The Application of Genetic Algorithms in Structural Seismic Image Interpretation

In this paper, we examine the applicability and repeatability of a genetic algorithm to automatically correlate horizons across faults in seismic data images. This problem arises from geological sciences where it is a subtask of the structural interpretation of seismic images. Because of the small amount of local information contained in those types of images, we developed a geological model in order to reduce interpretation uncertainties. The key problem is an optimisation task which cannot be solved exhaustively since it would cause exponential computational cost. Among stochastic methods, a genetic algorithm has been chosen to solve the application problem. Repeated application of the algorithm to four different faults delivered an acceptable solution in 94-100% of the experiments. The global optimum was equal to the geologically best solution in three of the four cases. 1 Geological Background Seismic data are acquired using the seismic reflection method which explores the subsurface by bouncing sound waves off the interfaces between rock layers with differing physical properties. After several pre-processing steps, a rough estimate of the underground structure can be obtained. By analysing the recorded and processed signals, hypotheses about the underground structure can be developed which should merge into a consistent subsurface model. All decisions in hydrocarbon exploration and production are underpinned by such models obtained by structural interpretation. Since drilling wells is very costly, as much information as possible should be derived from the seismic data to form an opinion about the probability of encountering petroleum in the structures [1]. Structural interpretation may be thought of as consisting of the following tasks: Localisation and interpretation of faults, tracking of uninterrupted horizon segments and correlating these segments across faults. Reflectors in seismic images usually correspond with horizons indicating boundaries between rocks of markedly different lithology. Faults are discrete fractures across which there is measurable displacement of rock layering. On seismic sections, faults are usually identified where reflectors can be seen to be displaced vertically. The amount of vertical displacement associated with a fault at any location is termed the throw of the fault. 2 Automated Structural Seismic Interpretation Modern commercial interpretation software packages offer assistance for the interpretation of horizons and fault surfaces. The most commonly employed tech-