1887

Abstract

Summary

Over the years numerous geophysical datasets have been released for public usage. However, with no central storage location or consistent description strategy, finding suitable openly available datasets still poses a large challenge to the geophysics community. Building on the work of the Open Subsurface Data Universe on defining schema for describing geoscientific datasets and a list of openly available datasets compiled by the Society of Exploration Geophysicists, GeoGraphI is an interactive graph database providing a single access point with the necessary structured information to search for suitable datasets. Currently populated with over 117 data subsets ranging from passive seismic to migrated volumes, and from core images to interpreted horizons, GeoGraphI can be queried either by key information matching, such as “Return a field seismic dataset acquired over a salt body" or by computing similarity scores, such as “Return similar field datasets to the SEAM dataset". Being a graph database, GeoGraphI can naturally handle a large number of relationships between different data features as well as being able to easily adapt for future growth, either through further population of the database or by modification of the underlying schema.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202113197
2021-10-18
2024-04-24
Loading full text...

Full text loading...

References

  1. Birnie, C.E., Sampson, J., Sjaastad, E., Johansen, B., Obrestad, L.E., Larsen, R. and Khamassi, A.
    [2019] Improving the quality and efficiency of operational planning and risk management with ml and nlp. In: SPE Offshore Europe Conference and ExhibitionSociety of Petroleum Engineers.
    [Google Scholar]
  2. Karim, S., Lucañas, P., Sazali, A.N., Hernandez, N.M. and Baillard, F.
    [2020] A case study of fully automated machine learning petrophysical interpretation using unstructured data. In: EAGE/AAPG Digital Subsurface for Asia Pacific Conference, 2020. European Association of Geoscientists & Engineers, 1-4.
    [Google Scholar]
  3. Silva, R.M., Baroni, L., Ferreira, R.S., Civitarese, D., Szwarcman, D. and Brazil, E.V.
    [2019] Netherlands dataset: A new public dataset for machine learning in seismic interpretation. arXiv preprint arXiv:1904.00770.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202113197
Loading
/content/papers/10.3997/2214-4609.202113197
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error