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
Comparing patterns of potential source rocks in text by geological age to their contribution in actual producing oil and gas fields.
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 →
Mineral to Hydrocarbon Occurrence and HC Source Rock Association (From Text Frequency)
Figure 1 - Mineral Associations to HC Source Rock (x-axis) and HC Occurrence (y-axis) Natural Language Processing (NLP) and Machine Learning was applied to 16 million geoscience sentences using over 48,000 lexicon terms. Their frequency of association (in the same sentence) is shown in Fig 1. Some patterns confirm known associations, such as the association... Continue Reading →
Deriving Hydrocarbon to Metal / Mineral associations found in unstructured text for use as potential ore analogues and exploratory data analysis
Figure 1 - Association (Text) Frequency between chemical elements (by group) and hydrocarbon source rock (x-axis) and hydrocarbon occurrence (y-axis). Deriving Hydrocarbon to Metal / Mineral associations found in unstructured text for use as potential ore analogues and exploratory data analysis: Applying Machine Learning and Natural Language Processing (NLP) to 16 Million Geoscience Sentences. Hydrocarbon... Continue Reading →
Merycoidodon skull
Fascinated by this Merycoidodon (Oreodont) fossil skull. An extinct herbivore from the Oligocene (~25 Million Years Ago) with no known close living relatives today. Related to the camel but 'sheep-like', it would have likely resembled a pig in appearance, but with a longer body, at about 1.5 metres with short limbs and probably moved in herds... Continue Reading →
Deep Learning Geoscience Named Entity Recognition
We are using Deep Learning to leverage the unique 45,000 petroleum system related textual clues in OpportunityFinder®. Designed for automation, the clues combined with auto-annotation of millions of sentences allow a deep learning model to generalise (learn). This enables the detection of valid clues in geoscience text (reports, presentations, papers) not present in the original... Continue Reading →
OpportunityFinder® and Renewables Geothermal Projects
OpportunityFinder® is being tested within a renewables geothermal project in collaboration with the British Geological Survey. BGS are investigating mine water in underground abandoned coal mines as a low carbon sustainable heat source for housing and manufacturing, and have several other potential use cases for knowledge extraction from their data archives to meet the challenges... Continue Reading →
OpportunityFinder®
Announcing V2.0 released. Discover new oil & gas exploration ideas, leads, plays and opportunities in your unstructured text. OpportunityFinder® - first of its kind pattern based geoscience search. http://www.infosciencetechnologies.com
New peer reviewed research published on search in the enterprise
Research published this week on the effects of COVID-19 on search in the enterprise. People often use search engines to resolve some level of uncertainty. Patterns in enterprise search logs may therefore yield insights in extreme situations such as a pandemic and lockdowns. These data could be used by organisations to assess the effectiveness of... Continue Reading →
GEOCLASSIFIER® – OUTPUT
Example showing autoclassification output from GeoClassifier® from a selection of public domain geoscience documents. The proportion of topics are clustered in a Pearson dendrogram heatmap. Those above the mean are in red, below the mean in dark blue relative to the corpus/collection. Easy to see clusters of documents predominantly about certain topics and to spot... Continue Reading →