Delighted to guest author an article on Natural Language Processing (NLP) in the Geosciences for Halliburton’s September Issue of Subsurface Insights. This month's issue is a minerals special. To access the article you can sign up free to Halliburton's magazine: https://geoweb.neftex.com/account/accessrequest Infoscience Technologies website is: http://www.infosciencetechnologies.com

When deploying a search engine in an organisation, it can be useful to think deeply about the underlying assumptions being made. These can help inform strategies. Arguably, some organisations may deploy reductionist technology focused strategies without perhaps thinking about all the assumptions they are making. CLEVERLEY, P.H. and BURNETT, S. 2019. Enterprise search and discovery... Continue Reading →

As well as detecting Geo-resources in unstructured text reports, papers and logs, OpportunityFinder can detect and disambiguate all kinds of geological concepts. High level lithology groupings in the Williston Basin are shown above in the Beeswarm chart. contact@infosciencetechnologies.com

Sentiment analysis of the last ten years of Guardian news articles mentioning geoscience. Geoscience is often mentioned in context to natural geohazards. However, there might be a trend towards increasing negative sentiment over time that may warrant further exploration. #geosciences #naturallanguageprocessing #oilandgas #mining #hydrogeology #geohazards

Topics mentioned with articles containing the word ‘geoscience’, past 10 years from The Guardian newspaper. Words are clustered automatically by their similarity (cosine) shown by the colour groupings. #geosciences #informationscience

The Python OpportunityFinder® algorithm from Infoscience Technologies can now automatically detect fossil names and their associated Lithostratigraphic Units and Geological Ages without a prior list of names. This can be useful because it is not always possible to predefine all the names and variations you are likely to come across in text. Furthermore, the way... Continue Reading →

Text mining algorithms were used to discover hidden geo-resource (metals, elements, minerals) associations in reports, maps, sketches and logs from the archives of the Geological Survey of Queensland in Australia. The Geological Survey of Queensland have made a number of excellent improvements recently increasing the accessibility of these data. A subset of report packages over... Continue Reading →

In April 2021 I worked on the world’s first large scale text analytics project to detect natural hydrogen. Working with a natural resources exploration company, this was to detect both explicit and implicit evidence for natural hydrogen in legacy oil & gas documentation. This contributed to the development of a new hydrogen play. It was... Continue Reading →

The OpportunityFinder® algorithm has now exceeded 50,000 terms in its lexicon for detecting petroleum systems automatically in text. This is combined with hundreds of thousands of labelled data for machine learning. These can support laser like tasks, improve search & discovery, insights, knowledge mining and also support the tuning of very large language models. http://www.infosciencetechnologies.com

Some research I conducted recently comparing the counts of potential oil and gas source rock "mentions" by geological age in unstructured text, to some (rather old) actual data published in the literature on the age of hydrocarbons generated from source rocks in producing oil & gas fields. Over 48,000 terms from a lexicon were applied to... Continue Reading →