Application of ARIMA-RTS optimal smoothing algorithm in gas well production prediction

Abstract

Gas field production forecast is an important basis for decision-making in the gas industry. How to accurately predict the dynamic production during gas field development is an important content of reservoir engineering research. Reservoir numerical simulation is the most common method for predicting oil and gas production. However, it requires a lot of data to build an accurate geological model which is tedious and time-consuming. At present, many scholars have used machine learning and data mining methods to predict oil and gas production, but they have not considered whether the use of increasing production measures will affect the predicted results.

Thus, ARIMA-RTS optimal smooth algorithm is the first applied to establish the prediction model of gas well production. According to the historical production data, the model is processed, the production differential autoregressive integral moving average (ARIMA) model in time series is established, then ARIMA model is combined with RTS (Rauch Tung Striebel) smoothing, and the production prediction model is constructed. RTS smoothing algorithm is an enhanced version of Kalman filter. The measurements are firstly processed by the forward filter, and then, a separate backward smoothing pass is used for obtaining the smoothing solution. The correctness of ARIMA-RTS model was verified with the actual production data. The results show that the prediction based on ARIMA-RTS model can accurately reflect the production performance of gas well. This method can effectively reduce the error caused by stimulation when predicting. When using the ARIMA-RTS model and the ARIMA-Kalman model to predict the production of the same gas well, the prediction accuracy of ARIMA-RTS model is higher than that of ARIMA-Kalman model in production wells with stimulation. Compared with that of the ARIMA-Kalman model, the mean relative error fitted by the ARIMA-RTS model is reduced by 46.3%, and the relative mean square error is reduced by 56.48%. ARIMA-RTS optimal smooth algorithm improves the prediction accuracy of gas well that uses stimulation. We therefore conclude that the ARIMA-RTS optimal smooth algorithm can help us better forecast the forecasting gas well production with stimulation, as well as other fuels output.

Keywords

Production forecasting / ARIMA / RTS / Kalman filter

References

[1] U. Nwaobi, G. Anandarajah, Parameter determination for a numerical approach to undeveloped shale gas production estimation: the UK Bowland shale region application, J. Nat. Gas Sci. Eng. 58 (2018) 80-91, https://doi.org/10.1016/j.jngse.2018.07.024.

[2] C.L. Cipolla, E.P. Lolon, J.C. Erdle, B. Rubin, Reservoir modeling in shale-gas reservoirs, J. spe reservoir.Eval. Eng. (13) (2010) 638-653, https://doi.org/10.1021/acs.energyfuels.0c03787.

[3] A.J. Clark, Production data analysis of unconventional gas wells: review of theory and best practices, J.Int. J. Coal Geol. 109 (2013) 101-146, https://doi.org/10.1016/j.coal.2013.01.002.

[4] Yihua Zhong, The Study of Dynamic Prediction Methods for Oilfield Development Programming in Ulter-High Water-Cut Stage, Southwest Petroleum University, D.Chengdu, 2008.

[5] Cailan Zhou, Min Liu,Application research on oil production forecasting based on BP neutral netwok, J. Wuhan Univ. Technol. 31 (3) (2009) 125-129.

[6] S. Fulford, B. Bowie, M.E. Berry, et al., Machine learning as a reliable technology for evaluating time/rate performance of unconventional wells, J. SPE Economics & Management 8 (1) (2016) 23-39, https://doi.org/10.2118/174784-PA.

[7] P.J. Brockwell, R.A. Davis, Introduction to Time Series and Forecasting, Springer International Publishing, Switzerland, 2016.

[8] Qiaohong Chen, Chaohong Sun, ShiminYu, et al., Research on estimation of ads click rate based on recurrent neural network, J. Zhejiang SCI-TECH Univ.(Nat. Sci. Ed.) 35 (6) (2016) 880-885.

[9] D. Seemann, M. Williamson, S. Hasan, Improving Reservoir Management through Big Data Technologies R, 2013. SPE 167482.

[10] M.O. Korovin, V.P. Merkulov, Formation evaluation and well-test analysis for complex interpretation of reservoir permeability distribution, C. USOV:IOP (2014) 1-6.

[11] R. Jozefowicz, W. Zaremba, I. Sutskever,An Empirical Exploration of Recurrent Network Architectures. C. International Conference on Machine Learn-Ing, Lille: JMLR., 2015, pp. 2342-2350.

[12] Jianwei Gu, Mei Zhou, L.I. Zhitao, et al., Oil well Production forecast with longshort term memory network m-odel based on data mining, J. Special Oil & Gas Reservoirs 26 (2) (2019) 81-85, 135.

[13] Chunhua Hou, Prediction method of oil production in new wells based on long and short term me-mory network, J. Oil and Gas Geology and Recovery 26 (3) (2019) 105-110.

[14] Xia Lin boyu Wu, Hongliang Wang, Zongshang Liu, Comparison of oilfield production forecast methods based on machine learning, J. Information System Engineering (2019) 120-122, 08.

[15] V.S. Ediger, S. Akar, B. Ugurlu, Foreccasting production of fossil fule sources in Turkey using a comparative regression and model, J. Energy Policy. 34 (18) (2006) 3836-3846.

[16] Dongyan Fan, Hai Sun, Jun Yao, Kai Zhang, Xia Yan, Zhixue Sun, Well production forecasting based on ARIMA-LSTM model considering manual operations, J. Energy 220 (2021) 119708, https://doi.org/10.1016/j.energy.2020.119708.

[17] J. Frausto-Solis, M. Chi-Chim, L. Sheremetov, Forecasting oil production time series with a population-based simulated annealing method, J.Arabian J. Sci. Eng. 40 (4) (2015) 1081-1096, https://doi.org/10.1007/s13369-015-1587-z.

[18] Qiang Wang, Shuyu Li, Rongrong Li, Forecasting Energy Demand in China and India: Using Single-Linear, Hybrid-Linear, and Non-linear Time Series Forecast Techniques, 2018, https://doi.org/10.1016/j.energy.2018.07.168.

[19] Qiang Wang, Shuyu Li, Rongrong Li,China's dependency on foreign oil will exceed 80% by 2030: developing a novel NMGM-ARIMA to forecast China's foreign oil dependence from two dimensions, Energy 163 (2018) 151-167.

[20] Qiang Wang, Shuyu Li, Rongrong Li,Forecasting US shale gas monthly production using a hybrid ARIMA and metabolic nonlinear grey model, Energy 160 (2018) 378-387.

[21] Jianwei Gu, Gulei Sui, L.I. Zhitao, Wei Liu, Yike Wang, Yigen Zhang,Oil well production forecasting method based on ARIMA-Kalman filter data mining model, J. Shenzhen Univ.(Sci. Eng.) 35 (2018) 575-581, https://doi.org/10.3724/SP.J.1249.2018.06575, 06.

[22] Zhendong Mao, Mugen Peng, Xiqing Liu, Channel estimation for reconfigurable intelligent surface assisted wireless communication systems in mobility scenarios, J. China Communications. 18 (2021) 29-38, 03.

[23] Chonglun Yue, Zeng Yuan, Yunkai Guo, Application research of Kalman filter algorithm for improving the precision of satellite navigation, 02, J. Survey Eng. 30 (2021) 60-64, 71.

[24] Yaoyu Wang, Renwen Chen, Xiang Zhang, Application of improved robust volume Kalman filter algorithm based on singular value decomposition in global positioning navigation, J. Sci.Technol.Eng. 21 (2021) 2356-2362, 06.

[25] Chi Guo, Shengyong You, Yarong Luo, Jianlang Hu, Wei Dong, A fast moving target detection tracking and trajectory prediction system for binocular vision, J. Wuhan Univ J Natural Sci 26 (2021) 69-80, 01.

[26] L. Xuan, Y. Jing, Application of RTS optimal smoothing algorithm in satellite attitude determination, in: 2011 2nd International Conference on Intelligent Control and Information Processing, Harbin, China, 2011, pp. 978-982, https://doi.org/10.1109/ICICIP.2011.6008397.

[27] Yubo Bao, Zong Hong, Chunqing Zhang, The application of RTS smooth filtering in post-event attitude determination, J. Space control technology and application 41 (2015) 18-22, 03.

[28] Lei Qi, Zhihui Gong, Hongyi Geng, Research on satellite attitude postprocessing based on RTS smoothing, J. Inf.Eng.Univ. 18 (2017) 370-374, 03.

[29] Min Li, Zhimei Chen, Xuejuan Shao, Iterated unscented Kalman particle filter of fusion RTS smoothing, J. Taiyuan Univ.Sci. Technol. 37 (2016) 266-269, 04.

[30] Xiaolin Gong, Jiancheng Fang, Application of SVD based R-T-S optimal smoothing algorithm to pos for airborne SAR motion compensation, J. Journal of Aeronautics. 30 (2009) 311-318, 02.

[31] Le Wang, Yue Fan, Chen Miao, GPS/GLONASS/GALILEO real-time service (RTS) product performance evaluation analysis, J. Navigation positioning and timing 7 (2020) 65-72, 05.

[32] Lu Deng, Xiaotong Zhang, The lag length selection in ADF test: simulation evidence from an ARIMA (0, 1,q) proces, J. Quant.Tech.Econ (9) (2008) 126-138.

[33] Jinzhou Xin, Jianting Zhou, S.X. Yang, et al., Bridge structure deformation prediction based on GNSS data using Kalman-ARIMA-GARCH model, J. Sensors 18 (1) (2018) 298, https://doi.org/10.3390/s18010298.

[34] Da Li, Forecast and Application of Oilfield Production Based on Time Series Analysis Method, D. Lanzhou University of Technology, 2018.