publiccode.yml

publiccodeYmlVersion: 0.5.0
name: swissgeol-boreholes-dataextraction
applicationSuite: swissgeol.ch
url: https://github.com/swisstopo/swissgeol-boreholes-dataextraction/
platforms:
  - web
developmentStatus: beta
softwareType: standalone/backend
organisation:
  uri: https://ld.admin.ch/office/IV.1.5a
  name: Bundesamt für Landestopografie (swisstopo)
description:
  en:
    shortDescription: >-
      Pipeline to extract structured data from borehole profiles in PDF files and
      return extracted coordinates, depths, and material descriptions as JSON.
    longDescription: >-
      Boreholes Data Extraction is a pipeline to extract structured data from
      borehole profiles in PDF files. Extracted properties (currently borehole name, groundwater data, elevation,
      coordinates, depths and associated material descriptions) are returned in
      JSON format, and (optionally) visualized as PNG images. Further, an API provides access to 
      the borehole data extraction pipeline, allowing to process PDF files, generate visualizations, 
      and retrieve structured geological data in JSON format.

      The goal of the project is to automate the extraction of structured data
      from borehole profiles as much as possible and to integrate it with the
      boreholes.swissgeol.ch application.
    features:
      - Extract borehole coordinates from PDF profiles
      - Extract depth intervals for lithological layers
      - Extract material descriptions as plain text
      - Export results as JSON (predictions.json) and optional PNG visualizations
      - Provide a layer description classification pipeline based on BERT

legal:
  license: AGPL-3.0-only
maintenance:
  type: community
  contacts:
    - name: Stijn Vermeeren
      email: stijn.vermeeren@swisstopo.ch
localisation:
  localisationReady: false
  availableLanguages:
    - en