Recently, Zhang Kai's team has made significant progress in the field of automatic history matching in reservoirs. Their research results have been published in the journal Computers & Geosciences, in a paper titled "An offline data-driven dual-surrogate framework considering prediction error for history matching"。
Innovation：We propose a novel offline data-driven dual-surrogate framework specifically designed to address surrogate prediction errors in the history matching process. This framework introduces two surrogate models: one for predicting reservoir production data and the other for learning and correcting the prediction errors of the former. This approach significantly enhances the accuracy of history matching. Specifically, the framework employs a recurrent neural network to handle the time-series characteristics of production data, combined with a fully convolutional neural network to capture the spatial correlation of multivariate prediction errors. This effectively reduces the impact of prediction errors on history matching results. Additionally, we have proposed an enhanced error model that incorporates prediction errors into the objective function, further improving the robustness of the surrogate models. Validation results demonstrate the effectiveness of this method in history matching.
Abstract：High computer power has long been a critical ingredient that affects the effectiveness and efficiency of history matching. Data-driven surrogate modeling as an efficient strategy can accelerate the history-matching process by constructing machine learning-based models with high computing speed but reduced accuracy. However, the applicability of surrogate models for different history-matching problems is uncertain due to the influence of data quality and quantity, model architectures, and hyperparameters. To overcome this issue, an offline data-driven dual-surrogate framework (ODDF) that considers the prediction error of surrogate models for history matching is proposed, where one surrogate model predicts the production data of reservoirs and the other one learns the prediction error of the former surrogate. The first surrogate model considers the time-series characteristics of production data using a recurrent neural network, while the second surrogate model regards the two-dimensional spatial correlation characteristics of multivariate prediction error using a fully convolutional neural network. Furthermore, an enhanced error model is applied to incorporate the prediction error into the objective function to reduce the influence of the prediction error on inversion results. Based on this hybrid framework, one can improve the prediction accuracy of surrogate models in history matching when the architectures or hyperparameters of surrogate models are not optimal. Additionally, one can obtain satisfactory results for history matching and uncertainty quantification based on surrogate modeling. The proposed framework is validated on the history matching of two- and three-dimensional reservoir models. The results show that the proposed method is robust in constructing the surrogate models and predicting the production data of reservoirs, which improves the efficiency and reliability of history matching.
Computers & Geosciences publishes high impact, original research at the interface between Computer Sciences and Geosciences. Its 2023 impact factor is 4.2, CiteScore is 9.3, and it is categorized as Q1 in the 2023 JCR rankings and in the second tier of the Chinese Academy of Sciences' engineering and technology category.
Paper link:
https://doi.org/10.1016/j.cageo.2024.105680
Citation:
Zhang Jinding, Zhang Kai, Zhang Liming, Zhou Wensheng, Liu Chen, Liu Piyang, Fu Wenhao, Chen Xu, Bian Ziwei, Yang Yongfei, Yao Jun. An offline data-driven dual-surrogate framework considering prediction error for history matching[J]. Computers & Geosciences, 2024, 192: 105680. DOI:10.1016/j.cageo.2024.105680.
