The Dawn of a New Era in Natural Language Understanding and Generation

When I look back to 1984 when I received my 32k home computer, at the time I didn't think I was at the dawn of personal computing and an explosion of creativity. The more I delve into the 175Billion parameter (in AI size matters) Transformer GPT-3 Language Model built from vast swathes of the Internet,... Continue Reading →

Uncertainty and risk: using unsupervised machine learning to show insights

Using over 700 public oil & gas license relinquishment reports from over 30 companies (2008-2017) in the UKCS, I built a language model of similarity between terms after careful semantic processing. The chart above shows vector cosine similarity between various play elements and the 'risk' word vector on the x -axis, and 'failure' (proxy 'actual'... Continue Reading →

3D lithological mapping of borehole descriptions using word embeddings

Interesting paper published in Computers and Geosciences. “3D lithological mapping of borehole descriptions using word embeddings” Fuentes et al (2020). Applied to groundwater studies in New South Wales, Australia. Also an interesting paper published in the AGU. Dictionary‐Based Automated Information Extraction From Geological Documents Using a Deep Learning Algorithm - Qiu - 2020 -... Continue Reading →

Digitally Transforming Geoscience Opportunity Generation Workflows with Natural Language Processing (NLP)

OpportunityFinder Milestone: the geoscience algorithm is now trained on over 25,000 terms & phrases for identifying clues for source rock, maturation, migration, reservoir, hydrocarbon occurrence, trap and seal in unstructured text (reports, presentations and papers). This is used by its one-of-a-kind pattern based discovery method to assist the Geoscientist and surface possible leads, analogues, opportunities... Continue Reading →

Analysing over 2 Trillion Possible Permutations from Unstructured Text in Under 1 Hour on an i5 laptop.

I recently ran 1 million sentences from public domain geoscience literature articles & reports through the OpportunityFinder® algorithm. The aim was detecting hydrocarbon exploration play elements and interesting combinations using Natural Language Processing (NLP) and Machine Learning. This involved analysing over 2 Trillion possible permutations hidden within the text. Through iterative design, I arrived at... Continue Reading →

Presented at Petrobras SIMGEO

Delighted to be invited by Petrobras this week to give a presentation of OpportunityFinder at the SIMGEO 'Digital Transformation in the Geosciences' symposium. OpportunityFinder(R) is a Python based algorithm which surfaces non-obvious exploration opportunities hidden in unstructured text (reports, documents) and can be adapted to other geosciences based work tasks.

Powered by

Up ↑