This study develops ensemble smoother–neural network (ES-NN) that combines an ensemble smoother (ES) with a convolutional autoencoder (CAE) to yield comparable performance at a lower computational cost to that of an ensemble smoother–multiple data assimilation (ES-MDA). The ES-NN updates reservoir facies models using CAE trained by importing initial and updated ensembles of ES as input and output of the CAE, respectively, which aims to learn the principle of assimilation of the ES. The trained CAE is recurrently applied in reservoir model calibration without additional forward simulation. The ES-NN yields satisfactory history matching results in terms of production profiles and facies distributions compared to ES and ES-MDA in two case studies. This comparison highlights the efficacy of ES-NN as a prospective data assimilation tool for history matching.
Bibliographical noteFunding Information:
This research was supported by the Korea Institute of Energy Technology Evaluation and Planning (KETEP) and the Ministry of Trade, Industry and Energy (MOTIE), Korea (No. 20172510102160 ) and also Korea Institute of Geoscience and Mineral Resources (KIGAM) ( GP2020-006 ). Baehyun Min was supported by the National Research Foundation of Korea (NRF) grants (No. 2018R1A6A1A08025520 and No. 2019R1C1C1002574 ). Kyungbook Lee was supported by Gas Hydrate R&D Organization (GHDO), MOTIE , and KIGAM ( GP2020-004 ).
© 2020 Elsevier B.V.
- Convolutional autoencoder
- Ensemble smoother–multiple data assimilation
- Ensemble smoother–neural network
- History matching