### Abstract

In geosciences, complex forward problems met in geophysics, petroleum system analysis and reservoir engineering problems often requires replacing these forward problems by proxies, and these proxies are used for optimizations problems. For instance, History Matching of observed field data requires a so large number of reservoir simulation runs (especially when using geostatistical geological models) that it is often impossible to use the full reservoir simulator. Therefore, several techniques have been proposed to mimic the reservoir simulations using proxies. Due to the use of experimental approach, most of authors propose to use second order polynomials. In this paper we demonstrate that: (1) Neural networks can also be second order polynomials. Therefore, the use of a neural network as a proxy is much more flexible and adaptable to the non linearity of the problem to be solved; (2) First order and second order derivatives of the neural network can be obtained providing gradients and hessian for optimizers. For inverse problems met in seismic inversion, well by well production data, optimal well locations, source rock generation, etc., most of the time, gradient methods are used for finding an optimal solution. The paper will describe how to calculate these gradients from a neural network built as a proxy. When needed, the hessian can also be obtained from the neural network approach. On a real case study, the ability of neural networks to reproduce complex phenomena (water-cuts, production rates. etc.) is showed. Comparisons with second polynomials (and kriging methods) will be done demonstrating the superiority of the neural network approach as soon as non linearity behaviors are present in the responses of the simulator. The gradients and the hessian of the neural network will be compared to those of the real response function.

Original language | English |
---|---|

Title of host publication | ECMOR 2012 - 13th European Conference on the Mathematics of Oil Recovery |

Publisher | European Association of Geoscientists and Engineers, EAGE |

Publication status | Published - 2012 |

Externally published | Yes |

Event | 13th European Conference on the Mathematics of Oil Recovery, ECMOR 2012 - Biarritz, France Duration: 10 Sep 2012 → 13 Sep 2012 |

### Other

Other | 13th European Conference on the Mathematics of Oil Recovery, ECMOR 2012 |
---|---|

Country | France |

City | Biarritz |

Period | 10/9/12 → 13/9/12 |

### Fingerprint

### Keywords

- Basin modelling
- Gradient methods
- Hessian
- History matching
- Optimizers
- Proxies
- Seismic inversion
- Uncertainty analysis

### ASJC Scopus subject areas

- Geophysics

### Cite this

*ECMOR 2012 - 13th European Conference on the Mathematics of Oil Recovery*European Association of Geoscientists and Engineers, EAGE.

**Neural networks and their derivatives for history matching and other seismic, basin and reservoir optimization problems.** / Bruyelle, J.; Guerillot, Dominique.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*ECMOR 2012 - 13th European Conference on the Mathematics of Oil Recovery.*European Association of Geoscientists and Engineers, EAGE, 13th European Conference on the Mathematics of Oil Recovery, ECMOR 2012, Biarritz, France, 10/9/12.

}

TY - GEN

T1 - Neural networks and their derivatives for history matching and other seismic, basin and reservoir optimization problems

AU - Bruyelle, J.

AU - Guerillot, Dominique

PY - 2012

Y1 - 2012

N2 - In geosciences, complex forward problems met in geophysics, petroleum system analysis and reservoir engineering problems often requires replacing these forward problems by proxies, and these proxies are used for optimizations problems. For instance, History Matching of observed field data requires a so large number of reservoir simulation runs (especially when using geostatistical geological models) that it is often impossible to use the full reservoir simulator. Therefore, several techniques have been proposed to mimic the reservoir simulations using proxies. Due to the use of experimental approach, most of authors propose to use second order polynomials. In this paper we demonstrate that: (1) Neural networks can also be second order polynomials. Therefore, the use of a neural network as a proxy is much more flexible and adaptable to the non linearity of the problem to be solved; (2) First order and second order derivatives of the neural network can be obtained providing gradients and hessian for optimizers. For inverse problems met in seismic inversion, well by well production data, optimal well locations, source rock generation, etc., most of the time, gradient methods are used for finding an optimal solution. The paper will describe how to calculate these gradients from a neural network built as a proxy. When needed, the hessian can also be obtained from the neural network approach. On a real case study, the ability of neural networks to reproduce complex phenomena (water-cuts, production rates. etc.) is showed. Comparisons with second polynomials (and kriging methods) will be done demonstrating the superiority of the neural network approach as soon as non linearity behaviors are present in the responses of the simulator. The gradients and the hessian of the neural network will be compared to those of the real response function.

AB - In geosciences, complex forward problems met in geophysics, petroleum system analysis and reservoir engineering problems often requires replacing these forward problems by proxies, and these proxies are used for optimizations problems. For instance, History Matching of observed field data requires a so large number of reservoir simulation runs (especially when using geostatistical geological models) that it is often impossible to use the full reservoir simulator. Therefore, several techniques have been proposed to mimic the reservoir simulations using proxies. Due to the use of experimental approach, most of authors propose to use second order polynomials. In this paper we demonstrate that: (1) Neural networks can also be second order polynomials. Therefore, the use of a neural network as a proxy is much more flexible and adaptable to the non linearity of the problem to be solved; (2) First order and second order derivatives of the neural network can be obtained providing gradients and hessian for optimizers. For inverse problems met in seismic inversion, well by well production data, optimal well locations, source rock generation, etc., most of the time, gradient methods are used for finding an optimal solution. The paper will describe how to calculate these gradients from a neural network built as a proxy. When needed, the hessian can also be obtained from the neural network approach. On a real case study, the ability of neural networks to reproduce complex phenomena (water-cuts, production rates. etc.) is showed. Comparisons with second polynomials (and kriging methods) will be done demonstrating the superiority of the neural network approach as soon as non linearity behaviors are present in the responses of the simulator. The gradients and the hessian of the neural network will be compared to those of the real response function.

KW - Basin modelling

KW - Gradient methods

KW - Hessian

KW - History matching

KW - Optimizers

KW - Proxies

KW - Seismic inversion

KW - Uncertainty analysis

UR - http://www.scopus.com/inward/record.url?scp=84896952512&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896952512&partnerID=8YFLogxK

M3 - Conference contribution

BT - ECMOR 2012 - 13th European Conference on the Mathematics of Oil Recovery

PB - European Association of Geoscientists and Engineers, EAGE

ER -