The conceptual model repurposes Blooms Taxonomy (Armstrong 2010). A work in progress - still evolving. Contribution - help organisations identify gaps in their exploitation strategies for the organisational 'exobrain' - large volumes of unstructured data and AI. Abstract currently submitted to EAGE. If accepted I'll post the full extended abstract here. The presentation will tie... Continue Reading →

Some new research published on geoscience text analytics. Research driven from China and Canada. Predominant focus on mining, using vectorspace and knowledge graphs on automatically extracted entities and concepts. Looking at associations to predict new deposits. Lawley et al (2023). Applications of Natural Language Processing to Geoscience Text Data and Prospectivity Modeling. Natural Resources Research.... Continue Reading →

Data Management and Artifical Intelligence. Final model from my presentation this week at the Society for Professional Data Managers using the Cynefin framework (Snowden) for aiding decision making in various situations applied to data management through semi fictitious examples. Key points: 1. Perspective: Being a data manager is so much more than just clicking a... Continue Reading →

Data Management and Artificial Intelligence. One of the models from my presentation at the Society for Professional Data Managers yesterday. Two sides of the same coin. Evolving nature of the role. Excellently put together, the online SPDM conference is still ongoing, great presentations and debate recommend to drop in and listen or join the discussion!... Continue Reading →

Language Models, Search, Vectors and Petroleum Systems: I’ve conducted some research on how well sentence transformers and other approaches are able to match a user query to sentences in order to answer questions and summarise. It’s a continuation from other posts I’ve made recently. A question was posed “Where are the potential hydrocarbon traps?”, with... Continue Reading →

Transformers over pre-trained Large Language Models (LLM) can be applied to facts expressed in natural language 'sentences' to answer certain queries. They can perform the selections, joins and projections required. An advantage of this approach is that 'the database' has no predefined schema and queries can be written as people prefer. Take these 3 sentences... Continue Reading →

Delighted to present at the Society for Professional Data Managers (SPDM) mid year event next week which is on the theme “Data Management in an AI World - Becoming Obsolete or Increasingly Vital?”. The abstract is titled “Unstructured Data Management and Artificial Intelligence: Two sides of the Same Coin?”. Abstract Data may be seen as... Continue Reading →

Selection of visualisations of the reference knowledge representations used by Infoscience Technologies GeoClassifier(R) to automatically classify documents. #knowledgegraph #taxonomy #ontology More: http://www.infosciencetechnologies.com

Petronas and Infoscience Technologies at the Petronas Digital Days Conference in Kuala Lumpur May 29th-May 30th 2023. Petronas demonstrated their work using Infoscience's Natural Language Processing (NLP) algorithms on their company documentation to improve search and data discovery, reduce risk and identify new business opportunities using insights. #digitalinnovation #machinelearning #artificialintelligence #taxonomy #unstructureddata #naturallanguageprocessing #datamanagement #informationmanagement... Continue Reading →

I've been experimenting to see how well Generative Artificial Intelligence (AI) can do 'joins' across data records for data management and search queries. Take this example. A prompt providing Gamma Ray well log data by Depth and API value, followed by Geological Formation well pick intervals. I then asked the question "What formations have average... Continue Reading →