Over 12,000 wells have been drilled in the UKCS. These have generated a lot of information, of great value to new and current explorers alike.
But most of this information is stored in an unstructured way, and mostly has been prepared by scanning paper documents.
Scanned images are easy for humans to read, but are inaccessible to modern computer analysis techniques.
Our project shows how we can make scanned information accessible to text analytics, and then applies those analytics to identify clusters of similar content within a document store - so you can finally find all those geochem reports you were looking for...