Automatic Parameter Estimation From Well Test Data Using Artificial Neural Network

Abstract

We propose a robust way of achieving a well test interpretation by combining the sequential predictive probability method with an artificial neural network approach. The sequential predictive probability method considers all possible reservoir models and determines which candidate model or models best predict the well response. This method is dependent on obtaining good initial estimates for the parameters governing the candidate reservoir models, which is achieved by applying the artificial neural network approach. We use the neural network to identify the characteristic components of the pressure derivative curve corresponding to the flow regimes known to be in each candidate model. Reservoir parameters are then computed using the data in the identified range of the corresponding behavior. As a final step, the candidate models and their initial estimates are evaluated using the sequential probability method. The method discriminates between the candidate models and simultaneously performs nonlinear regression to compute the best estimates of reservoir parameters. The trained neural network was able to identify the characteristic components of the derivative curve in most cases. The algorithm written to interpret the neural network signals into flow regimes required special procedures to take care of the misclassification from the neural network. The initial estimates of reservoir parameters from the neural network were found to be reasonably close to the eventual estimates from the sequential predictive probability method. Introduction Traditional methods of well test interpretation are usually based on a combination of manual and automated techniques, although both techniques are usually computer based. Manual interpretation uses the pressure derivative plot introduced by Bourdet et al. The characteristics of different reservoir flow regimes can be observed from the plot. Hence, we are able to analyze the type of the associated reservoir and determine their parameters from the appropriate flow regimes. Automated interpretation by nonlinear regression is then used to determine the best estimates of reservoir parameters, and confidence intervals are used to authenticate the selected reservoir model. With new developments in pressure measurement, including permanently installed gauges, we may have an enormous amount of pressure data coming in each day. This study looked at a procedure to mechanize the interpretation of such well test data. There are three key steps in the procedure. First, all the characteristic components of the derivative plot have to be recognized. This task is accomplished by a specially trained neural network. Second, the signals from the neural network are translated into reservoir flow regimes so that initial estimates of reservoir parameters can be evaluated. Third, the sequential predictive probability procedure discriminates between candidate reservoir models, simultaneously performing nonlinear regression based on the initial estimates provided by the neural network. Previous Work Allain and Horne used syntactic pattern recognition and a rule-based system to identify the reservoir model and to estimate its parameters. The pressure derivative data were first preprocessed in order to distinguish the true response from the noise. P. 249

Hydrocarbon reservoir model detection from pressure transient data using coupled artificial neural network—Wavelet transform approach

“…In our previous researches two different automated models based on MLPNN and recurrent network were developed for detection of eight different oil reservoir models from synthetic PD patterns which have 33 sample points [5,9]. In 1995, Athichanagorn and Horne used MLPNN for recognizing characteristic parts and their appearance times in pressure derivative plots of some candidate reservoir models [12]. The obtained values from MLPNN are then used as initial guesses in sequential predictive probability method for diagnosing reservoir model and estimating its parameters [12].…”

“…In 1995, Athichanagorn and Horne used MLPNN for recognizing characteristic parts and their appearance times in pressure derivative plots of some candidate reservoir models [12]. The obtained values from MLPNN are then used as initial guesses in sequential predictive probability method for diagnosing reservoir model and estimating its parameters [12].…”

Artificial Neural Network (ANN) to estimate reservoir parameters in Naturally Fractured Reservoirs using well test data

“…Advantages of using ANN to recognize reservoir model and estimate its parameters are (Al-Kaabi and Lee, 1990;Allian and Houze, 1992;Ershaghi et al, 1993;Athichanagorn and Horne, 1995;Deng and Chen, 2000):…”

“…They used ANN to identify the type of reservoir model and symbolic approach to estimate reservoir parameters. Although some other authors have also used ANN to recognize reservoir model from well test data (Ershaghi et al, 1993;Athichanagorn and Horne, 1995;Kharrat and Razavi, 2008;Vaferi et al, 2011), there are limited studies on using ANN to estimate reservoir parameters. Usual methods to estimate reservoir parameters using well test data include: conventional (straight line) analysis, type-curves, and non-linear regression.…”

Artificial Intelligence Assisted History Matching -- Proof of Concept

“…• Application of NNs in well log interpretation (Baldwin, Otte, & Whealtley, 1989) (Jong-Se & Jungwhan, 2004) (Masoud, 1998) • Using NNs in well test data analysis (Al-Kaabi & Lee, 1990) (Ershaghi, Li, Hassibi, & Shikari, 1993) (Athichanagorn & Horne, 1995) (Sultanp & Al-Kaabi, 2002) • NNs a helpful tool in reservoir characterization (Mohaghegh., Arefi, Ameri., & Rose., 1995) (Ahmed, Link, Porter, Wideman, Himmer, & Braun, 1997) (Singh, Painuly, Srivastava, Tiwary, & Chandra, 2008) • Application of NNs to calibrate seismic attributes (David, 1993), seismic pattern recognition (Yang & Huang, 1991), inversion of seismic waveforms (Roth & Tarantoia, 1992) • Prediction of PVT data (Briones, Rojas, Moreno, & Martinez, 1994) (Gharbi & Elsharkawy, 1997) (Osman, Abdel-Wahhab, & Al-Marhoun, 2001) (Oloso, Khoukhi, Abdulraheem, & Elshafei, 2009) • Identifying fractures and faults (L. Thomas & Pointe, 1995) (Key, Nielsen, Signer, Sønneland, Waagbø, & H. Veire, 1997) (Sadiq & I.S. Nashawi, 2000) (Aminzadeh & deGroot, 2005) • Detecting hydrocarbons (Cheng-Dang, Wu, Mo, Zhu, & Xu, 1994) (Aminzadeh & deGroot, 2005), forecast formation damage (Nikravesh, Kovscek, Johnston, & Patzek, 1996) (Kalam, Al-Alawi, & Al-Mukheini, 1996) etc…”