Machine Learning in Oil and Gas Exploration: A Review

IEEE Access, Год журнала: 2024, Номер 12, С. 19035 - 19058

Опубликована: Янв. 1, 2024

A comprehensive assessment of machine learning applications is conducted to identify the developing trends for Artificial Intelligence (AI) in oil and gas sector, specifically focusing on geological geophysical exploration reservoir characterization. Critical areas, such as seismic data processing, facies lithofacies classification, prediction essential petrophysical properties (e.g., porosity, permeability, water saturation), are explored. Despite vital role these resource assessment, accurate remains challenging. This paper offers a detailed overview learning's involvement property prediction. It highlights its potential address various challenges, including predictive modelling, clustering tasks. Furthermore, review identifies unique barriers hindering widespread application exploration, uncertainties subsurface parameters, scale discrepancies, handling temporal spatial complexity. proposes solutions, practices contributing achieving optimal accuracy, outlines future research directions, providing nuanced understanding field's dynamics. Adopting robust management methods crucial enhancing operational efficiency an era marked by extensive generation. While acknowledging inherent limitations approaches, they surpass constraints traditional empirical analytical methods, establishing themselves versatile tools addressing industrial challenges. serves invaluable researchers venturing into less-charted territories this evolving field, offering valuable insights guidance research.

Язык: Английский

---

Advanced Permeability Prediction Through Two-Dimensional Geological Feature Image Extraction with CNN Regression from Well Logs Data

Mathematical Geosciences, Год журнала: 2025, Номер unknown

Опубликована: Янв. 14, 2025

Язык: Английский

---

Predicting shear wave velocity from conventional well logs with deep and hybrid machine learning algorithms

Journal of Petroleum Exploration and Production Technology, Год журнала: 2022, Номер 13(1), С. 19 - 42

Опубликована: Июль 11, 2022

Abstract Shear wave velocity ( V S ) data from sedimentary rock sequences is a prerequisite for implementing most mathematical models of petroleum engineering geomechanics. Extracting such by analyzing finite reservoir cores very costly and limited. The high cost sonic dipole advanced wellbore logging service its implementation in few wells field has placed many limitations on geomechanical modeling. On the other hand, shear tends to be nonlinearly related influencing variables, making empirical correlations unreliable prediction. Hybrid machine learning (HML) algorithms are well suited improving predictions variables. Recent advances deep (DL) suggest that they too should useful predicting large gas oil datasets but this yet verified. In study, 6622 records two giant Iranian Marun (MN#163 MN#225) used train HML DL algorithms. 2072 independent another (MN#179) verify prediction performance based eight well-log-derived Input variables standard full-set recorded parameters conventional available older wells. predicts supervised validation subset with root mean squared error (RMSE) 0.055 km/s coefficient determination (R 2 0.9729. It achieves similar accuracy when applied an unseen dataset. By comparing results, it apparent convolutional neural network model slightly outperforms tested. Both HLM substantially outperform five commonly relationships calculating p Field Concerns regarding model's integrity reproducibility were also addressed evaluating field. findings study can lead development knowledge production patterns sustainability reservoirs prevention enormous damage geomechanics through better understanding instability casing collapse problems. Graphical abstract

Язык: Английский

---

A novel deep learning method based on 2-D CNNs and GRUs for permeability prediction of tight sandstone

Geoenergy Science and Engineering, Год журнала: 2024, Номер 238, С. 212851 - 212851

Опубликована: Апрель 28, 2024

Язык: Английский

---

Hydrocarbon Potential Assessment of Carbonate-Bearing Sediments in a Meyal Oil Field, Pakistan: Insights from Logging Data Using Machine Learning and Quanti Elan Modeling

ACS Omega, Год журнала: 2022, Номер 7(43), С. 39375 - 39395

Опубликована: Окт. 17, 2022

The Meyal oil field (MOF) is among the most important contributors to Pakistan's and gas industry. Northern Potwar Basin located in foreland thrust bands of Himalayan mountains. current research aims delineate hydrocarbon potential, reservoir zone evaluation, lithofacies identification through utilization seven conventional well logs (M-01, M-08, M-10, M-12, M-13P, M-17). We employed advanced unsupervised machine-learning method self-organizing maps for novel Quanti Elan model technique comprehensive multimineral evaluation. shale volume, porosity, permeability, water saturation (petrophysical parameters) six wells were evaluated identify potential prospective zones. Well-logging data used this study provide a less costly objective systematic lithofacies. According SOM Pickett plot analyses, interest mostly made up pure limestone zone, whereas sandy dolomitic behavior with mixture content shows non-reservoir oil-water has good porosity values that range from 0 18%, but there high 45% production presence entire interval negative effect on permeability value, petrophysical properties are enough permit production. estimates, field's Sakesar Chorgali Formations promising reservoirs, new prospects drilling southern central portions eastern portion area recommended.

Язык: Английский

---

A hybrid wavelet–machine learning model for qanat water flow prediction

Acta Geophysica, Год журнала: 2022, Номер 71(4), С. 1895 - 1913

Опубликована: Ноя. 29, 2022

Язык: Английский

---

Combined deep-learning optimization predictive models for determining carbon dioxide solubility in ionic liquids

Journal of Industrial Information Integration, Год журнала: 2024, Номер 41, С. 100662 - 100662

Опубликована: Июль 11, 2024

Язык: Английский

---

Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms

Journal of Petroleum Exploration and Production Technology, Год журнала: 2022, Номер 13(2), С. 661 - 689

Опубликована: Дек. 7, 2022

Abstract Permeability is an important parameter in the petrophysical study of a reservoir and serves as key tool development oilfield. This while its prediction, especially carbonate reservoirs with their relatively lower levels permeability compared to sandstone reservoirs, complicated task it has larger contributions from heterogeneously distributed vugs fractures. In this respect, present research uses data two wells (well A for modeling well B assessing generalizability developed models) drilled into estimate using composite formulations based on least square support vector machine (LSSVM) multilayer extreme learning (MELM) coupled so-called cuckoo optimization algorithm (COA), particle swarm (PSO), genetic (GA). We further used simple forms convolutional neural network (CNN) LSSVM sake comparison. To end, firstly, Tukey method was applied identify remove outliers data. next step, second version nondominated sorting (NSGA-II) training (70% entire dataset, selected randomly) select optimal group features that most affect permeability. The results indicated although including more input parameters added resultant coefficient determination ( R 2 ) reducing error successively, yet slope latter reduction got much slow number exceeded 4. logs P-wave travel time, bulk density, neutron porosity, formation resistivity were identified effective estimating Evaluation root-mean-square (RMSE) shed light MELM-COA best-performing model testing stages, by (RMSE = 0.5600 mD, 0.9931) 0.6019 0.9919), respectively. assessment conducted prediction confirmed can provide reliable predictions achieving RMSE 0.9219 mD. Consequently, mentioned methodology strongly recommended predicting high accuracy similar depth intervals at other same field should required dataset be available.

Язык: Английский

---

New insights into permeability determination by coupling Stoneley wave propagation and conventional petrophysical logs in carbonate oil reservoirs

Scientific Reports, Год журнала: 2022, Номер 12(1)

Опубликована: Июль 8, 2022

The need to determine permeability at different stages of evaluation, completion, optimization Enhanced Oil Recovery (EOR) operations, and reservoir modeling management is reflected. Therefore, various methods with distinct efficiency for the evaluation have been proposed by engineers petroleum geologists. oil industry uses acoustic Nuclear Magnetic Resonance (NMR) loggings extensively quantitatively. However, because number available NMR logs not enough there a significant difficulty in their interpreting use has become very important. Direct, continuous, in-reservoir condition estimation unique feature Stoneley waves analysis as an technique. In this study, five intelligent mathematical methods, including Adaptive Network-Based Fuzzy Inference System (ANFIS), Least-Square Support Vector Machine (LSSVM), Radial Basis Function Neural Network (RBFNN), Multi-Layer Perceptron (MLPNN), Committee Intelligent (CMIS), performed calculating terms shear travel-time, effective porosity, bulk density lithological data one naturally-fractured low-porosity carbonate reservoirs located Southwest Iran. models improved three popular algorithms, Coupled Simulated Annealing (CSA), Particle Swarm Optimization (PSO), Genetic Algorithm (GA). Among developed models, CMIS most accurate model forecast compared core determination coefficient (R2) 0.87 average absolute deviation (AAD) 3.7. Comparing method techniques (i.e., Timur-Coates Schlumberger-Doll-Research (SDR)), superiority demonstrated. With model, diverse types fractures formations can be easily identified. As result, it claimed that presented study are great value petrophysicists working on simulation well completion.

Язык: Английский

---

Integrating hydraulic flow unit concept and adaptive neuro-fuzzy inference system to accurately estimate permeability in heterogeneous reservoirs: Case study Sif Fatima oilfield, southern Algeria

Journal of African Earth Sciences, Год журнала: 2023, Номер 206, С. 105027 - 105027

Опубликована: Авг. 3, 2023

Язык: Английский

---