Hybrid AI Models for the Characterization of Oil and Gas Reservoirs

Oil and Gas remain the most exploited source of
energy in the world today and have been predicted
that they will continue to be available for
exploitation in many decades to come. Hence, there is
the need to develop accurate and robust predictive
models for their effective and efficient exploration,
exploitation and management to ensure consistent
availability. Various Artificial Intelligence
techniques have been used but with dire needs for
improvement. Recently, hybrid schemes have been
reported to offer better performance and reliability.
The capabilities of these schemes have not been well
utilized in Oil and Gas. This book explains how these
schemes have been utilized in the prediction of
porosity and permeability, two important indicators
of oil and gas reserves, based on the hybridization
of Type-2 Fuzzy Logic, Support Vector Machines and
Functional Networks, using real-world well logs. The
results are very promising. This book will be of
great benefit to researchers and practitioners in the
application of AI techniques in oil and gas as well
as in Data Mining and Machine Learning.

Autorentext

Fatai Anifowose (MSc) is a Research Scientist at the Centre forPetroleum and Minerals, King Fahd University of Petroleum andMinerals, Saudi Arabia. With a BTech in Computer Science, he hasvast experience in Software Development. He also has interest inthe application of Artificial Intelligence in thecharacterization of Oil and Gas Reservoirs.

Klappentext

Oil and Gas remain the most exploited source ofenergy in the world today and have been predictedthat they will continue to be available forexploitation in many decades to come. Hence, there isthe need to develop accurate and robust predictivemodels for their effective and efficient exploration,exploitation and management to ensure consistentavailability. Various Artificial Intelligencetechniques have been used but with dire needs forimprovement. Recently, hybrid schemes have beenreported to offer better performance and reliability.The capabilities of these schemes have not been wellutilized in Oil and Gas. This book explains how theseschemes have been utilized in the prediction ofporosity and permeability, two important indicatorsof oil and gas reserves, based on the hybridizationof Type-2 Fuzzy Logic, Support Vector Machines andFunctional Networks, using real-world well logs. Theresults are very promising. This book will be ofgreat benefit to researchers and practitioners in theapplication of AI techniques in oil and gas as wellas in Data Mining and Machine Learning.