission Reduction > Industry > Other
    - Emission Reduction > Agriculture > All
    - Emission Reduction > Agriculture > Livestock & Manure
    - Emission Reduction > Agriculture > Rice
    - Emission Reduction > Agriculture > Soils
    - Emission Reduction > Land Use & Forestry > All
    - Emission Reduction > Land Use & Forestry > Burning
    - Emission Reduction > Land Use & Forestry > Landfill
    - Emission Reduction > Waste
    - Societal > Climate & Weather
    - Societal > Policy
    - Societal > Green finance
    - Societal > Education
    - Societal > Climate Impacts
    example: Emission Reduction > Electricity > Renewables > Solar

  - name: secondary_taxonomy_category
    description: The (optional) secondary taxonomy that your would categorise the dataset under
    type: choice
    required: false
    choices:
    - Emission Reduction > Upstream Fossil Fuel > All
    - Emission Reduction > Electricity > All
    - Emission Reduction > Electricity > Fossil Fuel > All
    - Emission Reduction > Electricity > Fossil Fuel > Coal
    - Emission Reduction > Electricity > Fossil Fuel > Oil
    - Emission Reduction > Electricity > Fossil Fuel > Gas
    - Emission Reduction > Electricity > Renewables > All
    - Emission Reduction > Electricity > Renewables > Solar
    - Emission Reduction > Electricity > Renewables > Wind
    - Emission Reduction > Electricity > Renewables > Hydro electricity
    - Emission Reduction > Electricity > Nuclear
    - Emission Reduction > Electricity > Storage
    - Emission Reduction > Buildings > All
    - Emission Reduction > Buildings > Residential 
    - Emission Reduction > Buildings > Commercial
    - Emission Reduction > Transport > All
    - Emission Reduction > Transport > Land > All
    - Emission Reduction > Transport > Land > Light Road
    - Emission Reduction > Transport > Land > Heavy Road
    - Emission Reduction > Transport > Land > Rail
    - Emission Reduction > Transport > Sea
    - Emission Reduction > Transport > Air
    - Emission Reduction > Industry > Construction & Cement
    - Emission Reduction > Industry > Metallurgy
    - Emission Reduction > Industry > Chemical & Petrochemical
    - Emission Reduction > Industry > Other
    - Emission Reduction > Agriculture > All
    - Emission Reduction > Agriculture > Livestock & Manure
    - Emission Reduction > Agriculture > Rice
    - Emission Reduction > Agriculture > Soils
    - Emission Reduction > Land Use & Forestry > All
    - Emission Reduction > Land Use & Forestry > Burning
    - Emission Reduction > Land Use & Forestry > Landfill
    - Emission Reduction > Waste
    - Societal > Climate & Weather
    - Societal > Policy
    - Societal > Green finance
    - Societal > Education
    - Societal > Climate Impacts
    example: Emission Reduction > Electricity > Storage

  - name: keywords
    description: Comma-separated list of keywords describing the dataset
    type: short text
    required: false
    example: electricity, power, energy generation, energy demand

  - name: temporal_start
    description: Earliest date covered by dataset
    type: date (YYYY-MM-DD)
    required: false
    example: 2000-01-01
    
  - name: temporal_end
    description: Latest date covered by dataset (Leave blank if dataset is updated to the present day)
    type: date (YYYY-MM-DD)
    required: false
    example: 2020-12-31

  - name: temporal_resolution
    description: Most granular time resolution of the dataset
    type: choice
    required: false
    choices:
    - year
    - quarter
    - month
    - week
    - day
    - hour
    - minute
    - second
    - sub-second
    example: year
  
  - name: update_frequency
    description: How often the dataset is updated?
    type: choice
    required: false
    choices:
    - hourly
    - daily
    - weekly
    - monthly
    - quarterly
    - annually
    - never
    example: annually

  - name: geo_region
    description: Broad geographic region that the dataset covers
    type: choice
    required: false
    choices:
    - world
    - africa
    - americas
    - antarctica
    - asia
    - europe
    - oceania
    example: europe
  
  - name: countries
    description: List of countries that the dataset covers
    type: multi-choice
    required: false
    choices:
    - Afghanistan
    - Åland Islands
    - Albania
    - Algeria
    - American Samoa
    - Andorra
    - Angola
    - Anguilla
    - Antarctica
    - Antigua and Barbuda
    - Argentina
    - Armenia
    - Aruba
    - Australia
    - Austria
    - Azerbaijan
    - Bahamas
    - Bahrain
    - Bangladesh
    - Barbados
    - Belarus
    - Belgium
    - Belize
    - Benin
    - Bermuda
    - Bhutan
    - Bolivia (Plurinational State of)
    - Bonaire, Sint Eustatius and Saba
    - Bosnia and Herzegovina
    - Botswana
    - Bouvet Island
    - Brazil
    - British Indian Ocean Territory
    - Brunei Darussalam
    - Bulgaria
    - Burkina Faso
    - Burundi
    - Cabo Verde
    - Cambodia
    - Cameroon
    - Canada
    - Cayman Islands
    - Central African Republic
    - Chad
    - Chile
    - China
    - Christmas Island
    - Cocos (Keeling) Islands
    - Colombia
    - Comoros
    - Congo
    - Congo, Democratic Republic of the
    - Cook Islands
    - Costa Rica
    - Côte d'Ivoire
    - Croatia
    - Cuba
    - Curaçao
    - Cyprus
    - Czechia
    - Denmark
    - Djibouti
    - Dominica
    - Dominican Republic
    - Ecuador
    - Egypt
    - El Salvador
    - Equatorial Guinea
    - Eritrea
    - Estonia
    - Eswatini
    - Ethiopia
    - Falkland Islands (Malvinas)
    - Faroe Islands
    - Fiji
    - Finland
    - France
    - French Guiana
    - French Polynesia
    - French Southern Territories
    - Gabon
    - Gambia
    - Georgia
    - Germany
    - Ghana
    - Gibraltar
    - Greece
    - Greenland
    - Grenada
    - Guadeloupe
    - Guam
    - Guatemala
    - Guernsey
    - Guinea
    - Guinea-Bissau
    - Guyana
    - Haiti
    - Heard Island and McDonald Islands
    - Holy See
    - Honduras
    - Hong Kong
    - Hungary
    - Iceland
    - India
    - Indonesia
    - Iran (Islamic Republic of)
    - Iraq
    - Ireland
    - Isle of Man
    - Israel
    - Italy
    - Jamaica
    - Japan
    - Jersey
    - Jordan
    - Kazakhstan
    - Kenya
    - Kiribati
    - Korea (Democratic People's Republic of)
    - Korea, Republic of
    - Kuwait
    - Kyrgyzstan
    - Lao People's Democratic Republic
    - Latvia
    - Lebanon
    - Lesotho
    - Liberia
    - Libya
    - Liechtenstein
    - Lithuania
    - Luxembourg
    - Macao
    - Madagascar
    - Malawi
    - Malaysia
    - Maldives
    - Mali
    - Malta
    - Marshall Islands
    - Martinique
    - Mauritania
    - Mauritius
    - Mayotte
    - Mexico
    - Micronesia (Federated States of)
    - Moldova, Republic of
    - Monaco
    - Mongolia
    - Montenegro
    - Montserrat
    - Morocco
    - Mozambique
    - Myanmar
    - Namibia
    - Nauru
    - Nepal
    - Netherlands
    - New Caledonia
    - New Zealand
    - Nicaragua
    - Niger
    - Nigeria
    - Niue
    - Norfolk Island
    - North Macedonia
    - Northern Mariana Islands
    - Norway
    - Oman
    - Pakistan
    - Palau
    - Palestine, State of
    - Panama
    - Papua New Guinea
    - Paraguay
    - Peru
    - Philippines
    - Pitcairn
    - Poland
    - Portugal
    - Puerto Rico
    - Qatar
    - Réunion
    - Romania
    - Russian Federation
    - Rwanda
    - Saint Barthélemy
    - Saint Helena, Ascension and Tristan da Cunha
    - Saint Kitts and Nevis
    - Saint Lucia
    - Saint Martin (French part)
    - Saint Pierre and Miquelon
    - Saint Vincent and the Grenadines
    - Samoa
    - San Marino
    - Sao Tome and Principe
    - Saudi Arabia
    - Senegal
    - Serbia
    - Seychelles
    - Sierra Leone
    - Singapore
    - Sint Maarten (Dutch part)
    - Slovakia
    - Slovenia
    - Solomon Islands
    - Somalia
    - South Africa
    - South Georgia and the South Sandwich Islands
    - South Sudan
    - Spain
    - Sri Lanka
    - Sudan
    - Suriname
    - Svalbard and Jan Mayen
    - Sweden
    - Switzerland
    - Syrian Arab Republic
    - Taiwan, Province of China
    - Tajikistan
    - Tanzania, United Republic of
    - Thailand
    - Timor-Leste
    - Togo
    - Tokelau
    - Tonga
    - Trinidad and Tobago
    - Tunisia
    - Turkey
    - Turkmenistan
    - Turks and Caicos Islands
    - Tuvalu
    - Uganda
    - Ukraine
    - United Arab Emirates
    - United Kingdom of Great Britain and Northern Ireland
    - United States of America
    - United States Minor Outlying Islands
    - Uruguay
    - Uzbekistan
    - Vanuatu
    - Venezuela (Bolivarian Republic of)
    - Viet Nam
    - Virgin Islands (British)
    - Virgin Islands (U.S.)
    - Wallis and Futuna
    - Western Sahara
    - Yemen
    - Zambia
    - Zimbabwe
    example:
    - United Kingdom of Great Britain and Northern Ireland
    - Spain
    - France

  - name: spatial_resolution
    description: the spatial resolution that most closely represents the samples or aggregations within the dataset
    type: choice
    required: false
    choices:
    - global
    - continent/region
    - country
    - state/county
    - city/town
    - street/postcode
    - building/residence
    - device/asset
    - 100km-grid
    - 10km-grid
    - 1km-grid
    - 100m-grid
    - 10m-grid
    - 1m-grid
    example: country

  - name: license
    description: Name of the license you wish to publish the data under
    type: choice
    required: false
    choices:
    - Open Data Commons Public Domain Dedication and License (PDDL)
    - Open Data Commons Open Database License (ODbL)
    - Open Data Commons Attribution License
    - Creative Commons CCZero
    - Creative Commons Attribution
    - Creative Commons Attribution Share-Alike
    - GNU Free Documentation License
    - Other (Open)
    - Other (Public Domain)
    - Other (Attribution)
    - UK Open Government Licence (OGL)
    - Creative Commons Non-Commercial (Any)
    - Other (Non-Commercial)
    - Other (Not Open)
    example: Creative Commons Attribution

  - name: source
    description: URL for any other online home for the dataset
    type: url
    required: false
    example: https://ember-climate.org/data/global-electricity/

  - name: author
    description: Contact point for the Data Catalogue
    type: short text
    required: false
    example: Dave Jones - dave@example.com

  - name: data_applications
    description: What has the data been used for
    type: repeating, multiple sub-fields
    required: false
    repeating_subfields:
    - name: category
      description: Category
      type: choice
      required: true      
      choices:
      - tutorials
      - tools and applications
      - publications
      example: publications

    - name: title
      description: Title
      type: short text
      required: true
      example: Global Electricity Review Report 2021

    - name: url
      description: URL
      type: url
      required: true
      example: https://ember-climate.org/project/global-electricity-review-2021/

    - name: author
      description: Author
      type: short text
      required: false
      example: Ember Climate

  - name: data_sources
    description: Data sources
    type: long text or SOURCES.md markdown file
    required: false
    example: SOURCES.md

  - name: resources
    description: Fields describing the data files that make up this dataset
    type: repeating, multiple sub-fields
    required: true
    repeating_subfields:
    - name: url
      description: URL to online resource or or name of local file to be uploaded
      type: url
      required: true
      example: https://subak.org/my-dataset.csv

    - name: name
      description: Name for the resource
      type: short text
      required: false
      example: Core Dataset

    - name: description
      description: Description of the file
      type: short text
      required: false
      example: Main data values for dataset

    - name: format
      description: File format
      type: short text
      required: false
      example: CSV

    - name: file_size
      description: File size (in bytes)
      type: number
      required: false
      example: 102400

    - name: data_fields
      description: Rich information describing all the data fields (if tabular)
      type: repeating, multiple sub-fields
      required: false
      repeating_subfields:
      - name: name
        description: Field name
        type: short text
        required: true
        example: Energy consumption

      - name: type
        description: Field type
        type: choice
        required: false
        choices:
        - numeric
        - text
        - date/time
        example: numeric

      - name: description
        description: Field description
        type: short text
        required: false
        example: The household energy consumption for the period

      - name: units
        description: Field units
        type: short text
        required: false
        example: kWh