☆ 3.8 Article

Predicting CO2-EOR and storage in low-permeability reservoirs with deep learning-based surrogate flow models

GEOENERGY SCIENCE AND ENGINEERING (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Energy & Fuels

Carbon Circular Utilization and Partially Geological Sequestration: Potentialities, Challenges, and Trends

Zhengmeng Hou et al.

Summary: This paper proposes six priorities for China to achieve its dual carbon strategy, and analyzes the challenges and potential of conventional carbon utilization, carbon capture utilization, and carbon capture utilization storage. Based on the current development trend, CCCUS technology, namely biomethanation, is proposed as a solution for China's renewable energy utilization and storage, as well as the carbon circular economy.

ENERGIES (2023)

添加到收藏夹

Article Energy & Fuels

A novel deep learning-based automatic search workflow for CO2 sequestration surrogate flow models

Jianchun Xu et al.

Summary: Numerical simulation can improve subsurface resource utilization's efficiency and economic benefits, but it requires extensive computational demands and time due to high-dimensional nonlinearity, heterogeneity, and coupling of multiple physical processes. Surrogate models can accelerate the establishment of complex models without sacrificing accuracy, but their development usually requires extensive human intervention and trial-and-error processes. This study proposes an automated workflow based on deep learning called Surrogate Flow Model Search (SFMS) to develop high-quality surrogate models without extensive deep-learning expertise.

FUEL (2023)

添加到收藏夹

Article Energy & Fuels

Surrogate-assisted inversion for large-scale history matching: Comparative study between projection-based reduced-order modeling and deep neural network

Cong Xiao et al.

Summary: History matching plays a key role in improving geological characterization and reducing reservoir model prediction uncertainty. Computational cost is a major limitation, but surrogate models such as deep neural networks are used to reduce demands efficiently. The use of stochastic gradient optimizers and the comparison with subdomain POD-TPWL approach show great potential in solving large-scale history matching problems.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

添加到收藏夹

Article Energy & Fuels

Stochastic simplex approximation gradient for reservoir production optimization: Algorithm testing and parameter analysis

Jianchun Xu et al.

Summary: The study evaluated the impact of key parameters in the StoSAG optimization process, including ensemble size, step size, cut number, perturbation size, and initial position. Results showed that larger ensemble size and increased search step size were favorable for optimization results, but a large step size needed to match a larger cut number. Moreover, the increase of cut number was beneficial for local searchability but also increased the risk of falling into local optima. Random initial position was found to be helpful in finding the global optimal point.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

添加到收藏夹

Article Energy & Fuels

A physics-constrained deep learning model for simulating multiphase flow in 3D heterogeneous porous media

Bicheng Yan et al.

Summary: In this study, an efficient physics-constrained deep learning model is developed for solving multiphase flow in 3D porous media. The model utilizes convolutional neural networks and continuity-based smoothing to accurately predict the temporal-spatial evolution of flow responses and state variables. The decomposition of the 3D domain into 2D images reduces training cost and improves efficiency. A surrogate model is also constructed for well flow rate prediction.

FUEL (2022)

添加到收藏夹

Article Energy & Fuels

Fast evaluation of pressure and saturation predictions with a deep learning surrogate flow model

Eduardo Maldonado-Cruz et al.

Summary: Numerical models are crucial for forecasting subsurface fluid flow response to support optimal decision-making in developing subsurface resources. Though current methods focus on prediction accuracy and minimizing error, significant uncertainty necessitates considering the entire uncertainty distribution. New workflow integrates machine learning-based surrogate flow models to predict subsurface responses efficiently and accurately.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

添加到收藏夹

Article Energy & Fuels

Toward a Carbon-Neutral State: A Carbon-Energy-Water Nexus Perspective of China's Coal Power Industry

Yachen Xie et al.

Summary: Carbon neutrality is an important goal for the Chinese government, as coal is the dominant energy source and contributes to high carbon emissions. This study develops a tool to evaluate the trade-offs in China's coal power industry, considering the carbon-energy-water nexus and financial profits. The research finds that economic losses from coal reduction can be compensated by carbon trading, and financial profits in the coal power industry are not negatively correlated to carbon emissions.

ENERGIES (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

GSTools v1.3: a toolbox for geostatistical modelling in Python

Sebastian Mueller et al.

Summary: Geostatistics is a subfield of statistics that deals with spatial correlations in applications such as earth sciences. This article introduces GSTools, a user-friendly software suite based on Python that can solve various geostatistical problems, including random field generation, kriging, and variogram estimation. The capabilities of this software suite are demonstrated through example applications.

GEOSCIENTIFIC MODEL DEVELOPMENT (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Simulation on Effects of Injection Parameters on CO2 Enhanced Gas Recovery in a Heterogeneous Natural Gas Reservoir

Ling Fan et al.

Summary: The study found that perforating the CO2 injection well at a lower position can achieve larger natural gas recovery and CO2 storage simultaneously, with the optimal injection rate being 137.29 m(3).d(-1). The changes in injection pressure and temperature have minimal impact on the comprehensive benefits of natural gas recovery and CO2 storage.

ADVANCED THEORY AND SIMULATIONS (2021)

添加到收藏夹

Article Engineering, Multidisciplinary

Efficient uncertainty quantification for dynamic subsurface flow with surrogate by Theory-guided Neural Network

Nanzhe Wang et al.

Summary: This study proposes a methodology for efficient uncertainty quantification in dynamic subsurface flow using a surrogate constructed by Theory-guided Neural Network (TgNN), which is specially designed for problems with stochastic parameters. The neural network is trained with available simulation data and theory guidance, and can predict solutions of subsurface flow problems with new stochastic parameters. The TgNN surrogate significantly improves the efficiency of uncertainty quantification tasks compared to simulation based implementation.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2021)

添加到收藏夹

Article Biochemical Research Methods

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

Fabian Isensee et al.

Summary: nnU-Net is a deep learning-based image segmentation method that automatically configures itself for diverse biological and medical image segmentation tasks, offering state-of-the-art performance as an out-of-the-box tool.

NATURE METHODS (2021)

添加到收藏夹

Article Energy & Fuels

A framework for predicting the production performance of unconventional resources using deep learning

Sen Wang et al.

Summary: Developed deep belief network (DBN) models for predicting the production performance of unconventional wells effectively and accurately, showing higher prediction accuracy and generalization ability than traditional machine-learning techniques. Optimized fracturing design using the trained DBN model yielded outstanding results, demonstrating its potential as a powerful tool in optimizing fracturing designs.

APPLIED ENERGY (2021)

添加到收藏夹

Review Computer Science, Theory & Methods

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Laith Alzubaidi et al.

Summary: Deep learning has become the gold standard in the machine learning community, widely used in various domains and capable of learning massive data. Through a comprehensive survey, a better understanding of the most important aspects of deep learning is provided.

JOURNAL OF BIG DATA (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A survey of the recent architectures of deep convolutional neural networks

Asifullah Khan et al.

ARTIFICIAL INTELLIGENCE REVIEW (2020)

添加到收藏夹

Article Environmental Sciences

Physics-Informed Deep Neural Networks for Learning Parameters and Constitutive Relationships in Subsurface Flow Problems

A. M. Tartakovsky et al.

WATER RESOURCES RESEARCH (2020)

添加到收藏夹

Article Water Resources

Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport

QiZhi He et al.

ADVANCES IN WATER RESOURCES (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems

Meng Tang et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2020)

添加到收藏夹

Article Energy & Fuels

Predicting field production rates for waterflooding using a machine learning-based proxy model

Zhi Zhong et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2020)

添加到收藏夹

Article Energy & Fuels

Stochastic Simplex Approximate Gradient for Robust Life-Cycle Production Optimization: Applied to Brugge Field

Bailian Chen et al.

JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME (2019)

添加到收藏夹

Article Environmental Sciences

Predicting CO2 Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network

Zhi Zhong et al.

WATER RESOURCES RESEARCH (2019)

添加到收藏夹

Review Geosciences, Multidisciplinary

A review of proxy modeling applications in numerical reservoir simulation

Ahmed Khalil Jaber et al.

ARABIAN JOURNAL OF GEOSCIENCES (2019)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Non-intrusive subdomain POD-TPWL for reservoir history matching

Cong Xiao et al.

COMPUTATIONAL GEOSCIENCES (2019)

添加到收藏夹

Article Environmental Sciences

Deep Convolutional Encoder-Decoder Networks for Uncertainty Quantification of Dynamic Multiphase Flow in Heterogeneous Media

Shaoxing Mo et al.

WATER RESOURCES RESEARCH (2019)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification

Yinhao Zhu et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2018)

添加到收藏夹

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Gaussian Processes for history-matching: application to an unconventional gas reservoir

Hamidreza Hamdi et al.

COMPUTATIONAL GEOSCIENCES (2017)

添加到收藏夹

Article Water Resources

Surrogate accelerated sampling of reservoir models with complex structures using sparse polynomial chaos expansion

Hamid Bazargan et al.

ADVANCES IN WATER RESOURCES (2015)

添加到收藏夹

Article Energy & Fuels

Shale gas and non-aqueous fracturing fluids: Opportunities and challenges for supercritical CO2

Richard S. Middleton et al.

APPLIED ENERGY (2015)

添加到收藏夹

Article Energy & Fuels

Application of artificial neural networks in a history matching process

Luis Augusto Nagasaki Costa et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2014)

添加到收藏夹

Article Energy & Fuels

Unconventional hydrocarbon resources in China and the prospect of exploration and development

Jia Chengzao et al.

PETROLEUM EXPLORATION AND DEVELOPMENT (2012)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Reduced-order optimal control of water flooding using proper orthogonal decomposition

Jorn F. M. van Doren et al.

COMPUTATIONAL GEOSCIENCES (2006)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Image quality assessment: From error visibility to structural similarity

Z Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2004)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.