Instructions for AI to assist with collecting metadata
The text below assists with obtaining metadata using AI (Copilot, Gemini etc.) from a research report, scientific article or other source. Metadata can then be checked and manually entered by the user, or an xml file can be created to upload all the data at once (which should then be carefully checked).
Can you please help me extract the following metadata from the attached publication:
- Dataset title (a maximum of 100 characters)
- Author details
- Contact person details
- Dataset description (max 500 words, please write in the past tense)
- Organisation
- Private/Public
- Recommended citation (Please format like this for a report: ODINDO A, BAME I, MUSAZURA W, HUGHES J and BUCKLEY C (2016) integrating agriculture in designing on-site, low-cost sanitation technologies in social housing schemes, WRC Report No. TT 700/16. Water Research Commission, Pretoria.
And like this for a journal article:
MCCAFFERTY JR, ELLENDER BR, WEYL OLF and BRITZ PJ (2012) REVIEW: the use of water resources for inland fisheries in South Africa. Water SA 38 (2)327-334. http://doi.org/10.4314/wsa.v38i2.18.) - Organization/Publisher
- Publication date
- Project number
- License e.g. CC 4.0
- Keywords (please use commas to separate)
- Geographic co-ordinates (a single point (e.g., catchment centroid), or
bounding box (recommended) in this format -22.1265, 16.4699, -34.8212, 32.8931)
- Where to store the data
14.1 Dataset topic category (choose only one from Agriculture, Floods, Streamflow, Biodiversity, Food security, Transboundary water, Citizen Science, Groundwater, Water quality, Dam level, Hydrological data & modelling, Water scarcity, Drought, Legislation, Water user associations, Economics, Marine water, Weather & climate data, Ecosystems, Mine water, Wetlands, Estuaries, Social, Other)
14.2 Dataset structure category choose from:
Structured (clearly labelled and in a standardised format)
Semi-structured (does not fully conform to the tabular format of structured data, but may contain tags or markers identifying properties to arrange it into an organisational framework)
Unstructured (data cannot be stored in relational databases and is often stored in its raw format, such as images)
14.3 Uploader estimation of extent to which data have been processed (choose from Raw, Still being processed, Refined, Access)
14.4 Is the data time series or static (choose from Time Series, Static, Both)
- Data reference dates
- Alternate identifier
- Vertical extent data (For terrestrial (surface) data in South Africa it could be metres above sea level (masl). For groundwater datasets, use e.g. metres below ground level (mbgl). Always specify the unit and reference point to ensure clarity and consistency in metadata.)
- Vertical minimum-maximum extent (Specify the vertical minimum and maximum extent. For national scale datasets for South Africa use 0 - 3451masl. If not reported, please estimate from the study region site).
Please then prepare an .xml file using the metadata acquired with the following format:
<?xml version="1.0" encoding="UTF-8"?>
<dataset>
<title>Feasibility study on irrigation for long-term acid mine water management in the Vaal Basin</title>
<authors-0-author_name>Michael</authors-0-author_name>
<authors-0-author_surname>van der Laan</authors-0-author_surname>
<authors-0-author_email>orders@wrc.org.za</authors-0-author_email>
<authors-0-author_organization>University of Pretoria</authors-0-author_organization>
<authors-0-author_department>Plant Production and Soil Science</authors-0-author_department>
<authors-0-contact_same_as_author>true</authors-0-contact_same_as_author>
<contact_person-0-contact_name>Michael van der Laan</contact_person-0-contact_name>
<contact_person-0-contact_email>orders@wrc.org.za</contact_person-0-contact_email>
<contact_person-0-contact_orgnization>University of Pretoria</contact_person-0-contact_orgnization>
<contact_person-0-contact_department>Plant Production and Soil Science</contact_person-0-contact_department>
<notes>This dataset was generated as part of a feasibility study investigating irrigation as a long-term acid mine water management strategy in the Vaal Basin, South Africa.</notes>
<owner_org>WRC</owner_org>
<citation_title>VAN DER LAAN M, FEY MV, VAN DER BURGH G, DE JAGER PC, ANNANDALE JG and DU PLESSIS HM (2014) Feasibility study on the use of irrigation as part of a long-term acid mine water management strategy in the Vaal Basin. WRC Report No. 2233/1/14. Water Research Commission, Pretoria.</citation_title>
<did_author_or_contact_organization_collect_the_data>true</did_author_or_contact_organization_collect_the_data>
<data_collection_organization>University of Pretoria</data_collection_organization>
<dataset_language>English</dataset_language>
<publisher>Water Research Commission</publisher>
<publication_date>2014-12-01</publication_date>
<wrc_project_number>K5/2233//3</wrc_project_number>
<license>Open (Creative Commons)</license>
<dataset_license_url>https://creativecommons.org/licenses/by-sa/4.0/</dataset_license_url>
<keywords>acid mine drainage, mine water irrigation, Vaal Basin</keywords>
<spatial>-26.90, 26.50, -28.50, 29.50</spatial>
<wro_theme>inlandWaters</wro_theme>
<data_structure_category>structured</data_structure_category>
<uploader_estimation_of_extent_of_processing>refined</uploader_estimation_of_extent_of_processing>
<data_classification>both</data_classification>
<data_reference_date-0-data_reference_date_from>2012-01-01</data_reference_date-0-data_reference_date_from>
<data_reference_date-0-data_reference_date_to>2014-12-31</data_reference_date-0-data_reference_date_to>
<alternative_identifier>ISBN 978-1-4312-0607-0</alternative_identifier>
<vertical_extent_datum>masl</vertical_extent_datum>
<minimum_maximum_extent-0-minimum_vertical_extent>0</minimum_maximum_extent-0-minimum_vertical_extent>
<minimum_maximum_extent-0-maximum_vertical_extent>3451</minimum_maximum_extent-0-maximum_vertical_extent>
<agreement>true</agreement>
</dataset>