4.6 Article

Data-driven production optimization using particle swarm algorithm based on the ensemble-learning proxy model

Related references

Note: Only part of the references are listed.
Article Energy & Fuels

Robust hybrid machine learning algorithms for gas flow rates prediction through wellhead chokes in gas condensate fields

Abouzar Rajabi Behesht Abad et al.

Summary: Condensate reservoirs present unique challenges in the oil and gas industry, and machine learning methods show promise in predicting gas flow rates, with the MELM-PSO model demonstrating the highest accuracy.
Article Energy & Fuels

Knowledge-based machine learning techniques for accurate prediction of CO2 storage performance in underground saline aquifers

Hung Vo Thanh et al.

Summary: In this study, machine learning models were developed to predict the efficiency of carbon dioxide sequestration in saline formations, and the XGBoost model achieved the highest accuracy. This research provides a valuable and viable template for predicting the CO2 trapping index in other saline formations and can be used as a tool for assessing the uncertainty of carbon storage projects.

APPLIED ENERGY (2022)

Article Energy & Fuels

Evaluation of hydraulic fracturing effect on coalbed methane reservoir based on deep learning method considering physical constraints

Hongqing Song et al.

Summary: This study establishes a deep learning-based fracturing effect evaluation model that considers physical constraints, which can better guide deep learning and predict fracture half-length and permeability.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

Article Energy & Fuels

Rapid evaluation and optimization of carbon dioxide-enhanced oil recovery using reduced-physics proxy models

Watheq J. Al-Mudhafar et al.

Summary: This paper proposes a simplified physics surrogate model constructed using experimental design and machine learning, which is used to evaluate and optimize the CO2-assisted gravity drainage process. By manipulating operational decision parameters, the goal of increasing oil production in the reservoir is achieved. Additionally, four machine learning algorithms were built as proxy surrogates, and the most accurate metamodel was selected through cross-validation.

ENERGY SCIENCE & ENGINEERING (2022)

Article Energy & Fuels

A liquid loading prediction method of gas pipeline based on machine learning

Bing-Yuan Hong et al.

Summary: This paper aims to establish a liquid loading prediction model for natural gas pipeline using machine learning, which can accurately predict the liquid loading and provide technical support for gas pipeline flow assurance. The data-driven model improves calculation efficiency and reduces workload, and is based on a large number of simulations and various working conditions.

PETROLEUM SCIENCE (2022)

Article Energy & Fuels

Predicting gas-bearing distribution using DNN based on multi-component seismic data: Quality evaluation using structural and fracture factors

Kai Zhang et al.

Summary: This study presents a DNN-based method for identifying gas-bearing strata in tight sandstone. By constraining the strong nonlinear relationships between multi-component composite seismic attributes and gas-bearing reservoirs, the DNN can be used to identify and predict gas-bearing strata, extrapolating the distribution of the gas reservoir and predicting favorable exploration areas.

PETROLEUM SCIENCE (2022)

Article Geosciences, Multidisciplinary

Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization

Wengang Zhang et al.

Summary: This study applies XGBoost and RF methods to predict the USS of soft clays, showing that these approaches outperform traditional methods. Bayesian optimization is used to determine model hyperparameters, leading to more accurate and robust models.

GEOSCIENCE FRONTIERS (2021)

Article Engineering, Petroleum

Multifidelity Genetic Transfer: An Efficient Framework for Production Optimization

Faliang Yin et al.

Summary: This paper presents a novel production optimization framework based on genetic transfer learning to accelerate convergence and improve the quality of optimal solution. By combining results from high- and low-fidelity tasks, a multifidelity optimization model is established, and the concept of relative fidelity is introduced. The framework includes multitasking and sequential transfer modes to balance computing resources for tasks with different fidelity levels.

SPE JOURNAL (2021)

Article Energy & Fuels

A deep-learning-based prediction method of the estimated ultimate recovery (EUR) of shale gas wells

Yu-Yang Liu et al.

Summary: This paper develops a deep-learning algorithm for predicting the EUR of shale gas wells based on geological, hydraulic fracturing, and production data. The approach shows high accuracy and is influenced by various factors such as input parameters and network structure. The proposed method can be extended to other shale fields with similar technical processes.

PETROLEUM SCIENCE (2021)

Article Energy & Fuels

Support vector regression modeling in recursive just-in-time learning framework for adaptive soft sensing of naphtha boiling point in crude distillation unit

Venkata S. Vijayan et al.

Summary: The development of non-linear adaptive soft sensors for prediction of naphtha initial boiling point (IBP) and end boiling point (EBP) in crude distillation unit was investigated in this study. The results showed that the JITL model based on support vector regression with ISDA local model yielded the best prediction accuracy. The study also examined the impact of dataset size on model prediction and computation time.

PETROLEUM SCIENCE (2021)

Article Energy & Fuels

Enhanced oil recovery by nanoparticles flooding: From numerical modeling improvement to machine learning prediction

Budoor Alwated et al.

Summary: This study focuses on predicting nanoparticles transport in porous media using machine learning techniques and generating artificial datasets to compensate for the lack of experimental data. The decision tree model shows the best performance in one dataset, while the random forest model has the lowest root mean squared error and highest R-squared values in the rest of the datasets, including the combined dataset.

ADVANCES IN GEO-ENERGY RESEARCH (2021)

Article Computer Science, Information Systems

Random Forest-Bayesian Optimization for Product Quality Prediction With Large-Scale Dimensions in Process Industrial Cyber-Physical Systems

Tianteng Wang et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

Article Energy & Fuels

Robust Optimization of Cyclic CO2 flooding through the Gas-Assisted Gravity Drainage process under geological uncertainties

Watheq J. Al-Mudhafar et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2018)

Article Engineering, Petroleum

Robust Life-Cycle Production Optimization With a Support-Vector-Regression Proxy

Zhenyu Guo et al.

SPE JOURNAL (2018)

Article Engineering, Multidisciplinary

A Stochastic Simplex Approximate Gradient (StoSAG) for optimization under uncertainty

Rahul Rahul-Mark Fonseca et al.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING (2017)

Article Statistics & Probability

A random forest guided tour

Gerard Biau et al.

Article Energy & Fuels

Optimization of integrated production system using advanced proxy based models: A new approach

Shandad Ghassemzadeh et al.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2016)

Article Statistics & Probability

A random forest guided tour

Gerard Biau et al.

Review Multidisciplinary Sciences

Probabilistic machine learning and artificial intelligence

Zoubin Ghahramani

NATURE (2015)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Computer Science, Artificial Intelligence

Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation

Juan Diego Rodriguez et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2010)

Article Energy & Fuels

Ensemble-Based Closed-Loop Optimization Applied to Brugge Field

Yan Chen et al.

SPE RESERVOIR EVALUATION & ENGINEERING (2010)

Article Computer Science, Interdisciplinary Applications

The weighted sum method for multi-objective optimization: new insights

R. Timothy Marler et al.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION (2010)

Article Statistics & Probability

Variable Importance Assessment in Regression: Linear Regression versus Random Forest

Ulrike Groemping

AMERICAN STATISTICIAN (2009)

Article Engineering, Petroleum

Production Optimization in Closed-Loop Reservoir Management

Chunhong Wang et al.

SPE JOURNAL (2009)

Article Biochemical Research Methods

Bias in random forest variable importance measures: Illustrations, sources and a solution

Carolin Strobl et al.

BMC BIOINFORMATICS (2007)

Article Energy & Fuels

A capacitance model to infer interwell connectivity from production- and injection-rate fluctuations

Ali A. Yousef et al.

SPE RESERVOIR EVALUATION & ENGINEERING (2006)

Article Operations Research & Management Science

Some variants of the controlled random search algorithm for global optimization

P. Kaelo et al.

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS (2006)

Review Physics, Multidisciplinary

Power laws, Pareto distributions and Zipf's law

MEJ Newman

CONTEMPORARY PHYSICS (2005)

Review Computer Science, Theory & Methods

A tutorial on support vector regression

AJ Smola et al.

STATISTICS AND COMPUTING (2004)

Article Computer Science, Artificial Intelligence

Handling multiple objectives with particle swarm optimization

CAC Coello et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2004)

Article Energy & Fuels

Inferring interwell connectivity only from well-rate fluctuations in waterfloods

A Albertoni et al.

SPE RESERVOIR EVALUATION & ENGINEERING (2003)

Article Computer Science, Interdisciplinary Applications

Stochastic gradient boosting

JH Friedman

COMPUTATIONAL STATISTICS & DATA ANALYSIS (2002)

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)