Dynamic interwell connectivity analysis of multi-layer waterflooding reservoirs based on an improved graph neural network

The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention mechanism.Based on the material balance and physical information, the overall connectivity from the injection wells,through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.

On the uncertainty of interwell connectivity estimations from the capacitance-resistance model

The capacitance-resistance model （CRM） is an alternative to conventional reservoir simulation. CRM, a simplification of complex numerical models, uses production and injection rates to infer a reservoir description. There is no prior geologic model. The principal output of CRM fitting is the fraction of injected fluid （usually water） that is produced at a producer at steady-state. These fractions are interwell connectivities. Interwell connectivities are fundamental information needed to manage waterfloods in oil reservoirs. The data-driven CRM is a fast tool to estimate these parameters in mature fields and allows one to make full use of the dynamic data available. This paper considers the problem of setting an upper bound on the uncertainty of interwell connectivities for linear-constrained models. Using analytical bounds and numerical simulations, we derive a consistent upper limit on the uncertainty of interwell connections that can be used to quantify the information content of a given dataset.

A Model for the Connectivity of Horizontal Wells in Water-Flooding Oil Reservoirs

As current calculation models for inter-well connectivity in oilfields can only account for vertical wells,an updated model is elaborated here that can predict the future production performance and evaluate the connectivity of horizontal wells(or horizontal and vertical wells).In this model,the injection-production system of the considered reservoir is simplified and represented with many connected units.Moreover,the horizontal well is modeled with multiple connected wells without considering the pressure loss in the horizontal direction.With this approach,the production performance for both injection and production wells can be obtained by calculating the bottom-hole flowing pressure and oil/water saturation according to the material balance equation and a saturation front-tracking equation.Some effort is also provided to optimize(to fit known historical production performances)the two characteristic problem parameters,namely,the interwell conductivity and connected volume by means of a SPSA gradient-free algorithm.In order to verify the validity of the model,considering a heterogenous reservoir,three conceptual examples are constructed,where the number ratio between injection and production wells are 1/4,4/1 and 4/5,respectively.It is shown that there is a high consistency between simulation results and field data.

A Method for Identifying Channeling Paths in Low-Permeability Fractured Reservoirs

Often oilfield fractured horizontal wells produce water flowing in multiple directions.In this study,a method to identify such channeling paths is developed.The dual-medium model is based on the principle of inter-well connectivity and considers the flow characteristics and related channeling terms.The Lorentz curve is drawn to qualitatively discern the geological type of the low-permeability fractured reservoir and determine the channeling direction and size.The practical application of such an approach to a sample oilfield shows that it can accurately identify the channeling paths of the considered low-permeability fractured reservoir and predict production performances according to the inter-well connectivity model.As a result,early detection of water channeling becomes possible,paving the way to real-time production system optimization in low-permeability fractured reservoirs.

Kriging-boosted CR modeling for prompt infill drilling optimization

The capacitance-resistance model(CRM)has been a useful physics-based tool for obtaining production forecasts for decades.However,the model's limitations make it difficult to work with real field cases,where a lot of various events happen.Such events often include new well commissioning(NWC).We introduce a workflow that combines CRM concepts and kriging into a single tool to handle these types of events during history matching.Moreover,it can be used for selecting a new well placement during infill drilling.To make the workflow even more versatile,an improved version of CRM was used.It takes into account wells shut-ins and performed workovers by additional adjustment of the model coefficients.By preliminary re-weighing and interpolating these coefficients using kriging,the coefficients for potential wells can be determined.The approach was validated using both synthetic and real datasets,from which the cases of putting new wells into operation were selected.The workflow allows a fast assessment of future well performance with a minimal set of reservoir data.This way,a lot of well placement scenarios can be considered,and the best ones could be chosen for more detailed studies.

Analytical Determination of Interwell Connectivity Based on Interwell Influence

Interwell connectivity, an important element in reservoir characterization, especially for water flooding,is used to make decisions for better oil production. The existing methods in literature directly use related data of wells to infer interwell connectivity, but they ignore the influence between different wells. The connection of one well to more than two wells(as is often true in the oil field well pattern) will impact the accuracy of the connectivity analysis. To address this challenge, this paper proposes the Particle Swarm Optimization-based CatBoost for Interwell Connectivity(PSOC4IC) based on relative features to analyze interwell connectivity with the combination of joint mutual information maximization-based denoising sparse autoencoder for inter-feature construction and extraction and PSO-based CatBoost(PSO-CatBoost) for connectivity prediction with high-dimensional noise data.The experimental results show that the PSOC4IC improves analysis accuracy.