A physics-constrained long-term production prediction method for multiple fractured wells using deep learning
Authors:
- Xuechen LiXLXuechen Li
- Xinfang MaXMXinfang Ma
- Fengchao XiaoFXFengchao Xiao
- Cong XiaoCXCong Xiao
- Fei WangFWFei Wang
- Shicheng ZhangSZShicheng Zhang
- 5 July 2022
- journal article
- research article
- Published by Elsevier in Journal of Petroleum Science and Engineering
- Vol. 217
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (51974332)
- Science Foundation of China University of Petroleum, Beijing
This publication has 38 references indexed in Scilit:
- Research on the LSTM Mongolian and Chinese machine translation based on morpheme encodingNeural Computing and Applications, 2018
- Improving direct physical properties prediction of heterogeneous materials from imaging data via convolutional neural network and a morphology-aware generative modelComputational Materials Science, 2018
- Experimental Analysis of Hydraulic Fracture Growth and Acoustic Emission Response in a Layered FormationRock Mechanics and Rock Engineering, 2017
- Analytical model for production performance analysis of multi-fractured horizontal well in tight oil reservoirsJournal of Petroleum Science and Engineering, 2017
- Research on transient flow theory of a multiple fractured horizontal well in a composite shale gas reservoir based on the finite-element methodJournal of Natural Gas Science and Engineering, 2016
- Effect of Nanoscale Pore Confinement on Multi-Component Phase Equilibrium2016
- Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather predictionNeural Networks, 2006
- Long Short-Term MemoryNeural Computation, 1997
- Some advances in non‐linear and adaptive modelling in time‐seriesJournal of Forecasting, 1994
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982