Affiliation:
1. University of Portharcourt
2. CypherCrescent Limited
3. Stanford
Abstract
Abstract
Subsurface numerical models take a significant time to build and run. For this reason, the energy industry has been looking towards proxy models that could reduce model computational time. With the advancement of artificial neural network algorithms, building proxy models has become more efficient, and has enabled quick forecasting and quick reservoir management decision-making.
In this study, we used a geothermal reservoir to evaluate the suitability of two deep learning algorithms, feed forward neural network and convolutional neural network, for proxy modeling. We used metrics such as the mean square error, losses, number of parameters for the model, and time to run, to compare the two deep learning algorithms.
From our study, we determined that the convolutional neural network resulted in less error than the feed forward network and used less hyperparameters. However, the feed forward network was significantly faster than the convolutional neural network. The process of building the proxy model shows how a similar approach can be followed for oil and gas reservoir modeling and demonstrates the feasibility of neural networks in subsurface reservoir modeling and forecasting.
Reference16 articles.
1. Impact of Data Normalization on Stock Index Forecasting;Nayak;International Journal of Computer Information Systems and Industrial Management Applications.,2014
2. Bahr, B. A., Adewale, G., Shadi, W.H., 2019. Current trends and future developments in (Bio-) Membranes. https://doi.org/10.1016/C2016-0-02118-6.
3. ReLU Deep Neural Networks and Linear Finite Elements;Juncai;J. comput. Math.,2018
4. A scalable algorithm for the optimization of neural network architectures;Massimiliano,2021
5. Neural Networks for Systems Identification;Reynold Chu;IEEE controls system magazines.,2018
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献