Model-Free Assessment of Inter-Well Connectivity in CO2 WAG Projects Using Statistical Recurrent Unit Models
- 15 September 2021
- conference paper
- conference paper
- Published by Society of Petroleum Engineers (SPE) in Day 2 Wed, September 22, 2021
Abstract
Routine well-wise injection and production measurements contain significant information on subsurface structure and properties. Data-driven technology that interprets surface data into subsurface structure or properties can assist operators in making informed decisions by providing a better understanding of field assets. Our machine-learning framework is built on the statistical recurrent unit (SRU) model and interprets well-based injection/production data into inter-well connectivity without relying on a geologic model. We test it on synthetic and field-scale CO2 EOR projects utilizing the water-alternating-gas (WAG) process. SRU is a special type of recurrent neural network (RNN) that allows for better characterization of temporal trends, by learning various statistics of the input at different time scales. In our application, the complete states (injection rate, pressure and cumulative injection) at injectors and pressure states at producers are fed to SRU as the input and the phase rates at producers are treated as the output. Once the SRU is trained and validated, it is then used to assess the connectivity of each injector to any producer using permutation variable importance method, wherein inputs corresponding to an injector are shuffled and the increase in prediction error at a given producer is recorded as the importance (connectivity metric) of the injector to the producer. This method is tested in both synthetic and field-scale cases. The validation of the proposed data-driven inter-well connectivity assessment is performed using synthetic data from simulation models where inter-well connectivity can be easily measured using the streamline-based flux allocation. The SRU model is shown to offer excellent prediction performance on the synthetic case. Despite significant measurement noise and frequent well shut-ins imposed in the field-scale case, the SRU model offers good prediction accuracy, the overall relative error of the phase production rates at most producers ranges from 10% to 30%. It is shown that the dominant connections identified by the data-driven method and streamline method are in close agreement. This significantly improves confidence in our data-driven procedure. The novelty of this work is that it is purely data-driven method and can directly interpret routine surface measurements to intuitive subsurface knowledge. Furthermore, the streamline-based validation procedure provides physics-based backing to the results obtained from data analytics. The study results in a reliable and efficient data analytics framework that is well-suited for large field applications.Keywords
This publication has 47 references indexed in Scilit:
- Robust streamline tracing using inter-cell fluxes in locally refined and unstructured gridsWater Resources Research, 2012
- High-Dimensional Regression and Variable Selection Using CAR ScoresStatistical Applications in Genetics and Molecular Biology, 2011
- Nonstationary hydrological time series forecasting using nonlinear dynamic methodsJournal of Hydrology, 2005
- The Problem of OverfittingJournal of Chemical Information and Computer Sciences, 2003
- Forecasting and trading currency volatility: an application of recurrent neural regression and model combinationJournal of Forecasting, 2002
- Long Short-Term MemoryNeural Computation, 1997
- Dominance analysis: A new approach to the problem of relative importance of predictors in multiple regression.Psychological Bulletin, 1993
- Continuous groundwater velocity fields and path lines in linear, bilinear, and trilinear finite elementsWater Resources Research, 1992
- Semianalytical Computation of Path Lines for Finite‐Difference ModelsGroundwater, 1988
- Learning representations by back-propagating errorsNature, 1986