Karst systems heterogeneity may become a nightmare for reservoir modelers in predicting presence, spatial distribution, impact on formation petrophysical characteristics, and particularly in dynamic behaviour prediction. Moreover, the very high resolution required to describe in detail the phenomena does not reconcile with the geo-cellular model resolution typically used for reservoir simulation. The scope of the work is to present an effective approach to predict karst presence and model it dynamically. Karst presence recognition started from the analysis of anomalous well behaviour and potential sources of precursors (logs, drilling evidence, etc.) to derive concepts for karst reservoir model. This first demanding step implies then characterizing each cell classified as karstified in terms of petrophysical parameters. In a two-phase flow, karst brings to fast travelling of water which leaves the matrix almost unswept. This feature was characterized through dedicated fine simulations, leading to an upscaling of relative permeability curves for a single porosity formulation. The workflow was applied to a carbonate giant field with a long production history under waterflood development. Firstly, a machine learning algorithm was trained to recognize karst features based on log response, seismic attributes, and well dynamic evidence, then a karst probability volume was generated and utilized to predict the karst presence in the field. Karst characterization just in terms of porosity and permeability is sufficient to model the reservoir when still in single phase, however it fails to reproduce observed water production. Karst provides a high permeability path for water transport: classical history match approaches, such as the introduction of permeability multipliers, proved to be ineffective in reproducing the water breakthrough timing and growth rate. In fact, the reservoir consists of two systems, matrix, and karst: however, the karst is less known and laboratory analysis shows relative permeability only for the matrix medium. The introduction of equivalent or pseudo-relative permeability curves, accounting for both the media, was crucial for correct modelling of the reservoir underlying dynamics, allowing a proper reproduction of water breakthrough timing and water cut (WCT) trends. The implementation of a dedicated pseudo relative permeability curve dedicated to karstified cells allowed to replicate early water arrival, thus bringing to a correct prediction of oil and water rates, also highlighting the presence of bypassed oil associated with water circuiting, particularly in presence of highly karstified cells.

A proper reservoir management is mandatory to optimize the water injection strategy through time, since the injected fluids tend to flush the same preferential paths, leading to a significant reduction of the incremental swept oil. This paper shows the results of an integrated workflow applied to a giant brown field with complex geology. The proposed workflow is based on a semi-automated process to optimize water injection, embodying the improvement and assessment of the 3D model. An integrated Production Data Analysis (iPDA), initially available, allowed to understand the main fluid dynamics of the reservoir, which were integrated in the 3D model since the earliest setup. Streamlines methodology was then used to compare the 3D model with the iPDA outputs in terms of subsurface dynamics, guiding the reservoir model history match process. Finally, streamlines traced on the validated model allowed to optimize water injection strategy for the forecast simulations using a semi-automatic process. It relies upon an iterative loop of rates redistribution among all active injectors, based on their own oil displacement efficiency calculated using dedicated software. The mentioned workflow was applied on Beta formation of Alpha field, which is a mid-Cenomanian carbonate giant oilfield in the Middle East region with more than sixty years of production and about five hundred drilled wells, characterized by karstic behavior. In this very challenging context, streamlines simulation technique, mostly used during the HM phase, resulted in an increase of 3D model reliability and representativeness of the main evidence from iPDA. This led to generate more robust forecast scenarios. In particular, the proposed workflow allowed to optimize the water injection strategy, adequately redistributing the overall available injection rate between all the injectors, promoting the most efficient ones, and reducing the inefficient. This approach resulted in a definitively appreciable oil reserves potential gain, consisting in the plateau extension of about one year from the forecast 3D simulations. The economic value of this result can be better appreciated if we consider that it is associated only to the re-distribution of the injection rate, without any additional capex.