Text Analytics: Sentiment and Geological Seals

Topseal performance is critical for geological disposal sites, whether that is carbon capture & storage or radioactive storage, as well as natural hydrogen or oil & gas exploration. I’ve used patterns in text only using machine automated techniques, to visualise Lithostratigraphic Formations by their association to clues for ‘seal’ (y-axis), by the overall sentiment of the geological formation (x-axis). All these data are driven inductively by public UK North Sea Transition Authority License Relinquishment reports generating 22,000 data points.

The aim is to use data driven techniques from historical knowledge and past projects to stimulate ideation and curiosity, ‘show me something I don’t already know’. Where a trend or pattern does not fit our given expectations (biases) and models, which may present an area for further research.

Every dataset (particularly text based ones) can be biased in some way, which always needs to be taken in account. That said, it has been proven that any large body of geoscience text, has the affordance to contain significant new knowledge and insights, that cannot be discerned from any single report.

#subsurface #naturallanguageprocessing #ccus #oilandgas #geosciences #geology #datadiscovery #energytransition #decarbonisation #analytics #bigdata #digital #knowledgemanagement #digitaltransformation