Utilization of Time-Lapse Seismic Data to Semi Quantify Residual Oil Saturation by Karhunen-Loeve Transform and Neural Artificial Network during CSS

Abstract

Due to the nature of Cyclic steam stimulation (CSS), a steam chamber generated by CSS is not as consistent and detectable as SAGD's (steam assisted gravity drainage) one, which makes it challenging to predict the residual oil distribution and steam-unswept zones. Time-lapse seismic are a valuable and important method to monitor steam injection and soaking. During CSS process, rock-fluid densities and velocities are changed significantly during steam injection and oil production. These changes make time-lapse seismic monitoring feasible. The previous approaches were mainly about fluid contact determination, steam chamber supervision and field history matching. In this study, a new method using time-lapse seismic attribute differences is developed to semi quantify residual oil saturation and determine steam-unswept zones during thermal recovery. Twenty seismic attributes derived from time-lapse seismic data, which can sensitively reflect oil saturation changing, are selected as basic seismic attributes to quantify fluid saturation changes. The relationship between fluid properties and seismic attributes is complex and ambiguous. Only one seismic attribute difference between base data and monitored data is insufficient to reflect reservoir properties changes during thermal recovery process. In order to improve the accuracy of prediction, combinations of multiple seismic attributes differences are used to reflect rock-fluid properties changes such as oil saturation changes. The Karhunen-Loeve Transform is applied to squeeze twenty attributes into four new attributes by eliminating attributes correlation. Based on generated seismic attributes, the artificial neural network is implemented to illustrate the oil saturations changes, which is also constrained by the measured fluid reservoir data. Four attribute differences are tested to demonstrate the oil saturation changes. The best result only can partially match field production data. However, the residual oil saturation distribution generated by the proposed method can match the majority features of the field production data. This approach provides a reliable and valuable way to help operators monitor a CSS process and design infill well drilling.

A Critical Review of Reservoir Simulation Applications in Key Thermal Recovery Processes: Lessons, Opportunities, and Challenges

“…Its simulation challenges largely inherit from the previous CSS process such as uncertainties of its depletion area. Before simulating a steamflooding process, it is crucial to achieve good history matching on not only production but also the geometry and connection of steam chambers, which can be accessed by 4D seismic interpretations . As new additives have been proposed to enhance performance of steamflooding, rigorously modeling formation of foam or gel is a challenging task for most thermal simulators.…”