Efficient Optimization of Energy Recovery From Geothermal Reservoirs With Recurrent Neural Network Predictive Models

Improving the long‐term energy production performance of geothermal reservoirs can be accomplished by optimizing field development and management plans. Reliable prediction models, however, are needed to evaluate and optimize the performance of the underlying reservoirs under various operation and development strategies. In traditional frameworks, physics‐based simulation models are used to predict the energy production performance of geothermal reservoirs. However, detailed simulation models are not trivial to construct, require a reliable description of the reservoir conditions and properties, and entail high computational complexity. Data‐driven predictive models can offer an efficient alternative for use in optimization workflows. This paper presents an optimization framework for net power generation in geothermal reservoirs using a variant of the recurrent neural network (RNN) as a data‐driven predictive model. The RNN architecture is developed and trained to replace the simulation model for computationally efficient prediction of the objective function and its gradients with respect to the well control variables. The net power generation performance of the field is optimized by automatically adjusting the mass flow rate of production and injection wells over 12 years, using a gradient‐based local search algorithm. Two field‐scale examples are presented to investigate the performance of the developed data‐driven prediction and optimization framework. The prediction and optimization results from the RNN model are evaluated through comparison with the results obtained by using a numerical simulation model of a real geothermal reservoir.

[1]  L. Durlofsky,et al.  Convolutional – recurrent neural network proxy for robust optimization and closed-loop reservoir management , 2022, Computational Geosciences.

[2]  H. Nick,et al.  Optimisation of heat recovery from low-enthalpy aquifers with geological uncertainty using surrogate response surfaces and simple search algorithms , 2022, Sustainable Energy Technologies and Assessments.

[3]  Kyungbook Lee,et al.  Sequential field development plan through robust optimization coupling with CNN and LSTM-based proxy models , 2021, Journal of Petroleum Science and Engineering.

[4]  Yann LeCun,et al.  Learning in High Dimension Always Amounts to Extrapolation , 2021, ArXiv.

[5]  B. Jafarpour,et al.  Deep Convolutional Autoencoders for Robust Flow Model Calibration Under Uncertainty in Geologic Continuity , 2021, Water Resources Research.

[6]  Jianchao Cai,et al.  Evaluation of CO2 sequestration and circulation in fault-bounded thin geothermal reservoirs in North Oman using response surface methods , 2021, Journal of Hydrology.

[7]  L. Durlofsky,et al.  A Recurrent Neural Network–Based Proxy Model for Well-Control Optimization with Nonlinear Output Constraints , 2021 .

[8]  Yu Shi,et al.  An integrated multi-objective optimization method to improve the performance of multilateral-well geothermal system , 2021, Renewable Energy.

[9]  Behnam Jafarpour,et al.  Inverting subsurface flow data for geologic scenarios selection with convolutional neural networks , 2021 .

[10]  Yu Shi,et al.  Productivity prediction of a multilateral-well geothermal system based on a long short-term memory and multi-layer perceptron combinational neural network , 2021 .

[11]  J. Lund,et al.  Direct utilization of geothermal energy 2020 worldwide review , 2020, Geothermics.

[12]  K. Feigl,et al.  Optimizing geothermal production in fractured rock reservoirs under uncertainty , 2020 .

[13]  S. Geiger,et al.  Multi-objective optimization under uncertainty of geothermal reservoirs using experimental design-based proxy models , 2020 .

[14]  Behnam Jafarpour,et al.  Convolutional neural networks (CNN) for feature-based model calibration under uncertain geologic scenarios , 2020, Computational Geosciences.

[15]  T. Mukerji,et al.  Accounting for subsurface uncertainty in enhanced geothermal systems to make more robust techno-economic decisions , 2019, Applied Energy.

[16]  Ian Jefferson,et al.  A hybrid optimisation approach to improve long-term performance of enhanced geothermal system (EGS) reservoirs , 2019, Renewable Energy.

[17]  Behnam Jafarpour,et al.  Closed-Loop Stochastic Oilfield Optimization Under Uncertainty in Geologic Description and Future Development Plans , 2019, Day 1 Wed, April 10, 2019.

[18]  Behnam Jafarpour,et al.  Reservoir Performance Optimization under Uncertain Future Development Plans , 2018 .

[19]  Eric Laloy,et al.  Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network , 2017, 1710.09196.

[20]  Roland N. Horne,et al.  Recurrent Neural Networks for Permanent Downhole Gauge Data Analysis , 2017 .

[21]  Saman Razavi,et al.  Progressive Latin Hypercube Sampling: An efficient approach for robust sampling-based analysis of environmental models , 2017, Environ. Model. Softw..

[22]  J. Jansen,et al.  A Stochastic Simplex Approximate Gradient (StoSAG) for optimization under uncertainty , 2017 .

[23]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[24]  P. Olasolo,et al.  Enhanced geothermal systems (EGS): A review , 2016 .

[25]  R. Bertani.  Geothermal power generation in the world 2010–2014 update report , 2016 .

[26]  Anthony J. Jakeman,et al.  A review of surrogate models and their application to groundwater modeling , 2015 .

[27]  Hlynur Stefansson,et al.  Mixed integer optimization model for utilizing a geothermal reservoir , 2015 .

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[29]  Sadiq J. Zarrouk,et al.  Efficiency of geothermal power plants: A worldwide review , 2014 .

[30]  Maurizio Vaccaro,et al.  Numerical simulation of geothermal reservoirs for the sustainable design of energy plants: A review , 2014 .

[31]  P.M.J. Van den Hof,et al.  Improving the ensemble-optimization method through covariance-matrix adaptation , 2014 .

[32]  Roland N. Horne,et al.  Optimization of injection scheduling in fractured geothermal reservoirs , 2013 .

[33]  A. Reynolds,et al.  Theoretical connections between optimization algorithms based on an approximate gradient , 2013, Computational Geosciences.

[34]  Michael de Paly,et al.  Optimization of energy extraction for vertical closed-loop geothermal systems considering groundwater flow , 2013 .

[35]  Bryan A. Tolson,et al.  Review of surrogate modeling in water resources , 2012 .

[36]  Dongxiao Zhang,et al.  Efficient Ensemble-Based Closed-Loop Production Optimization , 2009 .

[37]  Behnam Jafarpour,et al.  Reservoir Characterization With the Discrete Cosine Transform , 2009 .

[38]  Gijs van Essen,et al.  Robust Waterflooding Optimization of Multiple Geological Scenarios , 2009 .

[39]  Paul M.J. Van den Hof,et al.  Model-based control of multiphase flow in subsurface oil reservoirs , 2008 .

[40]  Behnam Jafarpour,et al.  History matching with an ensemble Kalman filter and discrete cosine parameterization , 2008 .

[41]  Deniz Baş,et al.  Modeling and optimization I: Usability of response surface methodology , 2007 .

[42]  Jorge Nocedal,et al.  On the Implementation of an Algorithm for Large-Scale Equality Constrained Optimization , 1998, SIAM J. Optim..

[43]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[44]  G. M. Shook,et al.  Multi-purpose simulation , 1993 .

[45]  B. Jafarpour,et al.  Recurrent neural networks for short-term and long-term prediction of geothermal reservoirs , 2022, Geothermics.

[46]  B. Jafarpour,et al.  Recurrent Neural Networks for Prediction of Geothermal Reservoir Performance , 2021 .

[47]  R. Horne,et al.  Prediction Modeling for Geothermal Reservoirs Using Deep Learning , 2020 .

[48]  Robert J. Mellors,et al.  An efficient optimization of well placement and control for a geothermal prospect under geological uncertainty , 2015 .

[49]  Hans-Georg Frede,et al.  Comparison of two different approaches of sensitivity analysis , 2002 .