☆ 3.8 Article

Integrating drilling parameters and machine learning tools to improve real-time porosity prediction of multi-zone reservoirs. Case study: Rhourd Chegga oilfield, Algeria

GEOENERGY SCIENCE AND ENGINEERING (2023)

Related references

Note: Only part of the references are listed.

Article Thermodynamics

Application of machine learning to predict CO2 trapping performance in deep saline aquifers

Hung Vo Thanh et al.

Summary: This paper investigates the prediction of CO2 trapping efficiency in deep saline formations using machine learning models including Gaussian process regression (GPR), support vector machine (SVM), and random forest (RF). The results highlight the effectiveness of the GPR model in accurately estimating CO2 trapping performance and achieving good agreement with field observations.

ENERGY (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Quantification of reservoir rock properties (Porosity, Permeability and Vshale) in the reservoir rock units of South Lake Albert Basin, Albertine Rift, Western Uganda

M. W. Tumushabe et al.

Summary: The study focused on interpreting 3D seismic and wireline log datasets to evaluate reservoir rock properties in the South Lake Albert Basin (SLAB). Results showed that the reservoir rock properties varied at short intervals with changes in lithology, influenced by climatic conditions during the sedimentation process. Additionally, sediment compartmentalization and intercalation were found to impact the reservoir rock properties.

JOURNAL OF AFRICAN EARTH SCIENCES (2022)

Add to Collection

Article Energy & Fuels

Chain-based machine learning for full PVT data prediction

Kassem Ghorayeb et al.

Summary: This paper presents various algorithms developed to accurately predict a complete set of black oil and compositional properties within a PVT database. The methodology involves predicting properties in series and employing data clustering to enhance prediction accuracy. The algorithms have been tested using a large data set from onshore and offshore fields and reservoirs in Abu Dhabi.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

Add to Collection

Article Nuclear Science & Technology

Improved formation density measurement using controllable D-D neutron source and its lithological correction for porosity prediction

Li Zhang et al.

Summary: This study presents an improved method using a D-D neutron source to measure formation density and removes the lithological effect on the measured density. Through Monte Carlo simulations and experimental validation, the accuracy and feasibility of this method are demonstrated.

NUCLEAR SCIENCE AND TECHNIQUES (2022)

Add to Collection

Review Geochemistry & Geophysics

A review of machine learning in geochemistry and cosmochemistry: Method improvements and applications

Yuyang He et al.

Summary: The article introduces the applications of machine learning in geochemistry and cosmochemistry, including rock and sediment identification, digital mapping, water and soil quality prediction, and deep space exploration. Through improvements in research methods such as spectroscopy interpretation, numerical modeling, and molecular machine learning, there are vast opportunities to implement artificial intelligence and develop databases in these fields, while also promoting communication between geochemists/cosmochemists and data scientists.

APPLIED GEOCHEMISTRY (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Research on lithology identification method based on mechanical specific energy principle and machine learning theory

Haibo Liang et al.

Summary: Lithology identification plays a crucial role in petroleum drilling engineering to ensure smooth operation. Traditional methods relying on human experience are no longer efficient, requiring the development of intelligent recognition methods. The lithology identification model based on the principle of mechanical specific energy and simulated annealing optimization support vector machine algorithm can accurately predict lithology with a high accuracy rate, providing new technical support for oil drilling formation analysis.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Add to Collection

Article Energy & Fuels

Neural Network based Mechanical Earth Modelling (MEM): A case study in Hassi Messaoud Field, Algeria

Ala Eddine Aoun et al.

Summary: Accurate estimation of in-situ stresses is crucial for hydraulic fracturing design in the Hassi Messaoud Field (HMD) in Algeria. By constructing a Mechanical Earth Model (MEM) and utilizing Artificial Neural Networks (ANN), the study aims to improve operational efficiency in hydraulic fracturing by accurately estimating stress states.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Real-time porosity prediction using gas-while-drilling data and machine learning with reservoir associated gas: Case study for Hassi Messaoud field, Algeria

Ouafi Ameur-Zaimeche et al.

Summary: A novel inverse intelligent model has been developed to predict rock porosity in real time using gas-while-drilling data. The extreme learning machine (ELM) model achieved the highest accuracy among the evaluated machine learning models. This method offers significant time and cost savings, while providing petroleum engineers with real-time decision-making support.

MARINE AND PETROLEUM GEOLOGY (2022)

Add to Collection

Article Energy & Fuels

Workflow to predict wellhead choke performance during multiphase flow using machine learning

Sulaiman A. Alarifi

Summary: Multiphase flow metering plays a crucial role in monitoring the production performance of oil and gas reservoirs. The current practice involves monthly production rate tests for connected wells. This study aims to develop a machine learning model that outperforms existing correlations in predicting the flow rate of critical and subcritical multiphase flow through the wellhead choke.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

Add to Collection

Article

Review of application of artificial intelligence techniques in petroleum operations

Saeed Bahaloo et al.

Petroleum Research (2022)

Add to Collection

Article

Machine learning models for generating the drilled porosity log for composite formations

Hany Gamal et al.

Arabian Journal of Geosciences (2021)

Add to Collection

Article Energy & Fuels

Intelligent Detection of Small Faults Using a Support Vector Machine

Aiping Zeng et al.

Summary: This paper proposes an intelligent small fault identification method combining VMD and SVM, which can effectively reduce random noise in seismic data and extract seismic attributes related to small faults. Analysis of the SVM algorithm and fault forward model proves the feasibility of the method, demonstrating higher prediction accuracy than traditional methods and providing important guidance for coal mine production.

ENERGIES (2021)

Add to Collection

Article Energy & Fuels

Training-while-drilling approach to inclination prediction in directional drilling utilizing recurrent neural networks

Andrzej T. Tunkiel et al.

Summary: The adoption of machine learning in drilling is hindered by the need to train models on specific well data. To address this issue, a continuous learning method using neural networks to model dynamic behavior is proposed, presenting promising results in accurately predicting drilling data while drilling is ongoing.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2021)

Add to Collection

Article

Real-time static Poisson’s ratio prediction of vertical complex lithology from drilling parameters using artificial intelligence models

Ashraf Ahmed et al.

Arabian Journal of Geosciences (2021)

Add to Collection

Article Energy & Fuels

Rock Strength Prediction in Real-Time While Drilling Employing Random Forest and Functional Network Techniques

Hany Gamal et al.

Summary: This study utilized artificial intelligence to predict rock strength in real-time, with a PCA-based random forest model outperforming a functional network model in terms of accuracy. The developed models provide an accurate estimation of UCS from drilling data, improving efficiency and well stability.

JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME (2021)

Add to Collection

Article Energy & Fuels

A new data-driven predictor, PSO-XGBoost, used for permeability of tight sandstone reservoirs: A case study of member of chang 4+5, western Jiyuan Oilfield, Ordos Basin

Yufeng Gu et al.

Summary: Permeability is a critical parameter for geological work, and traditional physical models may not be efficient for predicting permeability in unconventional reservoirs. This study proposes using PSO-XGBoost as a better fitting model for permeability prediction, which shows stronger prediction capability compared to other validated models, suggesting promising application prospects in logging interpretation studies.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2021)

Add to Collection

Article Automation & Control Systems

A novel rate of penetration prediction model with identified condition for the complex geological drilling process

Yang Zhou et al.

Summary: The paper presents an online hybrid prediction model based on drilling data for high-accuracy prediction of rate of penetration (ROP). The method utilizes mutual information analysis, combines K-nearest neighbor algorithm and dynamic time warping, establishes ROP prediction model with support vector regression method, and obtains hyperparameters using hybrid bat algorithm and nondominated sorting genetic algorithm II.

JOURNAL OF PROCESS CONTROL (2021)

Add to Collection

Article Chemistry, Multidisciplinary

Data-Driven Modeling Approach for Pore Pressure Gradient Prediction while Drilling from Drilling Parameters

Ahmed Abdelaal et al.

Summary: This study developed three models using support vector machines, functional networks, and random forest to predict real-time pore pressure gradient using mechanical and hydraulic drilling parameters. The models exhibited high accuracy in both training and testing, with the random forest model outperforming the others.

ACS OMEGA (2021)

Add to Collection

Article Construction & Building Technology

Hybrid machine learning for pullback force forecasting during horizontal directional drilling

Hongfang Lu et al.

Summary: This study introduces a hybrid machine learning model that combines NSGA-II and SVM to predict the pullback force in HDD construction accurately, with validation in practical projects.

AUTOMATION IN CONSTRUCTION (2021)

Add to Collection

Article Energy & Fuels

Application of machine learning models for real-time prediction of the formation lithology and tops from the drilling parameters

Ahmed Abdulhamid Mahmoud et al.

Summary: This study investigated the use of three machine learning models to predict lithology changes and formation tops in real-time while drilling. The optimized ANN model showed high accuracy in predicting different formations, outperforming both ANFIS and FNN models. The ANN model achieved an accuracy of over 98.1% for both training and testing data.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2021)

Add to Collection

Article Geochemistry & Geophysics

Real-Time Prediction of Acoustic Velocities While Drilling Vertical Complex Lithology Using AI Technique

Ahmed Alsaihati et al.

Summary: This study introduced two data-driven models, artificial neural network (ANN) and random forest (RF), to estimate sonic velocities across different formations. The results showed that the RF outperformed the optimized ANN in estimating the velocities, with lower average absolute percentage error and higher correlation coefficients.

PETROPHYSICS (2021)

Add to Collection

Article Mathematical & Computational Biology

Intelligent Prediction for Rock Porosity While Drilling Complex Lithology in Real Time

Hany Gamal et al.

Summary: This paper aims to predict rock porosity in real time while drilling complex lithology using machine learning techniques. Two intelligent models (RF and DT) were developed and validated, with RF showing stronger prediction capability than DT. The models' performance was evaluated using multiple performance indices, confirming their high prediction performance.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2021)

Add to Collection

Article Engineering, Petroleum

Application of machine learning algorithms to predict permeability in tight sandstone formations

Tomasz Topor

Summary: The study utilizes machine learning algorithms to predict permeability of samples from tight sandstone formations under confining stress conditions. Both multiple linear regression (MLR) and random forests (RF) algorithms were used, showing that RF was more accurate and had better performance due to increased number of predictors, including depth factors. Porosity was found to be the most influential feature in the models' performance. The workflow will be further applied in more complex examples to predict spatial petrophysical features using various machine learning algorithms.

NAFTA-GAZ (2021)

Add to Collection

Article Computer Science, Information Systems

Deep Learning and Time-Series Analysis for the Early Detection of Lost Circulation Incidents During Drilling Operations

Mohammad Aljubran et al.

Summary: Drilling operations involve breaking rock to deepen a wellbore for oil or gas extraction, using a drilling fluid to remove rock cuttings and maintain pressure. Lost circulation incidents are a major cause of non-productive time and can lead to hazardous drilling phenomena. Machine learning algorithms have been shown to be effective in early detection of these incidents.

IEEE ACCESS (2021)

Add to Collection

Article Environmental Sciences

Artificial neural network model for reservoir petrophysical properties: porosity, permeability and water saturation prediction

Anietie N. Okon et al.

Summary: The study developed a MIMO artificial neural network model based on well-logs data from 15 fields in the Niger Delta region to predict reservoir porosity, permeability, and water saturation. The model showed high correlation and low error values, outperforming existing models and providing insight into input variables' contribution factors.

MODELING EARTH SYSTEMS AND ENVIRONMENT (2021)

Add to Collection

Article Energy & Fuels

Role of Alkali Type in Chemical Loss and ASP-Flooding Enhanced Oil Recovery in Sandstone Formations

Huiying Zhong et al.

SPE RESERVOIR EVALUATION & ENGINEERING (2020)

Add to Collection

Article Energy & Fuels

Real-time determination of rheological properties of high over-balanced drilling fluid used for drilling ultra-deep gas wells using artificial neural network

Ibrahim Gomaa et al.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2020)

Add to Collection

Article Mathematics

Predicting Hard Rock Pillar Stability Using GBDT, XGBoost, and LightGBM Algorithms

Weizhang Liang et al.

MATHEMATICS (2020)

Add to Collection

Article Geochemistry & Geophysics

Estimation of Reservoir Porosity From Drilling Parameters Using Artificial Neural Networks

Ahmad Al-AbdulJabbar et al.

PETROPHYSICS (2020)

Add to Collection

Article Energy & Fuels

Optimization of models for a rapid identification of lithology while drilling-A win-win strategy based on machine learning

Jian Sun et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2019)

Add to Collection

Article Ecology

Hyperparameter tuning and performance assessment of statistical and machine-learning algorithms using spatial data

Patrick Schratz et al.

ECOLOGICAL MODELLING (2019)

Add to Collection

Article Energy & Fuels

Lithology identification using an optimized KNN clustering method based on entropy-weighed cosine distance in Mesozoic strata of Gaoqing field, Jiyang depression

Xidong Wang et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2018)

Add to Collection

Article Multidisciplinary Sciences

Application of high-dimensional feature selection: evaluation for genomic prediction in man

M. L. Bermingham et al.

SCIENTIFIC REPORTS (2015)

Add to Collection

Article Geosciences, Multidisciplinary

Air quality modelling using the Met Office Unified Model (AQUM OS24-26): model description and initial evaluation

N. H. Savage et al.

GEOSCIENTIFIC MODEL DEVELOPMENT (2013)

Add to Collection

Article Computer Science, Artificial Intelligence

An improved K-nearest-neighbor algorithm for text categorization

Shengyi Jiang et al.

EXPERT SYSTEMS WITH APPLICATIONS (2012)

Add to Collection

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)

Add to Collection

Article Health Care Sciences & Services

Internal validation of predictive models: Efficiency of some procedures for logistic regression analysis

EW Steyerberg et al.

JOURNAL OF CLINICAL EPIDEMIOLOGY (2001)

Add to Collection

© Peeref 2019-2024. All rights reserved.