Reservoir simulation plays a vital role as oil and gas companies rely on them in the development of new fields. Therefore, a reliable and fast reservoir simulation is a crucial instrument to explore more scenarios and optimize the production. In each simulation, the reservoir is divided into millions of cells, and rock and fluid attributes are assigned to these cells. Then, based on these attributes, flow equations are solved with time-consuming numerical methods. Given the recent progress in machine learning, the possibility of using deep learning in reservoir simulation has been investigated in this paper. In the new approach, fluid flow equations are solved using a deep learning-based simulator instead of time-consuming mathematical approaches. In this paper, we studied 1D Oil Reservoir and 2D Gas Reservoir. Data sets generated using the numerical models were used to create the developed simulators. We used two metrics to evaluate our models: Mean Absolute Percentage Error (MAPE) and correlation coefficient (R2). Given the low value of these matrics (MAPE < 15.1%, R2 >0.84 for 1D and MAPE < 0.84%, R2 ≈ 1 for 2D), the results confirmed that the deep learning approach is reasonably accurate and trustworthy when compared with mathematically derived models.


Article metrics loading...

Loading full text...

Full text loading...


  1. Carminatti, M., Wolff, B., Gamboa, L.
    2008. New exploratory frontiers in Brazil. Proceedings of the 19th World Petroleum Congress., pp.28–37.
    [Google Scholar]
  2. Chafetz, H.S. and Folk, R.L.
    1984. Travertines: Depositional Morphology and the Bacterially Constructed Constituents. Journal of Sedimentary Petrology. 54(1), pp.289–316.
    [Google Scholar]
  3. Della Porta, G., Capezzuoli, E. and De Bernardo, A.
    , 2017. Facies character and depositional architecture of hydrothermal travertine slope aprons (Pleistocene, Acquasanta Terme, Central Italy). Marine and Petroleum Geology, 87, pp.171–187.
    [Google Scholar]
  4. Fisher, Q.J. and Knipe, R.J.
    1998. Fault sealing processes in siliciclastic sediments. Geological Society, London, Special Publications. [Online]. 147(1), pp. 117–134. Available from: http://sp.lyellcollection.org/lookup/doi/10.1144/GSL.SP.1998.147.01.08.
  5. Guo, L. and Riding, R.
    1998. Hot-spring travertine facies and sequences, Late Pleistocene, Rapolano Terme, Italy. Sedimentology. 45(1), pp.163–180.
    [Google Scholar]
  6. Knipe, R.J.
    1992. Faulting processes and fault seal. In: Larsen, R.M., Brekke, H., Larsen, B.T. & Talleras, E. (eds)Structural and Tectonic Modelling and its Application to Petroleum Geology, Volume 1. Elsevier, Amsterdam, 325–342
    [Google Scholar]
  7. Maggi, M., Cianfarra, P., Salvini, F. and De Lima, C.C.
    2015. Staircase fractures in microbialites and the role of lamination-related mechanical anisotropy: The example of the Acquasanta Terme travertine deposits (central Italy). Bulletin of the Geological Society of America. 127(5–6), pp.879–896.
    [Google Scholar]
  8. Michie, E.A.H., Yielding, G. and Fisher, Q.J.
    2018. Predicting transmissibilities of carbonate-hosted fault zones. Geological Society Special Publication. 459(1).
    [Google Scholar]
  9. Yielding, G., Freeman, B. and Needham, D.T.
    1997. Quantitative fault seal prediction. AAPG Bulletin. 81(6), pp.897–917.
    [Google Scholar]

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error