5: Knowledge Representation in a Workstation for Reservoir Analysis
When analyzing complex reservoirs, interpretation professionals have long felt the need for an integration of all forms of data. The interpretation system described in this paper integrates applications from geophysics, petrophysics, geology, and reservoir engineering around a common database that contains both the data and the resulting interpretation model.
The database includes both large numeric files (e.g., to store measurements for seismic cubes or sections, well logs or maps) and declarative, symbolic descriptions of these files (e.g., the field or wells to which they belong or how they were derived from one another). The symbolic descriptions, called knowledge bases, are implemented in an object-oriented Knowledge Representation System that made possible the integrating of notions that come from several disciplines and that are in constant evolution. Object-oriented modeling was also used to develop and execute a fast graphics code and to support tight interactions between graphics and the knowledge bases.
A system was built to analyze surface seismic and log data in an interactive environment. The system uses Knowledge Representation techniques to represent data and model in knowledge bases. The results of single well log interpretation are first used to calibrate surface seismic data, and to define at the well locations the reservoir components to be reconstructed. Seismic horizons are identified, interpreted, and mapped from seismic data, and are then used to model the geometry of the reservoir units. Log data provide measurements of the reservoir properties to be mapped within the components. Finally, the components are stacked together and their properties are interpolated on a simulation grid.
Figures & Tables
“So far as the laws of mathematics refer to reality they are not certain; and so far as they are certain, they don’t refer to reality.” This quote from Albert Einstein explains the difficulties associated with a mathematical description of many subjective rules used by human experts in reaching a decision. This fact, combined with the multidisciplinary nature of oil exploration, has prevented wide spread use of expert systems in the oil industry. Alternative approaches, that can account for uncertainty and are better equipped for integrating data and rules from different disciplines, should be used to allow expert systems to become viable tools in our applications.
This book examines a diverse set of petroleum exploration problems that properly designed expert systems can help solve. Chapter 1 provides an extensive review of current state-of-the-art expert systems as pertains to oil industry problems. Emphasis is given to how uncertainty and inexactness of data and rules from different disciplines could be handled by expert systems. The chapter suggests that fuzzy logic, evidential reasoning, and neural networks will prove essential in the design of many expert systems that are capable of solving more practical exploration problems. The problem of automatic picking of stacking velocities, using a rule based system, is addressed in Chapter 2. The expert system automates the task of picking the extreme of the velocity spectrum. The system incorporates common sense rules to distinguish primary reflection related peaks in the spectrum from those related to multiples and noise.