Comparing ARIMA and LSTM models to predict time series in the oil industry
Resumo
Monitoring and forecasting oil and gas (O\&G) production is essential to extend the life of a well and increase reservoirs' productivity. Popular models for O\&G time series are ARIMA and LSTM recurrent networks, and tipically several lags are forecasted at once. LSTM models can deploy the recursive prediction strategy, which uses one prediction to make the next, or the multiple outputs (MO) strategy, which predicts a sequence of values in a single shot. This work assesses ARIMA and LSTM models for the forecasting of petroleum production time series. We use time series of pressure and gas/oil flow from actual wells with distinct properties, for which we developed predictive models considering different time horizons. For the LSTM models, we deploy both the recursive and MO strategies. Our comparison revealed the superiority of LSTM models in general, and MO-based models for longer time intervals.
Referências
Bontempi, G., Taieb, S. B., and Le Borgne, Y.-A. Machine learning strategies for time series forecasting. In European business intelligence summer school. Springer, pp. 62–77, 2012.
Box, G. Time series analysis forecasting and control. Holden-Day, San Francisco, 1970.
Chimmula, V. K. R. and Zhang, L. Time series forecasting of covid-19 transmission in canada using lstm networks. Chaos, Solitons & Fractals vol. 135, pp. 109864, 2020.
Fan, D., Sun, H., Yao, J., Zhang, K., Yan, X., and Sun, Z. Well production forecasting based on arima-lstm model considering manual operations. Energy vol. 220, pp. 119708, 2021.
Garcia, J., Levy, A., Tung, A., Yang, R. M., and Kaynig, F. Applying deep learning to petroleum well data. Harvard University, Harvard John A Paulson School of Engineering and Applied Sciences , 2018.
Graves, A., Mohamed, A.-r., and Hinton, G. Speech recognition with deep recurrent neural networks. In 2013 IEEE international conference on acoustics, speech and signal processing. Ieee, pp. 6645–6649, 2013.
Guariso, G., Nunnari, G., and Sangiorgio, M. Multi-step solar irradiance forecasting and domain adaptation of deep neural networks. Energies 13 (15): 3987, 2020.
Hochreiter, S. and Schmidhuber, J. Long short-term memory. Neural computation 9 (8): 1735–1780, 1997.
Liu, W., Liu, W. D., and Gu, J. Forecasting oil production using ensemble empirical model decomposition based long short-term memory neural network. Journal of Petroleum Science and Engineering vol. 189, pp. 107013, 2020.
Masum, S., Liu, Y., and Chiverton, J. Multi-step time series forecasting of electric load using machine learning models. In International conference on artificial intelligence and soft computing. Springer, pp. 148–159, 2018.
Sagheer, A. and Kotb, M. Time series forecasting of petroleum production using deep lstm recurrent networks. Neurocomputing vol. 323, pp. 203–213, 2019.
Siami-Namini, S., Tavakoli, N., and Namin, A. S. A comparison of arima and lstm in forecasting time series. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, pp. 1394–1401, 2018.
Wang, Z. and Lou, Y. Hydrological time series forecast model based on wavelet de-noising and arima-lstm. In 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). IEEE, pp. 1697–1701, 2019.
Xiong, T., Bao, Y., and Hu, Z. Beyond one-step-ahead forecasting: evaluation of alternative multi-step-ahead forecasting models for crude oil prices. Energy Economics vol. 40, pp. 405–415, 2013.
Yunpeng, L., Di, H., Junpeng, B., and Yong, Q. Multi-step ahead time series forecasting for different data patterns based on lstm recurrent neural network. In 2017 14th web information systems and applications conference (WISA). IEEE, pp. 305–310, 2017.
