https://infosciencetechnologies.com/2020/11/18/automatically-read-massive-volumes-of-text-like-a-geoscientist/

Lyme Regis on the 'Jurassic' South Coast of England is well known for its Ammonite graveyards, Ichthyosaurs and dark organic rich mud facies which is an oil source rock. The top of the cliffs contain Cretaceous beds and where land slips have brought these down to the beach occasionally you can find Echinoids (sea urchins)... Continue Reading →

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 →

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 →

Delighted to be presenting research findings at the British Computer Society Search Solutions 2020. Showing how COVID-19 may have affected usage of search engines in the enterprise. British Computer Society (BCS) Search Solutions November 25th 2020. Agenda here: https://irsg.bcs.org/SearchSolutions/2020/sse2020.php

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. https://www.sciencedirect.com/science/article/pii/S0098300419306533 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 →

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 →

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. http://www.infosciencetechnologies.com

I attended the 3 hour virtual summit on the Future of Geoscience hosted by the Geological Society of London today (10th June 2020). Over 1,000 people attended from as far afield as Indonesia, Pakistan, Canada and Milton Keynes! It was excellently led by Tom Backhouse and joined by a range of people representing different areas... Continue Reading →

Along with some colleagues I'm writing up a paper over the summer looking at the impact COVID-19 has had on Enterprise Search and Scholarly Search behaviour, with so many people working remotely. There are some fascinating patterns in the search engine usage logs. One pattern in particular was unexpected and significant. This could have theoretical... Continue Reading →