1887

Abstract

Summary

Classical reservoir engineering studies require building geological models and solving complex fluid flow transport equations that require high-quality data, numerous computational resources, time and workflows.

For large and mature fields data-driven models can be used to get faster answer and to perform production analysis more efficiently.

Capacitance Resistive Models (CRM) are a class of methods based on material balance that can be used to estimate production wells liquid rates as a function of injected water and Bottom Hole Pressure (BHP) variations. CRM methods quantify the connectivity between producers and injectors using only dynamic data. An important drawback of CRM is that they can suffer from parameter identification problems. Moreover, the analytical solution can be only obtained in specific conditions: linear variations of BHP and fixed injection rate between two consecutive time steps.

In this work we present a new approach combining CRM material balance equations with neural networks in order to obtain more robust and reliable estimation of the CRM parameters (i.e. well connectivity, productivity indices and time constants). This proposal is also interesting since it is not based on any assumption on BHP and injection rates.

To this end, we use a recent approach called Physics Informed Neural Networks (PINNs). In this approach neural networks are trained on observed data with additional physics constraints traduced in appropriate loss functions. The parameters of this physical equation are evaluated at the same time as the neural network weights.

The introduction of PINNs in our approach raised after testing classical machine learning (ML) models (SVMs, Random Forests …) and deep learning models (MLP, LSTM, RNNs…). Indeed, such models can perform well in some specific cases but usually struggle to produce robust results (i.e. forecasting) in the long term. Unfortunately, such systems do not natively integrate physics constraints.

Our aim is to impose physic constraints in neural networks. Thus, we may obtain more stable and reliable results. On the same time, we should be able to account for more behaviors that are not explained by simplified physic equations such as material balance.

We performed a full comparison between our approach using PINNs, other standard ML and DL approaches and a given framework of CRMs on two data-sets: a simple but realistic model build using a commercial reservoir simulator, and a real data set. We show that our approach gives more robust results (in terms of MSE) while not suffering from parameter identification issue.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202035123
2020-09-14
2024-03-29
Loading full text...

Full text loading...

References

  1. RafaelWanderley de Holanda, EduardoGildin, Jerry L.Jensen, Lary W.Lake, C. ShahKabir
    State-of-the-Art Literature Review on Capacitance Resistive Models for Reservoir Characterization and Performance Forecasting, 2018.
    [Google Scholar]
  2. Ali AbdallahYoussef, Pablo HugoGentil, Jerry LJensen, LaryLake
    . A Capacitance Model to Infer Interwell Connectivity from Production and Injection Rate Fluctuations. SPE Reserv. Eval. Eng.2006, 9, 630–646. [CrossRef]
    [Google Scholar]
  3. Ali AbdallahAl-Yousef
    , investigating statistical techniques to infer interwell connectivity from injection and production rate fluctuations. Ph.D. Dissertation, University of Texas, Austin, TX, USA, 2006.
    [Google Scholar]
  4. MortezaSayarpour, LaryLake, C.ShahKabir, ElizabethZuluaga
    , The use of capacitance resistive models for rapid estimation of waterflood performance and optimization, 2007.
    [Google Scholar]
  5. IanGoodfellow, YoshuaBengio, AaronCourville
    , Deep learning, MIT Press, 2016.
    [Google Scholar]
  6. MaziarRaissi, ParisPerdikaris, GEKarniadakis
    , Physics informed deep learning (part I): Data-driven solutions of nonlinear partial differential equations - arXiv preprint arXiv:1711.10561, 2017
    [Google Scholar]
  7. , Physics informed deep learning (part II): Data-driven discovery of nonlinear partial differential equations arXiv preprint arXiv:1711.10561, 2017.
    [Google Scholar]
  8. NicholasGeneva, NicholasZabaras
    , Modelling the dynamics of PDE systems with physics constrained Deep Auto-Regressive Networks, 2019.
    [Google Scholar]
  9. YinhaoZhu, NicolasZabaras, Phaedon-SteliosKoutsourelakis, ParisPerdikaris
    , Physics-Constrained Deep learning for high dimensional surrogate modelling and uncertainty quantification without labelled data, 2019.
    [Google Scholar]
  10. ChengYang, XuboYang, XiangyunXiao
    , Data-driven projection method in fluid simulation, Computer Animation and Virtual Worlds27 (3-4) (2016) 415–424. arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/cav. 1695, doi:10.1002/cav.1695. URL https://onlinelibrary.wiley.com/doi/abs/10.1002/cav.1695
    [Google Scholar]
  11. MehryarMohri, AfshinRostamizadeh, AmeetTalwalkar
    , Foundations of Machine Learning, MIT Press2012.
    [Google Scholar]
  12. Robert E.Schapire, YoavFreund
    , Boosting Foundations and Algorithms, MIT Press2012.
    [Google Scholar]
  13. SteveCannon
    , Reservoir Modelling A Practical Guide, 2018.
    [Google Scholar]
  14. L.PDake
    , Fundamentals of Reservoir Engineering.
    [Google Scholar]
  15. MortezaSayarpour
    , Development and applications of Capacitance Resistive Models to water CO2/Floods. Ph.D. Dissertation, University of Texas, Austin, TX, USA, 2008.
    [Google Scholar]
  16. Dimitris C.Psichogios, LyleH.Ungar
    . (1992). A hybrid neural network-first principle approach to process modeling. AIChE Journal, 38(10), 1499–1511. doi:10.1002/aic.690381003
    https://doi.org/10.1002/aic.690381003 [Google Scholar]
  17. MaziarRaissi
    , Hidden fluid mechanics: learning velocity and pressure fields from flow visualizations, https://maziarraissi.github.io/research/09_hidden_fluid_mechanics/
    [Google Scholar]
  18. Richard H.Byrd, Nicolas I.MGould, JORGENocedal, RICHARD A.Waltz
    , On the convergence of successive linear-quadratic programming algorithms - SIAM Journal on Optimization, 2005 – SIAM
    [Google Scholar]
  19. AlexKendall, YarinGal, and RobertoCipolla
    . “Multi-task learning using uncertainty to weigh losses for scene geometry and semantics.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202035123
Loading
/content/papers/10.3997/2214-4609.202035123
Loading

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