Slides available for download here: Artificial Intelligence
The Benefits and Dangers of using Artificial Intelligence in Petrophysics
Abstract: Artificial Intelligence, or AI, is a method of data analysis that learns from data, identifies patterns and makes predictions with minimal human intervention. Essentially AI solves problems by writing its own software. AI is bringing many benefits to petrophysical evaluation. Using case studies this presentation describes several successful applications. The future of AI has even more potential. However, if used carelessly there are potentially grave consequences.
In a North Sea Field, AI was used to discover the relationships between the electrical logs, core, litho-facies and permeability in multi-dimensional data space. As a consequence, all wells in the field were populated with these data to build a robust reservoir model.
AI doesn’t require prior knowledge of the petrophysical response equations and is self-calibrating. There are no parameters to pick or cross-plots to make. There is very little user intervention and AI avoids the problem of “rubbish in, rubbish out”, by ignoring noise and outliers. AI programs work with an unlimited number of electrical logs, core and gas chromatography data; and don’t ‘fall-over’ if some of those inputs are missing.
AI programs currently being developed include ones where their machine code evolves using similar rules used by life’s DNA code. These AI programs pose considerable dangers far beyond the oil industry. A ‘risk assessment’ is essential on all AI programs so that all hazards and risk factors, that could cause harm, are identified and mitigated.
Biography – Steve Cuddy
Steve Cuddy holds a doctorate in petrophysics from Aberdeen University. He also holds BSc (Hons.) in physics and a BSc in astrophysics and philosophy. He is currently a Principal Petrophysicist with Baker Hughes and has 45 years industry experience in formation evaluation and reservoir description. He has authored several SPE and SPWLA papers and carried out more than 200 reservoir studies.