Skip to main content
Back to overview

Detailed Information

Software name

swissgeol-boreholes-dataextraction

Application suite

swissgeol.ch

Short description

Pipeline to extract structured data from borehole profiles in PDF files and return extracted coordinates, depths, and material descriptions as JSON.

Long description

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

Development status

beta

Software type

standalone/backend

Platforms

web

License

AGPL-3.0-only

Maintenance

Maintenance type:
community
Contacts:

Localisation

Localisation ready:
No
Available languages:
en

Publiccode.yml Version

0.5.0