当前位置: X-MOL 学术Comput. Geosci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Conditioning surface-based geological models to well data using artificial neural networks
Computational Geosciences ( IF 2.1 ) Pub Date : 2021-09-17 , DOI: 10.1007/s10596-021-10088-5
Zainab Titus 1 , Claire Heaney 1 , Carl Jacquemyn 1 , Pablo Salinas 1 , MD Jackson 1 , Christopher Pain 1
Affiliation  

Surface-based modelling provides a computationally efficient approach for generating geometrically realistic representations of heterogeneity in reservoir models. However, conditioning Surface-Based Geological Models (SBGMs) to well data can be challenging because it is an ill-posed inverse problem with spatially distributed parameters. To aid fast and efficient conditioning, we use here SBGMs that model geometries using parametric, grid-free surfaces that require few parameters to represent even realistic geological architectures. A neural network is trained to learn the underlying process of generating SBGMs by learning the relationship between the parametrized SBGM inputs and the resulting facies identified at well locations. To condition the SBGM to these observed data, inverse modelling of the SBGM inputs is achieved by replacing the forward model with the pre-trained neural network and optimizing the network inputs using the back-propagation technique applied in training the neural network. An analysis of the uncertainties associated with the conditioned realisations demonstrates the applicability of the approach for evaluating spatial variations in geological heterogeneity away from control data in reservoir modelling. This approach for generating geologically plausible models that are calibrated with observed well data could also be extended to other geological modelling techniques such as object- and process-based modelling.



中文翻译:

使用人工神经网络将基于地表的地质模型调节为井数据

基于表面的建模为在储层模型中生成几何上真实的非均质性表示提供了一种计算有效的方法。然而,将基于地表的地质模型 (SBGM) 调整为井数据可能具有挑战性,因为它是一个具有空间分布参数的不适定逆问题。为了帮助快速有效地调节,我们在这里使用 SBGM,它使用参数化、无网格的表面对几何进行建模,这些表面需要很少的参数来表示甚至真实的地质结构。通过学习参数化的 SBGM 输入与在井位识别的结果相之间的关系,训练神经网络来学习生成 SBGM 的基本过程。为了使 SBGM 适应这些观察到的数据,SBGM 输入的逆向建模是通过用预训练的神经网络替换前向模型并使用在训练神经网络中应用的反向传播技术优化网络输入来实现的。对与条件实现相关的不确定性的分析证明了该方法用于评估远离储层建模中控制数据的地质非均质性空间变化的适用性。这种生成用观测井数据校准的合理地质模型的方法也可以扩展到其他地质建模技术,例如基于对象和过程的建模。对与条件实现相关的不确定性的分析证明了该方法用于评估远离储层建模中控制数据的地质非均质性空间变化的适用性。这种生成用观测井数据校准的合理地质模型的方法也可以扩展到其他地质建模技术,例如基于对象和过程的建模。对与条件实现相关的不确定性的分析证明了该方法用于评估远离储层建模中控制数据的地质非均质性空间变化的适用性。这种生成用观测井数据校准的合理地质模型的方法也可以扩展到其他地质建模技术,例如基于对象和过程的建模。

更新日期:2021-09-17
down
wechat
bug